diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..b2ae984 --- /dev/null +++ b/.gitignore @@ -0,0 +1,2 @@ +/target +/result* diff --git a/Cargo.lock b/Cargo.lock new file mode 100644 index 0000000..99e137b --- /dev/null +++ b/Cargo.lock @@ -0,0 +1,659 @@ +# This file is automatically @generated by Cargo. +# It is not intended for manual editing. +version = 3 + +[[package]] +name = "ahash" +version = "0.8.11" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "e89da841a80418a9b391ebaea17f5c112ffaaa96f621d2c285b5174da76b9011" +dependencies = [ + "cfg-if", + "getrandom", + "once_cell", + "version_check", + "zerocopy", +] + +[[package]] +name = "autocfg" +version = "1.3.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "0c4b4d0bd25bd0b74681c0ad21497610ce1b7c91b1022cd21c80c6fbdd9476b0" + +[[package]] +name = "bitflags" +version = "2.6.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "b048fb63fd8b5923fc5aa7b340d8e156aec7ec02f0c78fa8a6ddc2613f6f71de" + +[[package]] +name = "byteorder" +version = "1.5.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "1fd0f2584146f6f2ef48085050886acf353beff7305ebd1ae69500e27c67f64b" + +[[package]] +name = "cfg-if" +version = "1.0.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "baf1de4339761588bc0619e3cbc0120ee582ebb74b53b4efbf79117bd2da40fd" + +[[package]] +name = "cssparser" +version = "0.31.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "5b3df4f93e5fbbe73ec01ec8d3f68bba73107993a5b1e7519273c32db9b0d5be" +dependencies = [ + "cssparser-macros", + "dtoa-short", + "itoa", + "phf 0.11.2", + "smallvec", +] + +[[package]] +name = "cssparser-macros" +version = "0.6.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "13b588ba4ac1a99f7f2964d24b3d896ddc6bf847ee3855dbd4366f058cfcd331" +dependencies = [ + "quote", + "syn", +] + +[[package]] +name = "derive_more" +version = "0.99.18" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "5f33878137e4dafd7fa914ad4e259e18a4e8e532b9617a2d0150262bf53abfce" +dependencies = [ + "proc-macro2", + "quote", + "syn", +] + +[[package]] +name = "dtoa" +version = "1.0.9" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "dcbb2bf8e87535c23f7a8a321e364ce21462d0ff10cb6407820e8e96dfff6653" + +[[package]] +name = "dtoa-short" +version = "0.3.5" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "cd1511a7b6a56299bd043a9c167a6d2bfb37bf84a6dfceaba651168adfb43c87" +dependencies = [ + "dtoa", +] + +[[package]] +name = "ego-tree" +version = "0.6.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "12a0bb14ac04a9fcf170d0bbbef949b44cc492f4452bd20c095636956f653642" + +[[package]] +name = "futf" +version = "0.1.5" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "df420e2e84819663797d1ec6544b13c5be84629e7bb00dc960d6917db2987843" +dependencies = [ + "mac", + "new_debug_unreachable", +] + +[[package]] +name = "fxhash" +version = "0.2.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "c31b6d751ae2c7f11320402d34e41349dd1016f8d5d45e48c4312bc8625af50c" +dependencies = [ + "byteorder", +] + +[[package]] +name = "getopts" +version = "0.2.21" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "14dbbfd5c71d70241ecf9e6f13737f7b5ce823821063188d7e46c41d371eebd5" +dependencies = [ + "unicode-width", +] + +[[package]] +name = "getrandom" +version = "0.2.15" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "c4567c8db10ae91089c99af84c68c38da3ec2f087c3f82960bcdbf3656b6f4d7" +dependencies = [ + "cfg-if", + "libc", + "wasi", +] + +[[package]] +name = "html-rs-bench" +version = "0.1.0" +dependencies = [ + "html5ever", + "scraper", + "tl", +] + +[[package]] +name = "html5ever" +version = "0.27.