diff --git a/Cargo.lock b/Cargo.lock index 1ba7ccb..a2ccf28 100644 --- a/Cargo.lock +++ b/Cargo.lock @@ -11,6 +11,12 @@ dependencies = [ "memchr", ] +[[package]] +name = "anes" +version = "0.1.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "4b46cbb362ab8752921c97e041f5e366ee6297bd428a31275b9fcf1e380f7299" + [[package]] name = "anstream" version = "0.6.19" @@ -73,18 +79,91 @@ version = "1.5.0" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "c08606f8c3cbf4ce6ec8e28fb0014a2c086708fe954eaa885384a6165172e7e8" +[[package]] +name = "bincode" +version = "1.3.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "b1f45e9417d87227c7a56d22e471c6206462cba514c7590c09aff4cf6d1ddcad" +dependencies = [ + "serde", +] + [[package]] name = "bitflags" version = "2.9.1" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "1b8e56985ec62d17e9c1001dc89c88ecd7dc08e47eba5ec7c29c7b5eeecde967" +[[package]] +name = "bumpalo" +version = "3.19.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "46c5e41b57b8bba42a04676d81cb89e9ee8e859a1a66f80a5a72e1cb76b34d43" + +[[package]] +name = "cast" +version = "0.3.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "37b2a672a2cb129a2e41c10b1224bb368f9f37a2b16b612598138befd7b37eb5" + [[package]] name = "cfg-if" version = "1.0.1" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "9555578bc9e57714c812a1f84e4fc5b4d21fcb063490c624de019f7464c91268" +[[package]] +name = "ciborium" +version = "0.2.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "42e69ffd6f0917f5c029256a24d0161db17cea3997d185db0d35926308770f0e" +dependencies = [ + "ciborium-io", + "ciborium-ll", + "serde", +] + +[[package]] +name = "ciborium-io" +version = "0.2.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "05afea1e0a06c9be33d539b876f1ce3692f4afea2cb41f740e7743225ed1c757" + +[[package]] +name = "ciborium-ll" +version = "0.2.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "57663b653d948a338bfb3eeba9bb2fd5fcfaecb9e199e87e1eda4d9e8b240fd9" +dependencies = [ + "ciborium-io", + "half", +] + +[[package]] +name = "clap" +version = "4.5.41" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "be92d32e80243a54711e5d7ce823c35c41c9d929dc4ab58e1276f625841aadf9" +dependencies = [ + "clap_builder", +] + +[[package]] +name = "clap_builder" +version = "4.5.41" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "707eab41e9622f9139419d573eca0900137718000c517d47da73045f54331c3d" +dependencies = [ + "anstyle", + "clap_lex", +] + +[[package]] +name = "clap_lex" +version = "0.7.5" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "b94f61472cee1439c0b966b47e3aca9ae07e45d070759512cd390ea2bebc6675" + [[package]] name = "colog" version = "1.3.0" @@ -112,12 +191,73 @@ dependencies = [ "windows-sys 0.59.0", ] +[[package]] +name = "criterion" +version = "0.5.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "f2b12d017a929603d80db1831cd3a24082f8137ce19c69e6447f54f5fc8d692f" +dependencies = [ + "anes", + "cast", + "ciborium", + "clap", + "criterion-plot", + "is-terminal", + "itertools", + "num-traits", + "once_cell", + "oorandom", + "plotters", + "rayon", + "regex", + "serde", + "serde_derive", + "serde_json", + "tinytemplate", + "walkdir", +] + +[[package]] +name = "criterion-plot" +version = "0.5.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "6b50826342786a51a89e2da3a28f1c32b06e387201bc2d19791f622c673706b1" +dependencies = [ + "cast", + "itertools", +] + +[[package]] +name = "crossbeam-deque" +version = "0.8.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "9dd111b7b7f7d55b72c0a6ae361660ee5853c9af73f70c3c2ef6858b950e2e51" +dependencies = [ + "crossbeam-epoch", + "crossbeam-utils", +] + +[[package]] +name = "crossbeam-epoch" +version = "0.9.18" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "5b82ac4a3c2ca9c3460964f020e1402edd5753411d7737aa39c3714ad1b5420e" +dependencies = [ + "crossbeam-utils", +] + [[package]] name = "crossbeam-utils" version = "0.8.21" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "d0a5c400df2834b80a4c3327b3aad3a4c4cd4de0629063962b03235697506a28" +[[package]] +name = "crunchy" +version = "0.2.4" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "460fbee9c2c2f33933d720630a6a0bac33ba7053db5344fac858d4b8952d77d5" + [[package]] name = "csv" version = "1.3.1" @@ -230,6 +370,12 @@ version = "2.3.0" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "37909eebbb50d72f9059c3b6d82c0463f2ff062c9e95845c43a6c9c0355411be" +[[package]] +name = "fnv" +version = "1.0.7" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "3f9eec918d3f24069decb9af1554cad7c880e2da24a9afd88aca000531ab82c1" + [[package]] name = "getrandom" version = "0.3.3" @@ -242,6 +388,16 @@ dependencies = [ "wasi", ] +[[package]] +name = "half" +version = "2.6.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "459196ed295495a68f7d7fe1d84f6c4b7ff0e21fe3017b2f283c6fac3ad803c9" +dependencies = [ + "cfg-if", + "crunchy", +] + [[package]] name = "hashbrown" version = "0.14.5" @@ -260,6 +416,12 @@ version = "0.5.0" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "2304e00983f87ffb38b55b444b5e3b60a884b5d30c0fca7d82fe33449bbe55ea" +[[package]] +name = "hermit-abi" +version = "0.5.