From 66967a1b9e42fb2d3887f4e091ab982aa0b3cb46 Mon Sep 17 00:00:00 2001 From: Michael Macnair Date: Sun, 9 May 2021 19:05:14 +0100 Subject: [PATCH] Fuzzing (#726) * Add fuzzing support See fuzz/README.md for details. Example bug: #725 * improve fuzz docs * fuzzing: make relevant config part of input Most of the config is to do with what files to parse, however one setting - treat_doc_strings_as_comments - does impact parse_from_slice * fuzzing: improve docs + config clarity * fuzz/README.md: install instructions + another todo item --- Cargo.lock | 21 + Cargo.toml | 1 + fuzz/.gitignore | 4 + fuzz/Cargo.lock | 1147 +++++++++++++++++++ fuzz/Cargo.toml | 33 + fuzz/README.md | 30 + fuzz/fuzz_targets/parse_from_slice.rs | 51 + fuzz/fuzz_targets/parse_from_slice_panic.rs | 9 + fuzz/fuzz_targets/parse_from_slice_total.rs | 9 + src/language/language_type.tera.rs | 4 +- 10 files changed, 1308 insertions(+), 1 deletion(-) create mode 100644 fuzz/.gitignore create mode 100644 fuzz/Cargo.lock create mode 100644 fuzz/Cargo.toml create mode 100644 fuzz/README.md create mode 100644 fuzz/fuzz_targets/parse_from_slice.rs create mode 100644 fuzz/fuzz_targets/parse_from_slice_panic.rs create mode 100644 fuzz/fuzz_targets/parse_from_slice_total.rs diff --git a/Cargo.lock b/Cargo.lock index b0e236d..ed8bf60 100644 --- a/Cargo.lock +++ b/Cargo.lock @@ -18,6 +18,15 @@ dependencies = [ "winapi", ] +[[package]] +name = "arbitrary" +version = "1.0.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "698b65a961a9d730fb45b6b0327e20207810c9f61ee421b082b27ba003f49e2b" +dependencies = [ + "derive_arbitrary", +] + [[package]] name = "arrayvec" version = "0.4.12" @@ -207,6 +216,17 @@ dependencies = [ "serde", ] +[[package]] +name = "derive_arbitrary" +version = "1.0.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "df89dd0d075dea5cc5fdd6d5df6b8a61172a710b3efac1d6bdb9dd8b78f82c1a" +dependencies = [ + "proc-macro2", + "quote", + "syn", +] + [[package]] name = "deunicode" version = "0.4.3" @@ -1073,6 +1093,7 @@ name = "tokei" version = "12.1.2" dependencies = [ "aho-corasick", + "arbitrary", "clap", "crossbeam-channel", "dashmap", diff --git a/Cargo.toml b/Cargo.toml index e79b96b..329b582 100644 --- a/Cargo.toml +++ b/Cargo.toml @@ -30,6 +30,7 @@ serde_json = "1.0.64" [dependencies] aho-corasick = "0.7.15" +arbitrary = { version = "1.0.0", features = ["derive"] } clap = "2.33.3" crossbeam-channel = "0.5.0" encoding_rs_io = "0.1.7" diff --git a/fuzz/.gitignore b/fuzz/.gitignore new file mode 100644 index 0000000..572e03b --- /dev/null +++ b/fuzz/.gitignore @@ -0,0 +1,4 @@ + +target +corpus +artifacts diff --git a/fuzz/Cargo.lock b/fuzz/Cargo.lock new file mode 100644 index 0000000..3ded87e --- /dev/null +++ b/fuzz/Cargo.lock @@ -0,0 +1,1147 @@ +# This file is automatically @generated by Cargo. +# It is not intended for manual editing. +version = 3 + +[[package]] +name = "aho-corasick" +version = "0.7.15" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "7404febffaa47dac81aa44dba71523c9d069b1bdc50a77db41195149e17f68e5" +dependencies = [ + "memchr", +] + +[[package]] +name = "ansi_term" +version = "0.11.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "ee49baf6cb617b853aa8d93bf420db2383fab46d314482ca2803b40d5fde979b" +dependencies = [ + "winapi", +] + +[[package]] +name = "arbitrary" +version = "1.0.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "698b65a961a9d730fb45b6b0327e20207810c9f61ee421b082b27ba003f49e2b" +dependencies = [ + "derive_arbitrary", +] + +[[package]] +name = "arrayvec" +version = "0.4.12" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "cd9fd44efafa8690358b7408d253adf110036b88f55672a933f01d616ad9b1b9" +dependencies = [ + "nodrop", +] + +[[package]] +name = "atty" +version = "0.2.14" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "d9b39be18770d11421cdb1b9947a45dd3f37e93092cbf377614828a319d5fee8" +dependencies = [ + "hermit-abi", + "libc", + "winapi", +] + +[[package]] +name = "autocfg" +version = "1.0.