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "c13771afe0e6e846f1e67d038d4cb29998a6779f93c809212e4e9c32efd244d4" +dependencies = [ + "log", + "mac", + "markup5ever", + "proc-macro2", + "quote", + "syn", +] + +[[package]] +name = "itoa" +version = "1.0.11" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "49f1f14873335454500d59611f1cf4a4b0f786f9ac11f4312a78e4cf2566695b" + +[[package]] +name = "libc" +version = "0.2.158" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "d8adc4bb1803a324070e64a98ae98f38934d91957a99cfb3a43dcbc01bc56439" + +[[package]] +name = "lock_api" +version = "0.4.12" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "07af8b9cdd281b7915f413fa73f29ebd5d55d0d3f0155584dade1ff18cea1b17" +dependencies = [ + "autocfg", + "scopeguard", +] + +[[package]] +name = "log" +version = "0.4.22" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "a7a70ba024b9dc04c27ea2f0c0548feb474ec5c54bba33a7f72f873a39d07b24" + +[[package]] +name = "mac" +version = "0.1.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "c41e0c4fef86961ac6d6f8a82609f55f31b05e4fce149ac5710e439df7619ba4" + +[[package]] +name = "markup5ever" +version = "0.12.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "16ce3abbeba692c8b8441d036ef91aea6df8da2c6b6e21c7e14d3c18e526be45" +dependencies = [ + "log", + "phf 0.11.2", + "phf_codegen 0.11.2", + "string_cache", + "string_cache_codegen", + "tendril", +] + +[[package]] +name = "new_debug_unreachable" +version = "1.0.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "650eef8c711430f1a879fdd01d4745a7deea475becfb90269c06775983bbf086" + +[[package]] +name = "once_cell" +version = "1.20.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "33ea5043e58958ee56f3e15a90aee535795cd7dfd319846288d93c5b57d85cbe" + +[[package]] +name = "parking_lot" +version = "0.12.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "f1bf18183cf54e8d6059647fc3063646a1801cf30896933ec2311622cc4b9a27" +dependencies = [ + "lock_api", + "parking_lot_core", +] + +[[package]] +name = "parking_lot_core" +version = "0.9.10" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "1e401f977ab385c9e4e3ab30627d6f26d00e2c73eef317493c4ec6d468726cf8" +dependencies = [ + "cfg-if", + "libc", + "redox_syscall", + "smallvec", + "windows-targets", +] + +[[package]] +name = "phf" +version = "0.10.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "fabbf1ead8a5bcbc20f5f8b939ee3f5b0f6f281b6ad3468b84656b658b455259" +dependencies = [ + "phf_shared 0.10.0", +] + +[[package]] +name = "phf" +version = "0.11.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "ade2d8b8f33c7333b51bcf0428d37e217e9f32192ae4772156f65063b8ce03dc" +dependencies = [ + "phf_macros", + "phf_shared 0.11.2", +] + +[[package]] +name = "phf_codegen" +version = "0.10.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "4fb1c3a8bc4dd4e5cfce29b44ffc14bedd2ee294559a294e2a4d4c9e9a6a13cd" +dependencies = [ + "phf_generator 0.10.0", + "phf_shared 0.10.0", +] + +[[package]] +name = "phf_codegen" +version = "0.11.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "e8d39688d359e6b34654d328e262234662d16cc0f60ec8dcbe5e718709342a5a" +dependencies = [ + "phf_generator 0.11.2", + "phf_shared 0.11.2", +] + +[[package]] +name = "phf_generator" +version = "0.10.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "5d5285893bb5eb82e6aaf5d59ee909a06a16737a8970984dd7746ba9283498d6" +dependencies = [ + "phf_shared 0.10.0", + "rand", +] + +[[package]] +name = "phf_generator" +version = "0.11.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "48e4cc64c2ad9ebe670cb8fd69dd50ae301650392e81c05f9bfcb2d5bdbc24b0" +dependencies = [ + "phf_shared 0.11.2", + "rand", +] + +[[package]] +name = "phf_macros" +version = "0.11.