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "fc0fef456e4baa96da950455cd02c081ca953b141298e41db3fc7e36b1da849c" + [[package]] name = "home" version = "0.5.11" @@ -279,12 +441,32 @@ dependencies = [ "hashbrown 0.15.4", ] +[[package]] +name = "is-terminal" +version = "0.4.16" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "e04d7f318608d35d4b61ddd75cbdaee86b023ebe2bd5a66ee0915f0bf93095a9" +dependencies = [ + "hermit-abi", + "libc", + "windows-sys 0.59.0", +] + [[package]] name = "is_terminal_polyfill" version = "1.70.1" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "7943c866cc5cd64cbc25b2e01621d07fa8eb2a1a23160ee81ce38704e97b8ecf" +[[package]] +name = "itertools" +version = "0.10.5" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "b0fd2260e829bddf4cb6ea802289de2f86d6a7a690192fbe91b3f46e0f2c8473" +dependencies = [ + "either", +] + [[package]] name = "itoa" version = "1.0.15" @@ -315,6 +497,16 @@ dependencies = [ "syn", ] +[[package]] +name = "js-sys" +version = "0.3.77" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "1cfaf33c695fc6e08064efbc1f72ec937429614f25eef83af942d0e227c3a28f" +dependencies = [ + "once_cell", + "wasm-bindgen", +] + [[package]] name = "lazy_static" version = "1.5.0" @@ -327,6 +519,12 @@ version = "0.2.174" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "1171693293099992e19cddea4e8b849964e9846f4acee11b3948bcc337be8776" +[[package]] +name = "linked-hash-map" +version = "0.5.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "0717cef1bc8b636c6e1c1bbdefc09e6322da8a9321966e8928ef80d20f7f770f" + [[package]] name = "linux-raw-sys" version = "0.4.15" @@ -355,12 +553,46 @@ version = "0.4.27" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "13dc2df351e3202783a1fe0d44375f7295ffb4049267b0f3018346dc122a1d94" +[[package]] +name = "lru-cache" +version = "0.1.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "31e24f1ad8321ca0e8a1e0ac13f23cb668e6f5466c2c57319f6a5cf1cc8e3b1c" +dependencies = [ + "linked-hash-map", +] + [[package]] name = "memchr" version = "2.7.5" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "32a282da65faaf38286cf3be983213fcf1d2e2a58700e808f83f4ea9a4804bc0" +[[package]] +name = "minimal-lexical" +version = "0.2.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "68354c5c6bd36d73ff3feceb05efa59b6acb7626617f4962be322a825e61f79a" + +[[package]] +name = "nom" +version = "7.1.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "d273983c5a657a70a3e8f2a01329822f3b8c8172b73826411a55751e404a0a4a" +dependencies = [ + "memchr", + "minimal-lexical", +] + +[[package]] +name = "num-traits" +version = "0.2.19" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "071dfc062690e90b734c0b2273ce72ad0ffa95f0c74596bc250dcfd960262841" +dependencies = [ + "autocfg", +] + [[package]] name = "once_cell" version = "1.21.3" @@ -373,6 +605,18 @@ version = "1.70.1" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "a4895175b425cb1f87721b59f0f286c2092bd4af812243672510e1ac53e2e0ad" +[[package]] +name = "oncemutex" +version = "0.1.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "44d11de466f4a3006fe8a5e7ec84e93b79c70cb992ae0aa0eb631ad2df8abfe2" + +[[package]] +name = "oorandom" +version = "11.1.5" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "d6790f58c7ff633d8771f42965289203411a5e5c68388703c06e14f24770b41e" + [[package]] name = "parking_lot_core" version = "0.9.11" @@ -386,6 +630,54 @@ dependencies = [ "windows-targets 0.52.6", ] +[[package]] +name = "phonenumber" +version = "0.3.7+8.13.52" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "2247167dc3741816fdd4d3690e97f56a892a264b44f4c702078b72d1f8b6bd40" +dependencies = [ + "bincode", + "either", + "fnv", + "nom", + "once_cell", + "quick-xml", + "regex", + "regex-cache", + "serde", + "serde_derive", + "strum 0.26.3", + "thiserror 1.0.69", +] + +[[package]] +name = "plotters" +version = "0.3.7" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "5aeb6f403d7a4911efb1e33402027fc44f29b5bf6def3effcc22d7bb75f2b747" +dependencies = [ + "num-traits", + "plotters-backend", + "plotters-svg", + "wasm-bindgen", + "web-sys", +] + +[[package]] +name = "plotters-backend" +version = "0.3.7" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "df42e13c12958a16b3f7f4386b9ab1f3e7933914ecea48da7139435263a4172a" + +[[package]] +name = "plotters-svg" +version = "0.3.7" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "51bae2ac328883f7acdfea3d66a7c35751187f870bc81f94563733a154d7a670" +dependencies = [ + "plotters-backend", +] + [[package]] name = "portable-atomic" version = "1.11.1" @@ -461,6 +753,15 @@ dependencies = [ "thiserror 1.0.69", ] +[[package]] +name = "quick-xml" +version = "0.37.5" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "331e97a1af0bf59823e6eadffe373d7b27f485be8748f71471c662c1f269b7fb" +dependencies = [ + "memchr", +] + [[package]] name = "quote" version = "1.0.40" @@ -476,6 +777,26 @@ version = "5.3.0" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "69cdb34c158ceb288df11e18b4bd39de994f6657d83847bdffdbd7f346754b0f" +[[package]] +name = "rayon" +version = "1.10.