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "cdb031dd78e28731d87d56cc8ffef4a8f36ca26c38fe2de700543e627f8a464a" + +[[package]] +name = "bitflags" +version = "1.2.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "cf1de2fe8c75bc145a2f577add951f8134889b4795d47466a54a5c846d691693" + +[[package]] +name = "block-buffer" +version = "0.7.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "c0940dc441f31689269e10ac70eb1002a3a1d3ad1390e030043662eb7fe4688b" +dependencies = [ + "block-padding", + "byte-tools", + "byteorder", + "generic-array", +] + +[[package]] +name = "block-padding" +version = "0.1.5" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "fa79dedbb091f449f1f39e53edf88d5dbe95f895dae6135a8d7b881fb5af73f5" +dependencies = [ + "byte-tools", +] + +[[package]] +name = "bstr" +version = "0.2.15" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "a40b47ad93e1a5404e6c18dec46b628214fee441c70f4ab5d6942142cc268a3d" +dependencies = [ + "memchr", +] + +[[package]] +name = "byte-tools" +version = "0.3.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "e3b5ca7a04898ad4bcd41c90c5285445ff5b791899bb1b0abdd2a2aa791211d7" + +[[package]] +name = "bytecount" +version = "0.6.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "72feb31ffc86498dacdbd0fcebb56138e7177a8cc5cea4516031d15ae85a742e" + +[[package]] +name = "byteorder" +version = "1.4.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "ae44d1a3d5a19df61dd0c8beb138458ac2a53a7ac09eba97d55592540004306b" + +[[package]] +name = "cc" +version = "1.0.67" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "e3c69b077ad434294d3ce9f1f6143a2a4b89a8a2d54ef813d85003a4fd1137fd" + +[[package]] +name = "cfg-if" +version = "1.0.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "baf1de4339761588bc0619e3cbc0120ee582ebb74b53b4efbf79117bd2da40fd" + +[[package]] +name = "chrono" +version = "0.4.19" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "670ad68c9088c2a963aaa298cb369688cf3f9465ce5e2d4ca10e6e0098a1ce73" +dependencies = [ + "libc", + "num-integer", + "num-traits", + "time", + "winapi", +] + +[[package]] +name = "chrono-tz" +version = "0.5.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "2554a3155fec064362507487171dcc4edc3df60cb10f3a1fb10ed8094822b120" +dependencies = [ + "chrono", + "parse-zoneinfo", +] + +[[package]] +name = "clap" +version = "2.33.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "37e58ac78573c40708d45522f0d80fa2f01cc4f9b4e2bf749807255454312002" +dependencies = [ + "ansi_term", + "atty", + "bitflags", + "strsim", + "textwrap", + "unicode-width", + "vec_map", +] + +[[package]] +name = "crossbeam-channel" +version = "0.5.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "dca26ee1f8d361640700bde38b2c37d8c22b3ce2d360e1fc1c74ea4b0aa7d775" +dependencies = [ + "cfg-if", + "crossbeam-utils", +] + +[[package]] +name = "crossbeam-deque" +version = "0.8.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "94af6efb46fef72616855b036a624cf27ba656ffc9be1b9a3c931cfc7749a9a9" +dependencies = [ + "cfg-if", + "crossbeam-epoch", + "crossbeam-utils", +] + +[[package]] +name = "crossbeam-epoch" +version = "0.9.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "d60ab4a8dba064f2fbb5aa270c28da5cf4bbd0e72dae1140a6b0353a779dbe00" +dependencies = [ + "cfg-if", + "crossbeam-utils", + "lazy_static", + "loom", + "memoffset", + "scopeguard", +] + +[[package]] +name = "crossbeam-utils" +version = "0.8.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "bae8f328835f8f5a6ceb6a7842a7f2d0c03692adb5c889347235d59194731fe3" +dependencies = [ + "autocfg", + "cfg-if", + "lazy_static", + "loom", +] + +[[package]] +name = "dashmap" +version = "4.0.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "e77a43b28d0668df09411cb0bc9a8c2adc40f9a048afe863e05fd43251e8e39c" +dependencies = [ + "cfg-if", + "num_cpus", + "serde", +] + +[[package]] +name = "derive_arbitrary" +version = "1.0.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "df89dd0d075dea5cc5fdd6d5df6b8a61172a710b3efac1d6bdb9dd8b78f82c1a" +dependencies = [ + "proc-macro2", + "quote", + "syn", +] + +[[package]] +name = "deunicode" +version = "0.4.