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "3444646e286606587e49f3bcf1679b8cef1dc2c5ecc29ddacaffc305180d464b" +dependencies = [ + "phf_generator 0.11.2", + "phf_shared 0.11.2", + "proc-macro2", + "quote", + "syn", +] + +[[package]] +name = "phf_shared" +version = "0.10.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "b6796ad771acdc0123d2a88dc428b5e38ef24456743ddb1744ed628f9815c096" +dependencies = [ + "siphasher", +] + +[[package]] +name = "phf_shared" +version = "0.11.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "90fcb95eef784c2ac79119d1dd819e162b5da872ce6f3c3abe1e8ca1c082f72b" +dependencies = [ + "siphasher", +] + +[[package]] +name = "ppv-lite86" +version = "0.2.20" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "77957b295656769bb8ad2b6a6b09d897d94f05c41b069aede1fcdaa675eaea04" +dependencies = [ + "zerocopy", +] + +[[package]] +name = "precomputed-hash" +version = "0.1.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "925383efa346730478fb4838dbe9137d2a47675ad789c546d150a6e1dd4ab31c" + +[[package]] +name = "proc-macro2" +version = "1.0.86" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "5e719e8df665df0d1c8fbfd238015744736151d4445ec0836b8e628aae103b77" +dependencies = [ + "unicode-ident", +] + +[[package]] +name = "quote" +version = "1.0.37" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "b5b9d34b8991d19d98081b46eacdd8eb58c6f2b201139f7c5f643cc155a633af" +dependencies = [ + "proc-macro2", +] + +[[package]] +name = "rand" +version = "0.8.5" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "34af8d1a0e25924bc5b7c43c079c942339d8f0a8b57c39049bef581b46327404" +dependencies = [ + "libc", + "rand_chacha", + "rand_core", +] + +[[package]] +name = "rand_chacha" +version = "0.3.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "e6c10a63a0fa32252be49d21e7709d4d4baf8d231c2dbce1eaa8141b9b127d88" +dependencies = [ + "ppv-lite86", + "rand_core", +] + +[[package]] +name = "rand_core" +version = "0.6.4" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "ec0be4795e2f6a28069bec0b5ff3e2ac9bafc99e6a9a7dc3547996c5c816922c" +dependencies = [ + "getrandom", +] + +[[package]] +name = "redox_syscall" +version = "0.5.4" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "0884ad60e090bf1345b93da0a5de8923c93884cd03f40dfcfddd3b4bee661853" +dependencies = [ + "bitflags", +] + +[[package]] +name = "scopeguard" +version = "1.2.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "94143f37725109f92c262ed2cf5e59bce7498c01bcc1502d7b9afe439a4e9f49" + +[[package]] +name = "scraper" +version = "0.20.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "b90460b31bfe1fc07be8262e42c665ad97118d4585869de9345a84d501a9eaf0" +dependencies = [ + "ahash", + "cssparser", + "ego-tree", + "getopts", + "html5ever", + "once_cell", + "selectors", + "tendril", +] + +[[package]] +name = "selectors" +version = "0.25.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "4eb30575f3638fc8f6815f448d50cb1a2e255b0897985c8c59f4d37b72a07b06" +dependencies = [ + "bitflags", + "cssparser", + "derive_more", + "fxhash", + "log", + "new_debug_unreachable", + "phf 0.10.1", + "phf_codegen 0.10.0", + "precomputed-hash", + "servo_arc", + "smallvec", +] + +[[package]] +name = "serde" +version = "1.0.210" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "c8e3592472072e6e22e0a54d5904d9febf8508f65fb8552499a1abc7d1078c3a" +dependencies = [ + "serde_derive", +] + +[[package]] +name = "serde_derive" +version = "1.0.210" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "243902eda00fad750862fc144cea25caca5e20d615af0a81bee94ca738f1df1f" +dependencies = [ + "proc-macro2", + "quote", + "syn", +] + +[[package]] +name = "servo_arc" +version = "0.3.