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "b418a60154510ca1a002a752ca9714984e21e4241e804d32555251faf8b78ffa" +dependencies = [ + "either", + "rayon-core", +] + +[[package]] +name = "rayon-core" +version = "1.12.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "1465873a3dfdaa8ae7cb14b4383657caab0b3e8a0aa9ae8e04b044854c8dfce2" +dependencies = [ + "crossbeam-deque", + "crossbeam-utils", +] + [[package]] name = "redox_syscall" version = "0.5.13" @@ -494,7 +815,7 @@ dependencies = [ "aho-corasick", "memchr", "regex-automata", - "regex-syntax", + "regex-syntax 0.8.5", ] [[package]] @@ -505,9 +826,27 @@ checksum = "809e8dc61f6de73b46c85f4c96486310fe304c434cfa43669d7b40f711150908" dependencies = [ "aho-corasick", "memchr", - "regex-syntax", + "regex-syntax 0.8.5", ] +[[package]] +name = "regex-cache" +version = "0.2.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "2f7b62d69743b8b94f353b6b7c3deb4c5582828328bcb8d5fedf214373808793" +dependencies = [ + "lru-cache", + "oncemutex", + "regex", + "regex-syntax 0.6.29", +] + +[[package]] +name = "regex-syntax" +version = "0.6.29" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "f162c6dd7b008981e4d40210aca20b4bd0f9b60ca9271061b07f78537722f2e1" + [[package]] name = "regex-syntax" version = "0.8.5" @@ -519,16 +858,18 @@ name = "rlibphonenumber" version = "0.1.0" dependencies = [ "colog", + "criterion", "dashmap", "dec_from_char", "env_logger", "fast-cat", "itoa", "log", + "phonenumber", "protobuf", "protobuf-codegen", "regex", - "strum", + "strum 0.27.1", "thiserror 2.0.12", ] @@ -570,6 +911,15 @@ version = "1.0.20" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "28d3b2b1366ec20994f1fd18c3c594f05c5dd4bc44d8bb0c1c632c8d6829481f" +[[package]] +name = "same-file" +version = "1.0.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "93fc1dc3aaa9bfed95e02e6eadabb4baf7e3078b0bd1b4d7b6b0b68378900502" +dependencies = [ + "winapi-util", +] + [[package]] name = "scopeguard" version = "1.2.0" @@ -596,19 +946,53 @@ dependencies = [ "syn", ] +[[package]] +name = "serde_json" +version = "1.0.140" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "20068b6e96dc6c9bd23e01df8827e6c7e1f2fddd43c21810382803c136b99373" +dependencies = [ + "itoa", + "memchr", + "ryu", + "serde", +] + [[package]] name = "smallvec" version = "1.15.1" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "67b1b7a3b5fe4f1376887184045fcf45c69e92af734b7aaddc05fb777b6fbd03" +[[package]] +name = "strum" +version = "0.26.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "8fec0f0aef304996cf250b31b5a10dee7980c85da9d759361292b8bca5a18f06" +dependencies = [ + "strum_macros 0.26.4", +] + [[package]] name = "strum" version = "0.27.1" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "f64def088c51c9510a8579e3c5d67c65349dcf755e5479ad3d010aa6454e2c32" dependencies = [ - "strum_macros", + "strum_macros 0.27.1", +] + +[[package]] +name = "strum_macros" +version = "0.26.4" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "4c6bee85a5a24955dc440386795aa378cd9cf82acd5f764469152d2270e581be" +dependencies = [ + "heck", + "proc-macro2", + "quote", + "rustversion", + "syn", ] [[package]] @@ -688,6 +1072,16 @@ dependencies = [ "syn", ] +[[package]] +name = "tinytemplate" +version = "1.2.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "be4d6b5f19ff7664e8c98d03e2139cb510db9b0a60b55f8e8709b689d939b6bc" +dependencies = [ + "serde", + "serde_json", +] + [[package]] name = "unicode-ident" version = "1.0.18" @@ -700,6 +1094,16 @@ version = "0.2.2" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "06abde3611657adf66d383f00b093d7faecc7fa57071cce2578660c9f1010821" +[[package]] +name = "walkdir" +version = "2.5.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "29790946404f91d9c5d06f9874efddea1dc06c5efe94541a7d6863108e3a5e4b" +dependencies = [ + "same-file", + "winapi-util", +] + [[package]] name = "wasi" version = "0.14.2+wasi-0.2.4" @@ -709,6 +1113,74 @@ dependencies = [ "wit-bindgen-rt", ] +[[package]] +name = "wasm-bindgen" +version = "0.2.100" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "1edc8929d7499fc4e8f0be2262a241556cfc54a0bea223790e71446f2aab1ef5" +dependencies = [ + "cfg-if", + "once_cell", + "rustversion", + "wasm-bindgen-macro", +] + +[[package]] +name = "wasm-bindgen-backend" +version = "0.2.100" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "2f0a0651a5c2bc21487bde11ee802ccaf4c51935d0d3d42a6101f98161700bc6" +dependencies = [ + "bumpalo", + "log", + "proc-macro2", + "quote", + "syn", + "wasm-bindgen-shared", +] + +[[package]] +name = "wasm-bindgen-macro" +version = "0.2.100" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "7fe63fc6d09ed3792bd0897b314f53de8e16568c2b3f7982f468c0bf9bd0b407" +dependencies = [ + "quote", + "wasm-bindgen-macro-support", +] + +[[package]] +name = "wasm-bindgen-macro-support" +version = "0.2.100" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "8ae87ea40c9f689fc23f209965b6fb8a99ad69aeeb0231408be24920604395de" +dependencies = [ + "proc-macro2", + "quote", + "syn", + "wasm-bindgen-backend", + "wasm-bindgen-shared", +] + +[[package]] +name = "wasm-bindgen-shared" +version = "0.2.100" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "1a05d73b933a847d6cccdda8f838a22ff101ad9bf93e33684f39c1f5f0eece3d" +dependencies = [ + "unicode-ident", +] + +[[package]] +name = "web-sys" +version = "0.3.77" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "33b6dd2ef9186f1f2072e409e99cd22a975331a6b3591b12c764e0e55c60d5d2" +dependencies = [ + "js-sys", + "wasm-bindgen", +] + [[package]] name = "which" version = "4.4.2" @@ -721,6 +1193,15 @@ dependencies = [ "rustix 0.38.44", ] +[[package]] +name = "winapi-util" +version = "0.1.9" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "cf221c93e13a30d793f7645a0e7762c55d169dbb0a49671918a2319d289b10bb" +dependencies = [ + "windows-sys 0.59.0", +] + [[package]] name = "windows-sys" version = "0.59.0" diff --git a/Cargo.toml b/Cargo.toml index cea18f6..829e66c 100644 --- a/Cargo.toml +++ b/Cargo.toml @@ -34,4 +34,14 @@ protobuf-codegen = "3.7.2" [dev-dependencies] colog = "1.3.0" -env_logger = "0.11.8" \ No newline at end of file +env_logger = "0.11.8" +criterion = "0.5" +phonenumber = "0.3" + +[[bench]] +name = "format_bench" +harness = false + +[[bench]] +name = "parsing_bench" +harness = false \ No newline at end of file diff --git a/Readme.md b/Readme.md index cf3e420..bfd5a8b 100644 --- a/Readme.md +++ b/Readme.md @@ -18,6 +18,27 @@ This library gives you access to a wide range of functionalities, including: * Determining the number type (e.g., Mobile, Fixed-line, Toll-free). * Providing example numbers for every country. +## Performance + +The following benchmarks were run against the `rust-phonenumber` crate. All tests were performed on the same machine and dataset. *Lower is better.* + +### Formatting + +| Format | rlibphonenumber (this crate) | rust-phonenumber | Performance Gain | +|:---|:---:|:---:|:---:| +| **E164** | **~78 ns** | ~2.59 µs | **~33x faster** | +| **International** | **~1.34 µs** | ~3.21 µs | **~2.4x faster** | +| **National** | **~2.33 µs** | ~4.87 µs | **~2.1x faster** | +| **RFC3966** | **~1.62 µs** | ~3.47 µs | **~2.1x faster** | + +### Parsing + +| Task | rlibphonenumber (this crate) | rust-phonenumber | Performance Gain | +|:--- |:---:|:---:|:---:| +| **Parse** | **~11.60 µs** | ~13.45 µs | **~16% faster** | + +This significant performance advantage is achieved through a focus on minimizing allocations, a more direct implementation path, and the use of modern tooling for metadata generation. + ## Current Status The project is currently in its initial phase of development. The core functionalities are being ported module by module to ensure quality and consistency. diff --git a/benches/format_bench.rs b/benches/format_bench.rs new file mode 100644 index 0000000..49b915e --- /dev/null +++ b/benches/format_bench.rs @@ -0,0 +1,76 @@ +use criterion::{Criterion, black_box, criterion_group, criterion_main}; + +use rlibphonenumber::{PhoneNumberFormat, PHONE_NUMBER_UTIL}; + +use phonenumber::{ + self as rlp, + country::Id::{self, AU}, Mode, +}; + +type TestEntity = (&'static str, &'static str, Id); + +fn setup_numbers() -> Vec { + vec![("0011 54 9 11 8765 4321 ext. 1234", "AU", AU)] +} + +fn convert_to_rlp_numbers(numbers: &[TestEntity]) -> Vec { + numbers + .iter() + .map(|s| rlp::parse(Some(s.2), s.0).unwrap()) + .collect() +} + +fn convert_to_rlibphonenumber_numbers( + numbers: &[TestEntity], +) -> Vec { + numbers + .iter() + .map(|s| PHONE_NUMBER_UTIL.parse(s.0, s.1).unwrap()) + .collect() +} + +fn formatting_benchmark(c: &mut Criterion) { + let numbers = setup_numbers(); + let rlp_numbers = convert_to_rlp_numbers(&numbers); + let numbers = convert_to_rlibphonenumber_numbers(&numbers); + + let mut group = c.benchmark_group("Formatting Comparison"); + + let mut test = |format_a: PhoneNumberFormat, format_b: Mode| { + group.bench_function(format!("rlibphonenumber: format({:?})", format_a), |b| { + b.iter(|| { + for number in &numbers { + PHONE_NUMBER_UTIL + .format(black_box(number), black_box(format_a)) + .unwrap(); + } + }) + }); + + group.bench_function(format!("rust-phonenumber: format({:?})", format_b), |b| { + b.iter(|| { + for number in &rlp_numbers { + rlp::format(black_box(number)).mode(format_b).to_string(); + } + }) + }); + + for (number_a, number_b) in rlp_numbers.iter().zip(numbers.iter()) { + assert_eq!( + rlp::format(number_a).mode(format_b).to_string(), + PHONE_NUMBER_UTIL + .format(number_b, format_a) + .unwrap() + ); + } + }; + + test(PhoneNumberFormat::E164, Mode::E164); + test(PhoneNumberFormat::International, Mode::International); + test(PhoneNumberFormat::National, Mode::National); + test(PhoneNumberFormat::RFC3966, Mode::Rfc3966); + group.finish(); +} + +criterion_group!(benches, formatting_benchmark); +criterion_main!