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "850878694b7933ca4c9569d30a34b55031b9b139ee1fc7b94a527c4ef960d690" + +[[package]] +name = "digest" +version = "0.8.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "f3d0c8c8752312f9713efd397ff63acb9f85585afbf179282e720e7704954dd5" +dependencies = [ + "generic-array", +] + +[[package]] +name = "dirs-next" +version = "2.0.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "b98cf8ebf19c3d1b223e151f99a4f9f0690dca41414773390fc824184ac833e1" +dependencies = [ + "cfg-if", + "dirs-sys-next", +] + +[[package]] +name = "dirs-sys-next" +version = "0.1.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "4ebda144c4fe02d1f7ea1a7d9641b6fc6b580adcfa024ae48797ecdeb6825b4d" +dependencies = [ + "libc", + "redox_users", + "winapi", +] + +[[package]] +name = "either" +version = "1.6.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "e78d4f1cc4ae33bbfc157ed5d5a5ef3bc29227303d595861deb238fcec4e9457" + +[[package]] +name = "encoding_rs" +version = "0.8.28" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "80df024fbc5ac80f87dfef0d9f5209a252f2a497f7f42944cff24d8253cac065" +dependencies = [ + "cfg-if", +] + +[[package]] +name = "encoding_rs_io" +version = "0.1.7" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "1cc3c5651fb62ab8aa3103998dade57efdd028544bd300516baa31840c252a83" +dependencies = [ + "encoding_rs", +] + +[[package]] +name = "env_logger" +version = "0.8.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "17392a012ea30ef05a610aa97dfb49496e71c9f676b27879922ea5bdf60d9d3f" +dependencies = [ + "atty", + "humantime", + "log", + "regex", + "termcolor", +] + +[[package]] +name = "fake-simd" +version = "0.1.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "e88a8acf291dafb59c2d96e8f59828f3838bb1a70398823ade51a84de6a6deed" + +[[package]] +name = "fnv" +version = "1.0.7" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "3f9eec918d3f24069decb9af1554cad7c880e2da24a9afd88aca000531ab82c1" + +[[package]] +name = "generator" +version = "0.6.24" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "a9fed24fd1e18827652b4d55652899a1e9da8e54d91624dc3437a5bc3a9f9a9c" +dependencies = [ + "cc", + "libc", + "log", + "rustversion", + "winapi", +] + +[[package]] +name = "generic-array" +version = "0.12.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "c68f0274ae0e023facc3c97b2e00f076be70e254bc851d972503b328db79b2ec" +dependencies = [ + "typenum", +] + +[[package]] +name = "getrandom" +version = "0.2.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "c9495705279e7140bf035dde1f6e750c162df8b625267cd52cc44e0b156732c8" +dependencies = [ + "cfg-if", + "libc", + "wasi", +] + +[[package]] +name = "globset" +version = "0.4.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "c152169ef1e421390738366d2f796655fec62621dabbd0fd476f905934061e4a" +dependencies = [ + "aho-corasick", + "bstr", + "fnv", + "log", + "regex", +] + +[[package]] +name = "globwalk" +version = "0.8.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "93e3af942408868f6934a7b85134a3230832b9977cf66125df2f9edcfce4ddcc" +dependencies = [ + "bitflags", + "ignore", + "walkdir", +] + +[[package]] +name = "grep-matcher" +version = "0.1.4" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "fdf0e1fd5af17008a918fd868e63ec0226e96ce88b832f00c7fb041e014b9350" +dependencies = [ + "memchr", +] + +[[package]] +name = "grep-searcher" +version = "0.1.7" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "19897320890970db77fb9e8110aeafdf5a74f4ee32756db16d44a96d8f454b1b" +dependencies = [ + "bstr", + "bytecount", + "encoding_rs", + "encoding_rs_io", + "grep-matcher", + "log", + "memmap", +] + +[[package]] +name = "hermit-abi" +version = "0.1.18" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "322f4de77956e22ed0e5032c359a0f1273f1f7f0d79bfa3b8ffbc730d7fbcc5c" +dependencies = [ + "libc", +] + +[[package]] +name = "humansize" +version = "1.1.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "b6cab2627acfc432780848602f3f558f7e9dd427352224b0d9324025796d2a5e" + +[[package]] +name = "humantime" +version = "2.1.