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "d036d71a959e00c77a63538b90a6c2390969f9772b096ea837205c6bd0491a44" +dependencies = [ + "stable_deref_trait", +] + +[[package]] +name = "siphasher" +version = "0.3.11" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "38b58827f4464d87d377d175e90bf58eb00fd8716ff0a62f80356b5e61555d0d" + +[[package]] +name = "smallvec" +version = "1.13.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "3c5e1a9a646d36c3599cd173a41282daf47c44583ad367b8e6837255952e5c67" + +[[package]] +name = "stable_deref_trait" +version = "1.2.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "a8f112729512f8e442d81f95a8a7ddf2b7c6b8a1a6f509a95864142b30cab2d3" + +[[package]] +name = "string_cache" +version = "0.8.7" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "f91138e76242f575eb1d3b38b4f1362f10d3a43f47d182a5b359af488a02293b" +dependencies = [ + "new_debug_unreachable", + "once_cell", + "parking_lot", + "phf_shared 0.10.0", + "precomputed-hash", + "serde", +] + +[[package]] +name = "string_cache_codegen" +version = "0.5.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "6bb30289b722be4ff74a408c3cc27edeaad656e06cb1fe8fa9231fa59c728988" +dependencies = [ + "phf_generator 0.10.0", + "phf_shared 0.10.0", + "proc-macro2", + "quote", +] + +[[package]] +name = "syn" +version = "2.0.77" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "9f35bcdf61fd8e7be6caf75f429fdca8beb3ed76584befb503b1569faee373ed" +dependencies = [ + "proc-macro2", + "quote", + "unicode-ident", +] + +[[package]] +name = "tendril" +version = "0.4.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "d24a120c5fc464a3458240ee02c299ebcb9d67b5249c8848b09d639dca8d7bb0" +dependencies = [ + "futf", + "mac", + "utf-8", +] + +[[package]] +name = "tl" +version = "0.7.8" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "b130bd8a58c163224b44e217b4239ca7b927d82bf6cc2fea1fc561d15056e3f7" + +[[package]] +name = "unicode-ident" +version = "1.0.13" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "e91b56cd4cadaeb79bbf1a5645f6b4f8dc5bde8834ad5894a8db35fda9efa1fe" + +[[package]] +name = "unicode-width" +version = "0.1.13" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "0336d538f7abc86d282a4189614dfaa90810dfc2c6f6427eaf88e16311dd225d" + +[[package]] +name = "utf-8" +version = "0.7.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "09cc8ee72d2a9becf2f2febe0205bbed8fc6615b7cb429ad062dc7b7ddd036a9" + +[[package]] +name = "version_check" +version = "0.9.5" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "0b928f33d975fc6ad9f86c8f283853ad26bdd5b10b7f1542aa2fa15e2289105a" + +[[package]] +name = "wasi" +version = "0.11.0+wasi-snapshot-preview1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "9c8d87e72b64a3b4db28d11ce29237c246188f4f51057d65a7eab63b7987e423" + +[[package]] +name = "windows-targets" +version = "0.52.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "9b724f72796e036ab90c1021d4780d4d3d648aca59e491e6b98e725b84e99973" +dependencies = [ + "windows_aarch64_gnullvm", + "windows_aarch64_msvc", + "windows_i686_gnu", + "windows_i686_gnullvm", + "windows_i686_msvc", + "windows_x86_64_gnu", + "windows_x86_64_gnullvm", + "windows_x86_64_msvc", +] + +[[package]] +name = "windows_aarch64_gnullvm" +version = "0.52.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "32a4622180e7a0ec044bb555404c800bc9fd9ec262ec147edd5989ccd0c02cd3" + +[[package]] +name = "windows_aarch64_msvc" +version = "0.52.