(benches); diff --git a/benches/parsing_bench.rs b/benches/parsing_bench.rs new file mode 100644 index 0000000..6fa7afe --- /dev/null +++ b/benches/parsing_bench.rs @@ -0,0 +1,73 @@ +// benches/parsing_benchmark.rs + +use criterion::{black_box, criterion_group, criterion_main, Criterion}; + +// --- Импорты из вашей библиотеки --- +use rlibphonenumber::PHONE_NUMBER_UTIL; + +// --- Импорты из внешней библиотеки --- +use phonenumber::{self as rlp, country::Id}; + +// Тип для наших тестовых данных: (строка_номера, регион_для_вас, регион_для_rlp) +type TestEntity = (&'static str, &'static str, Id); + +/// Подготавливает разнообразный набор данных для тестирования парсинга. +/// Это дает более объективную оценку, чем один номер. +fn setup_parsing_data() -> Vec { + use phonenumber::country::Id::*; + vec![ + // Оригинальный номер из вашего примера + ("0011 54 9 11 8765 4321 ext. 1234", "AU", AU), + // Простой номер США в национальном формате + ("(650) 253-0000", "US", US), + // Номер Великобритании в международном формате со знаком + + ("+44 20 8765 4321", "GB", GB), + // Номер Великобритании с национальным префиксом (ведущий ноль) + ("020 8765 4321", "GB", GB), + // Сложный мобильный номер Аргентины + ("011 15-1234-5678", "AR", AR), + // Итальянский номер со значащим ведущим нулем + ("02 12345678", "IT", IT), + // "Vanity" номер (с буквами) + ("1-800-FLOWERS", "US", US), + // Короткий номер, который может быть валидным в некоторых регионах + ("12345", "DE", DE), + ] +} + +fn parsing_benchmark(c: &mut Criterion) { + // Получаем наш набор тестовых данных + let numbers_to_parse = setup_parsing_data(); + + let mut group = c.benchmark_group("Parsing Comparison"); + + // --- Бенчмарк для вашей библиотеки rlibphonenumber --- + group.bench_function("rlibphonenumber: parse()", |b| { + // b.iter() запускает код в цикле много раз для замера + b.iter(|| { + // Итерируемся по всем номерам в нашем наборе + for (number_str, region, _) in &numbers_to_parse { + // Вызываем parse, обернув аргументы в black_box. + // Это гарантирует, что компилятор не оптимизирует вызов. + // Мы не используем результат, так как нас интересует только скорость выполнения. + let _ = PHONE_NUMBER_UTIL.parse(black_box(number_str), black_box(region)); + } + }) + }); + + // --- Бенчмарк для библиотеки rust-phonenumber --- + group.bench_function("rust-phonenumber: parse()", |b| { + b.iter(|| { + for (number_str, _, region_id) in &numbers_to_parse { + // Аналогичный вызов для второй библиотеки + let _ = rlp::parse(black_box(Some(*region_id)), black_box(number_str)); + } + }) + }); + + group.finish(); +} + +// Макросы для регистрации и запуска бенчмарка +criterion_group!(benches, parsing_benchmark); +criterion_main!(benches); \ No newline at end of file diff --git a/src/interfaces/mod.rs b/src/interfaces/mod.rs index 14abd41..d4f41c0 100644 --- a/src/interfaces/mod.rs +++ b/src/interfaces/mod.rs @@ -13,7 +13,7 @@ // See the License for the specific language governing permissions and // limitations under the License. -use crate::phonemetadata::PhoneNumberDesc; +use crate::PhoneNumberDesc; /// Internal phonenumber matching API used to isolate the underlying /// implementation of the matcher and allow different implementations to be diff --git a/src/lib.rs b/src/lib.rs index 7d3d667..0f63064 100644 --- a/src/lib.rs +++ b/src/lib.rs @@ -41,9 +41,24 @@ pub use phonenumberutil::{ ExtractNumberResult, PhoneNumberUtil }, - errors, - enums, + errors::{ + ExtractNumberError, + GetExampleNumberError, + ParseError, + NotANumberError, + ValidationError, + InternalLogicError, + InvalidNumberError, + InvalidMetadataForValidRegionError + }, + enums::{ + MatchType, + PhoneNumberType, + NumberLengthType, + PhoneNumberFormat + }, }; -pub use generated::proto::phonemetadata; -pub use generated::proto::phonenumber; +pub use generated::proto::phonemetadata::{*}; +pub use generated::proto::phonenumber::PhoneNumber; +pub use generated::proto::phonenumber::phone_number::CountryCodeSource; mod tests; diff --git a/src/phonenumberutil/helper_functions.rs b/src/phonenumberutil/helper_functions.rs index 80ed092..15ac854 100644 --- a/src/phonenumberutil/helper_functions.rs +++ b/src/phonenumberutil/helper_functions.rs @@ -20,8 +20,8 @@ use strum::IntoEnumIterator; use crate::{ interfaces::MatcherApi, generated::metadata::METADATA, - phonemetadata::{PhoneMetadata, PhoneMetadataCollection, PhoneNumberDesc}, - phonenumber::PhoneNumber, + PhoneMetadata, PhoneMetadataCollection, PhoneNumberDesc, + PhoneNumber, }; diff --git a/src/phonenumberutil/helper_types.rs b/src/phonenumberutil/helper_types.rs index ac679cb..243a7d7 100644 --- a/src/phonenumberutil/helper_types.rs +++ b/src/phonenumberutil/helper_types.rs @@ -16,7 +16,7 @@ use std::borrow::Cow; -use crate::phonenumber::phone_number::CountryCodeSource; +use crate::CountryCodeSource; #[derive(Debug)] pub struct PhoneNumberWithCountryCodeSource<'a> { diff --git a/src/phonenumberutil/mod.rs b/src/phonenumberutil/mod.rs index aa08db8..7d85cea 100644 --- a/src/phonenumberutil/mod.rs +++ b/src/phonenumberutil/mod.rs @@ -26,6 +26,7 @@ use std::sync::LazyLock; pub use enums::{MatchType, PhoneNumberFormat, PhoneNumberType, NumberLengthType}; use crate::phonenumberutil::phonenumberutil::PhoneNumberUtil; +/// Singleton instance of phone number util for general use pub static PHONE_NUMBER_UTIL: LazyLock = LazyLock::new(|| { PhoneNumberUtil::new() }); \ No newline at end of file diff --git a/src/phonenumberutil/phonenumberutil.rs b/src/phonenumberutil/phonenumberutil.rs index 46ce6a6..2849dda 100644 --- a/src/phonenumberutil/phonenumberutil.rs +++ b/src/phonenumberutil/phonenumberutil.rs @@ -21,11 +21,11 @@ use std::{ use super::phone_number_regexps_and_mappings::PhoneNumberRegExpsAndMappings; use crate::{ - errors::NotANumberError, region_code::RegionCode, interfaces::MatcherApi, macros::owned_from_cow_or, phonemetadata::PhoneMetadataCollection, phonenumberutil::{ + region_code::RegionCode, interfaces::MatcherApi, macros::owned_from_cow_or, PhoneMetadataCollection, phonenumberutil::{ errors::{ ExtractNumberError, GetExampleNumberError, InternalLogicError, InvalidMetadataForValidRegionError, InvalidNumberError, ParseError, - ValidationError, + ValidationError, NotANumberError }, helper_constants::{ DEFAULT_EXTN_PREFIX, MAX_LENGTH_COUNTRY_CODE, MAX_LENGTH_FOR_NSN, MIN_LENGTH_FOR_NSN, NANPA_COUNTRY_CODE, PLUS_SIGN, REGION_CODE_FOR_NON_GEO_ENTITY, RFC3966_EXTN_PREFIX, @@ -37,8 +37,8 @@ use crate::{ test_number_length_with_unknown_type, }, helper_types::{PhoneNumberWithCountryCodeSource}, MatchType, PhoneNumberFormat, PhoneNumberType, NumberLengthType }, - phonemetadata::{NumberFormat, PhoneMetadata, PhoneNumberDesc}, - phonenumber::{phone_number::CountryCodeSource, PhoneNumber}, + NumberFormat, PhoneMetadata, PhoneNumberDesc, + CountryCodeSource, PhoneNumber, regex_based_matcher::RegexBasedMatcher, regex_util::{RegexConsume, RegexFullMatch}, regexp_cache::ErrorInvalidRegex, string_util::strip_cow_prefix }; @@ -189,10 +189,11 @@ impl PhoneNumberUtil { /// # Arguments /// /// * `region_code` - The region code for which to get the types. - pub fn get_supported_types_for_region( + pub fn get_supported_types_for_region>( &self, - region_code: &str, + region_code: S, ) -> Option> { + let region_code = region_code.as_ref(); self.region_to_metadata_map .get(region_code) .and_then(|metadata| Some(get_supported_types_for_metadata(metadata))) @@ -227,12 +228,12 @@ impl PhoneNumberUtil { return &self.reg_exps.extn_patterns_for_matching; } - pub fn starts_with_plus_chars_pattern(&self, phone_number: &str) -> bool { - self.reg_exps.plus_chars_pattern.matches_start(phone_number) + pub fn starts_with_plus_chars_pattern>(&self, phone_number: S) -> bool { + self.reg_exps.plus_chars_pattern.matches_start(phone_number.as_ref()) } - pub fn contains_only_valid_digits(&self, s: &str) -> bool { - self.reg_exps.digits_pattern.full_match(s) + pub fn contains_only_valid_digits>(&self, s: S) -> bool { + self.reg_exps.digits_pattern.full_match(s.as_ref()) } pub(crate) fn trim_unwanted_end_chars<'a>(&self, phone_number: &'a str) -> &'a str { @@ -704,11 +705,12 @@ impl PhoneNumberUtil { /// /// * `phone_number` - The phone number to format. /// * `carrier_code` - The carrier code to include in the formatted number. - pub fn format_national_number_with_carrier_code( + pub fn format_national_number_with_carrier_code>( &self, phone_number: &PhoneNumber, - carrier_code: &str, + carrier_code: S, ) -> RegexResult { + let carrier_code= carrier_code.as_ref(); let country_calling_code = phone_number.country_code(); let national_significant_number = self.get_national_significant_number(phone_number); let region_code = self.get_region_code_for_country_code(country_calling_code); @@ -752,15 +754,15 @@ impl PhoneNumberUtil { /// /// * `phone_number` - The phone number to format. /// * `fallback_carrier_code` - The carrier code to use if a preferred one is not available. - pub fn format_national_number_with_preferred_carrier_code( + pub fn format_national_number_with_preferred_carrier_code>( &self, phone_number: &PhoneNumber, - fallback_carrier_code: &str, + fallback_carrier_code: S, ) -> RegexResult { let carrier_code = if !phone_number.preferred_domestic_carrier_code().is_empty() { phone_number.preferred_domestic_carrier_code() } else { - fallback_carrier_code + fallback_carrier_code.as_ref() }; self.format_national_number_with_carrier_code(phone_number, carrier_code) } @@ -782,12 +784,13 @@ impl PhoneNumberUtil { /// * `phone_number` - The phone number to format. /// * `calling_from` - The region where the call is being placed. /// * `with_formatting` - Whether to include formatting characters. - pub fn format_number_for_mobile_dialing<'b>( + pub fn format_number_for_mobile_dialing<'b, S: AsRef>( &self, phone_number: &'b PhoneNumber, - calling_from: &str, + calling_from: S, with_formatting: bool, ) -> InternalLogicResult> { + let calling_from = calling_from.as_ref(); let country_calling_code = phone_number.country_code(); if !self.has_valid_country_calling_code(country_calling_code) { return if phone_number.has_raw_input() { @@ -1120,8 +1123,8 @@ impl PhoneNumberUtil { /// # Arguments /// /// * `phone_number` - The phone number string to normalize. - pub fn normalize_digits_only<'a>(&self, phone_number: &'a str) -> String { - dec_from_char::normalize_decimals_filtering(phone_number) + pub fn normalize_digits_only>(&self, phone_number: S) -> String { + dec_from_char::normalize_decimals_filtering(phone_number.as_ref()) } /// Formats a phone number for calling from outside the number's region. @@ -1130,11 +1133,12 @@ impl PhoneNumberUtil { /// /// * `phone_number` - The phone number to format. /// * `calling_from` - The region where the call is being placed from. - pub fn format_out_of_country_calling_number<'a>( + pub fn format_out_of_country_calling_number<'a, S: AsRef>( &self, phone_number: &'a PhoneNumber, - calling_from: &str, + calling_from: S, ) -> InternalLogicResult> { + let calling_from = calling_from.as_ref(); let Some(metadata_calling_from) = self.region_to_metadata_map.get(calling_from) else { trace!( "Trying to format number from invalid region {calling_from}\ @@ -1253,11 +1257,12 @@ impl PhoneNumberUtil { /// /// * `phone_number` - The phone number to format. /// * `region_calling_from` - The region from which the number was originally parsed. - pub fn format_in_original_format<'a>( + pub fn format_in_original_format<'a, S: AsRef>( &self, phone_number: &'a PhoneNumber, - region_calling_from: &str, + region_calling_from: S, ) -> InternalLogicResult> { + let region_calling_from = region_calling_from.as_ref(); if phone_number.has_raw_input() && !self.has_formatting_pattern_for_number(phone_number)? { // We check if we have the formatting pattern because without that, we might // format the number as a group without national prefix. @@ -1404,8 +1409,10 @@ impl PhoneNumberUtil { /// /// * `number_to_parse` - The number string to parse. /// * `default_region` - The region to assume if the number is not in international format. - pub fn parse(&self, number_to_parse: &str, default_region: &str) -> ParseResult { - self.parse_helper(number_to_parse, default_region, false, true) + pub fn parse, S2: AsRef>( + &self, number_to_parse: S1, default_region: S2 + ) -> ParseResult { + self.parse_helper(number_to_parse.as_ref(), default_region.as_ref(), false, true) } /// Parses a string into a phone number object, keeping the raw input. @@ -1414,12 +1421,12 @@ impl PhoneNumberUtil { /// /// * `number_to_parse` - The number string to parse. /// * `default_region` - The region to assume if the number is not in international format. - pub fn parse_and_keep_raw_input( + pub fn parse_and_keep_raw_input, S2: AsRef>( &self, - number_to_parse: &str, - default_region: &str, + number_to_parse: S1, + default_region: S2, ) -> ParseResult { - self.parse_helper(number_to_parse, default_region, true, true) + self.parse_helper(number_to_parse.as_ref(), default_region.as_ref(), true, true) } /// Checks if a phone number is valid. @@ -1438,11 +1445,12 @@ impl PhoneNumberUtil { /// /// * `phone_number` - The phone number to validate. /// * `region_code` - The region to validate against. - pub fn is_valid_number_for_region( + pub fn is_valid_number_for_region>( &self, phone_number: &PhoneNumber, - region_code: &str, + region_code: S, ) -> bool { + let region_code = region_code.as_ref(); let country_code = phone_number.country_code(); let metadata = self.get_metadata_for_region_or_calling_code(country_code, region_code); if let Some(metadata) = metadata.filter(|metadata| { @@ -1465,11 +1473,12 @@ impl PhoneNumberUtil { /// /// * `phone_number` - The phone number to format. /// * `calling_from` - The region where the call is being placed from. - pub fn format_out_of_country_keeping_alpha_chars<'a>( + pub fn format_out_of_country_keeping_alpha_chars<'a, S: AsRef>( &self, phone_number: &'a PhoneNumber, - calling_from: &str, + calling_from: S, ) -> InternalLogicResult> { + let calling_from = calling_from.as_ref(); // If there is no raw input, then we can't keep alpha characters because there // aren't any. In this case, we return FormatOutOfCountryCallingNumber. if phone_number.raw_input().is_empty() { @@ -1797,11 +1806,13 @@ impl PhoneNumberUtil { /// /// * `number` - The number string to check. /// * `region_code` - The region to check against. - pub fn is_possible_number_for_string( + pub fn is_possible_number_for_string, S2: AsRef>( &self, - phone_number: &str, - region_dialing_from: &str, + phone_number: S1, + region_dialing_from: S2, ) -> bool { + let phone_number = phone_number.as_ref(); + let region_dialing_from = region_dialing_from.as_ref(); match self.parse(phone_number, region_dialing_from) { Ok(number_proto) => self.is_possible_number(&number_proto), @@ -2037,7 +2048,8 @@ impl PhoneNumberUtil { /// method does not require the number to be normalized in advance - but does /// assume that leading non-number symbols have been removed, such as by the /// method `ExtractPossibleNumber`. - pub fn is_viable_phone_number(&self, phone_number: &str) -> bool { + pub fn is_viable_phone_number>(&self, phone_number: S) -> bool { + let phone_number = phone_number.as_ref(); if phone_number.len() < MIN_LENGTH_FOR_NSN { false } else { @@ -2216,8 +2228,8 @@ impl PhoneNumberUtil { /// # Arguments /// /// * `region_code` - The region for which to get an example number. - pub fn get_example_number(&self, region_code: &str) -> ExampleNumberResult { - self.get_example_number_for_type_and_region_code(region_code, PhoneNumberType::FixedLine) + pub fn get_example_number>(&self, region_code: S) -> ExampleNumberResult { + self.get_example_number_for_type_and_region_code(region_code.as_ref(), PhoneNumberType::FixedLine) } /// Gets an example of an invalid phone number for a given region. @@ -2225,7 +2237,8 @@ impl PhoneNumberUtil { /// # Arguments /// /// * `region_code` - The region for which to get an invalid example number. - pub fn get_invalid_example_number(&self, region_code: &str) -> ExampleNumberResult { + pub fn get_invalid_example_number>(&self, region_code: S) -> ExampleNumberResult { + let region_code = region_code.as_ref(); let Some(region_metadata) = self.region_to_metadata_map.get(region_code) else { warn!