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "09ec2a7bb152e2252b53fa7803150007879548bc709c039df7627cabbd05d469" + +[[package]] +name = "windows_i686_gnu" +version = "0.52.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "8e9b5ad5ab802e97eb8e295ac6720e509ee4c243f69d781394014ebfe8bbfa0b" + +[[package]] +name = "windows_i686_gnullvm" +version = "0.52.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "0eee52d38c090b3caa76c563b86c3a4bd71ef1a819287c19d586d7334ae8ed66" + +[[package]] +name = "windows_i686_msvc" +version = "0.52.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "240948bc05c5e7c6dabba28bf89d89ffce3e303022809e73deaefe4f6ec56c66" + +[[package]] +name = "windows_x86_64_gnu" +version = "0.52.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "147a5c80aabfbf0c7d901cb5895d1de30ef2907eb21fbbab29ca94c5b08b1a78" + +[[package]] +name = "windows_x86_64_gnullvm" +version = "0.52.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "24d5b23dc417412679681396f2b49f3de8c1473deb516bd34410872eff51ed0d" + +[[package]] +name = "windows_x86_64_msvc" +version = "0.52.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "589f6da84c646204747d1270a2a5661ea66ed1cced2631d546fdfb155959f9ec" + +[[package]] +name = "zerocopy" +version = "0.7.35" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "1b9b4fd18abc82b8136838da5d50bae7bdea537c574d8dc1a34ed098d6c166f0" +dependencies = [ + "byteorder", + "zerocopy-derive", +] + +[[package]] +name = "zerocopy-derive" +version = "0.7.35" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "fa4f8080344d4671fb4e831a13ad1e68092748387dfc4f55e356242fae12ce3e" +dependencies = [ + "proc-macro2", + "quote", + "syn", +] diff --git a/Cargo.toml b/Cargo.toml new file mode 100644 index 0000000..b83c806 --- /dev/null +++ b/Cargo.toml @@ -0,0 +1,9 @@ +[package] +name = "html-rs-bench" +version = "0.1.0" +edition = "2021" + +[dependencies] +html5ever = "0.27.0" +scraper = "0.20.0" +tl = "0.7.8" diff --git a/README.md b/README.md new file mode 100644 index 0000000..6df75f9 --- /dev/null +++ b/README.md @@ -0,0 +1,37 @@ +Benchmark Rust libraries working with HTML: +- [`scraper`](https://crates.io/crates/scraper) (built with [`html5ever`](https://crates.io/crates/html5ever)) +- [`tl`](https://crates.io/crates/tl) +- *(haven't found anything else that can build DOM, select an element and serialize)* + +Output is unformatted CSV (probably because I'm lazy), +a nushell's `from csv` can be used to print a neat table. + +Test results on my PC: +``` +~/code/html-rs-bench> cargo run -r | save -f result; open result | from csv + Finished `release` profile [optimized] target(s) in 0.03s + Running `target/release/html-rs-bench` +╭───┬───────────┬─────────┬───────────┬───────────┬───────────┬────────────┬────────────┬────────────┬────────────┬────────────┬────────────╮ +│ # │ engine │ page │ parse min │ parse avg │ parse max │ select min │ select avg │ select max │ serial min │ serial avg │ serial max │ +├───┼───────────┼─────────┼───────────┼───────────┼───────────┼────────────┼────────────┼────────────┼────────────┼────────────┼────────────┤ +│ 0 │ html5ever │ tochb │ 77.42 │ 78.08 │ 81.70 │ 0.00 │ 0.00 │ 0.02 │ 67.16 │ 67.75 │ 69.38 │ +│ 1 │ html5ever │ android │ 123.75 │ 124.81 │ 126.88 │ 0.00 │ 0.00 │ 0.02 │ 66.44 │ 66.74 │ 66.99 │ +│ 2 │ html5ever │ 10mb │ 135.00 │ 135.34 │ 136.73 │ 0.00 │ 0.00 │ 0.02 │ 248.11 │ 248.69 │ 249.58 │ +│ 3 │ tl │ tochb │ 19.60 │ 19.72 │ 20.00 │ 0.00 │ 0.00 │ 0.02 │ 1024.16 │ 1025.30 │ 1027.68 │ +│ 4 │ tl │ android │ 11.68 │ 11.78 │ 11.96 │ 0.00 │ 0.00 │ 0.02 │ 82.70 │ 84.07 │ 92.40 │ +│ 5 │ tl │ 10mb │ 2.09 │ 2.14 │ 2.24 │ 0.00 │ 0.00 │ 0.00 │ 14.04 │ 14.19 │ 14.56 │ +╰───┴───────────┴─────────┴───────────┴───────────┴───────────┴────────────┴────────────┴────────────┴────────────┴────────────┴────────────╯ +``` + +Keep in mind that, despite `tl` being really fast (except serializing many tags in `tochb` sample), +it's not a browser-grade parser, and also that it doesn't fully support the CSS selector syntax +(e.g. `a[data-abc]` is OK, but not `a[data-abc="123"]`). + +I do not own anything in the sample HTML pages. Here are the sources: +- `tochb` - [Dictionary of Tocharian B](https://www.win.tue.nl/~aeb/natlang/ie/tochB.html) +- `android` - [BluetoothDevice Android API reference](https://developer.android.com/reference/android/bluetooth/BluetoothDevice) +- `10mb` - [Random 10MB page with Shakespeare's poem](https://github.com/adriancbjie/my-kitty-cat/raw/master/web/staticpages/10MB.html) + +Size of developer.android.com is surprising... +It's ~3.8 MiB even for the API reference homepage. +It's bigger than the whole Tocharian-B dictionary. diff --git a/src/main.rs b/src/main.rs new file mode 100644 index 0000000..1aa9d7e --- /dev/null +++ b/src/main.rs @@ -0,0 +1,126 @@ +use std::time::Instant; + +use scraper::{Html, Selector}; + +const SAMPLES: [(&str, &str, &str); 3] = [ + ("tochb", "a[name]", include_str!("../html/tochb.html")), + ( + "android", + ".devsite-top-logo-row", + include_str!("../html/android.html"), + ), + ("10mb", "b", include_str!("../html/10mb.html")), +]; + +fn main() { + println!(concat!( + "engine,page,", + "parse min,parse avg,parse max,", + "select min,select avg,select max,", + "serial min,serial avg,serial max", + )); + run::(); + run::(); +} + +fn run() { + for (page_name, selector, content) in SAMPLES { + print!("{},{}", E::NAME, page_name); + + // parse, build DOM + let dom = { + bench(20, || { + E::parse(content); + }); + E::parse(content) + }; + + // find elem + bench(10000, || { + dom.select(selector); + }); + + // serialize + bench(10, || { + assert!(!dom.serialize().is_empty()); + }); + + println!(); + } +} + +fn bench(repeats: u16, cb: impl Fn()) { + let mut min = f64::INFINITY; + let mut max = 0.0; + let mut sum = 0.0; + for _ in 0..repeats { + let start = Instant::now(); + cb(); + let delta = Instant::now() - start; + + let millis = delta.as_nanos() as f64 / 1_000_000.0; + + if millis < min { + min = millis; + } + if millis > max { + max = millis; + } + + sum += millis; + } + print!(",{:.5},{:.5},{:.5}", min, sum / repeats as f64, max); +} + +trait Engine { + const NAME: &'static str; + fn parse(doc: &str) -> impl Document; +} + +trait Document<'d> { + fn select(&self, pattern: &str); + fn serialize(&self) -> String; +} + +pub struct ScraperEngine; +impl Engine for ScraperEngine { + const NAME: &'static str = "html5ever"; + + fn parse(doc: &str) -> impl Document<'_> { + ScraperDocument(Html::parse_document(doc)) + } +} + +pub struct ScraperDocument(Html); +impl Document<'_> for ScraperDocument { + fn select(&self, pattern: &str) { + self.0 + .select(&Selector::parse(pattern).unwrap()) + .next() + .unwrap(); + } + + fn serialize(&self) -> String { + self.0.html() + } +} + +pub struct TlEngine; +impl Engine for TlEngine { + const NAME: &'static str = "tl"; + + fn parse(doc: &str) -> impl Document<'_> { + TlDocument(tl::parse(doc, tl::ParserOptions::default()).unwrap()) + } +} + +pub struct TlDocument<'d>(tl::VDom<'d>); +impl Document<'_> for TlDocument<'_> { + fn select(&self, pattern: &str) { + self.0.query_selector(pattern).unwrap().next().unwrap(); + } + + fn serialize(&self) -> String { + self.0.outer_html() + } +}