("Invalid or unknown region code ({}) provided.", region_code); return Err(GetExampleNumberError::InvalidMetadata); @@ -2281,11 +2294,12 @@ impl PhoneNumberUtil { /// /// * `region_code` - The region for which to get an example number. /// * `number_type` - The type of number to get an example for. - pub fn get_example_number_for_type_and_region_code( + pub fn get_example_number_for_type_and_region_code>( &self, - region_code: &str, + region_code: S, phone_number_type: PhoneNumberType, ) -> ExampleNumberResult { + let region_code = region_code.as_ref(); let Some(region_metadata) = self.region_to_metadata_map.get(region_code) else { warn!("Invalid or unknown region code ({}) provided.", region_code); return Err(GetExampleNumberError::InvalidMetadata); @@ -2471,7 +2485,8 @@ impl PhoneNumberUtil { /// # Arguments /// /// * `phone_number` - Number to normalize. - pub fn normalize(&self, phone_number: &str) -> String { + pub fn normalize>(&self, phone_number: S) -> String { + let phone_number = phone_number.as_ref(); if self .reg_exps .valid_alpha_phone_pattern @@ -2788,8 +2803,10 @@ impl PhoneNumberUtil { /// # Arguments /// /// * `phone_number` - The phone number string with alpha characters. - pub fn convert_alpha_characters_in_number(&self, phone_number: &str) -> String { - normalize_helper(&self.reg_exps.alpha_phone_mappings, false, phone_number) + pub fn convert_alpha_characters_in_number>(&self, phone_number: S) -> String { + normalize_helper( + &self.reg_exps.alpha_phone_mappings, false, phone_number.as_ref() + ) } /// Checks whether two phone numbers match. @@ -2856,11 +2873,13 @@ impl PhoneNumberUtil { /// /// * `number1` - The first phone number to compare. /// * `number2` - The second phone number to compare. - pub fn is_number_match_with_two_strings( + pub fn is_number_match_with_two_strings, S2: AsRef>( &self, - first_number: &str, - second_number: &str, + first_number: S1, + second_number: S2, ) -> MatchResult { + let first_number = first_number.as_ref(); + let second_number = second_number.as_ref(); match self.parse(first_number, RegionCode::get_unknown()) { Ok(first_number_as_proto) => { return self.is_number_match_with_one_string(&first_number_as_proto, second_number); @@ -2899,11 +2918,13 @@ impl PhoneNumberUtil { /// /// * `number1` - The first phone number to compare. /// * `number2` - The second phone number to compare. - pub fn is_number_match_with_one_string( + pub fn is_number_match_with_one_string>( &self, first_number: &PhoneNumber, - second_number: &str, + second_number: S, ) -> MatchResult { + let second_number = second_number.as_ref(); + // First see if the second number has an implicit country calling code, by // attempting to parse it. match self.parse(second_number, RegionCode::get_unknown()) { @@ -2945,13 +2966,13 @@ impl PhoneNumberUtil { /// # Arguments /// /// * `phone_number` - The string to check. - pub fn is_alpha_number(&self, phone_number: &str) -> bool { - if !self.is_viable_phone_number(phone_number) { + pub fn is_alpha_number>(&self, phone_number: S) -> bool { + if !self.is_viable_phone_number(phone_number.as_ref()) { // Number is too short, or doesn't match the basic phone number pattern. return false; } // Copy the number, since we are going to try and strip the extension from it. - let (number, _extension) = self.maybe_strip_extension(&phone_number); + let (number, _extension) = self.maybe_strip_extension(phone_number.as_ref()); return self.reg_exps.valid_alpha_phone_pattern.full_match(number); } } diff --git a/src/regex_based_matcher.rs b/src/regex_based_matcher.rs index 8b631b5..1723c6a 100644 --- a/src/regex_based_matcher.rs +++ b/src/regex_based_matcher.rs @@ -17,7 +17,7 @@ use log::{error}; use super::regex_util::{RegexFullMatch, RegexConsume}; -use crate::{interfaces, phonemetadata::PhoneNumberDesc, regexp_cache::{ErrorInvalidRegex, RegexCache}}; +use crate::{interfaces, PhoneNumberDesc, regexp_cache::{ErrorInvalidRegex, RegexCache}}; pub struct RegexBasedMatcher { cache: RegexCache, diff --git a/src/tests/phonenumberutil_tests.rs b/src/tests/phonenumberutil_tests.rs index 19a8388..dbe2c6a 100644 --- a/src/tests/phonenumberutil_tests.rs +++ b/src/tests/phonenumberutil_tests.rs @@ -1,10 +1,10 @@ use protobuf::{Message, MessageField}; use crate::{ - enums::{PhoneNumberFormat, PhoneNumberType, NumberLengthType}, - errors::{ParseError, ValidationError}, - phonemetadata::{NumberFormat, PhoneMetadata, PhoneMetadataCollection, PhoneNumberDesc}, - phonenumber::{phone_number::CountryCodeSource, PhoneNumber}, + PhoneNumberFormat, PhoneNumberType, NumberLengthType, + ParseError, ValidationError, + NumberFormat, PhoneMetadata, PhoneMetadataCollection, PhoneNumberDesc, + CountryCodeSource, PhoneNumber, PhoneNumberUtil, };