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "9a3a5bfb195931eeb336b2a7b4d761daec841b97f947d34394601737a7bba5e4" + +[[package]] +name = "ignore" +version = "0.4.17" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "b287fb45c60bb826a0dc68ff08742b9d88a2fea13d6e0c286b3172065aaf878c" +dependencies = [ + "crossbeam-utils", + "globset", + "lazy_static", + "log", + "memchr", + "regex", + "same-file", + "thread_local", + "walkdir", + "winapi-util", +] + +[[package]] +name = "instant" +version = "0.1.9" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "61124eeebbd69b8190558df225adf7e4caafce0d743919e5d6b19652314ec5ec" +dependencies = [ + "cfg-if", +] + +[[package]] +name = "itoa" +version = "0.4.7" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "dd25036021b0de88a0aff6b850051563c6516d0bf53f8638938edbb9de732736" + +[[package]] +name = "lazy_static" +version = "1.4.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "e2abad23fbc42b3700f2f279844dc832adb2b2eb069b2df918f455c4e18cc646" + +[[package]] +name = "libc" +version = "0.2.86" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "b7282d924be3275cec7f6756ff4121987bc6481325397dde6ba3e7802b1a8b1c" + +[[package]] +name = "libfuzzer-sys" +version = "0.4.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "86c975d637bc2a2f99440932b731491fc34c7f785d239e38af3addd3c2fd0e46" +dependencies = [ + "arbitrary", + "cc", +] + +[[package]] +name = "lock_api" +version = "0.4.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "dd96ffd135b2fd7b973ac026d28085defbe8983df057ced3eb4f2130b0831312" +dependencies = [ + "scopeguard", +] + +[[package]] +name = "log" +version = "0.4.14" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "51b9bbe6c47d51fc3e1a9b945965946b4c44142ab8792c50835a980d362c2710" +dependencies = [ + "cfg-if", +] + +[[package]] +name = "loom" +version = "0.4.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "d44c73b4636e497b4917eb21c33539efa3816741a2d3ff26c6316f1b529481a4" +dependencies = [ + "cfg-if", + "generator", + "scoped-tls", +] + +[[package]] +name = "maplit" +version = "1.0.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "3e2e65a1a2e43cfcb47a895c4c8b10d1f4a61097f9f254f183aee60cad9c651d" + +[[package]] +name = "memchr" +version = "2.3.4" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "0ee1c47aaa256ecabcaea351eae4a9b01ef39ed810004e298d2511ed284b1525" + +[[package]] +name = "memmap" +version = "0.7.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "6585fd95e7bb50d6cc31e20d4cf9afb4e2ba16c5846fc76793f11218da9c475b" +dependencies = [ + "libc", + "winapi", +] + +[[package]] +name = "memoffset" +version = "0.6.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "157b4208e3059a8f9e78d559edc658e13df41410cb3ae03979c83130067fdd87" +dependencies = [ + "autocfg", +] + +[[package]] +name = "nodrop" +version = "0.1.14" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "72ef4a56884ca558e5ddb05a1d1e7e1bfd9a68d9ed024c21704cc98872dae1bb" + +[[package]] +name = "num-format" +version = "0.4.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "bafe4179722c2894288ee77a9f044f02811c86af699344c498b0840c698a2465" +dependencies = [ + "arrayvec", + "itoa", +] + +[[package]] +name = "num-integer" +version = "0.1.44" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "d2cc698a63b549a70bc047073d2949cce27cd1c7b0a4a862d08a8031bc2801db" +dependencies = [ + "autocfg", + "num-traits", +] + +[[package]] +name = "num-traits" +version = "0.2.14" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "9a64b1ec5cda2586e284722486d802acf1f7dbdc623e2bfc57e65ca1cd099290" +dependencies = [ + "autocfg", +] + +[[package]] +name = "num_cpus" +version = "1.13.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "05499f3756671c15885fee9034446956fff3f243d6077b91e5767df161f766b3" +dependencies = [ + "hermit-abi", + "libc", +] + +[[package]] +name = "once_cell" +version = "1.7.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "10acf907b94fc1b1a152d08ef97e7759650268cf986bf127f387e602b02c7e5a" + +[[package]] +name = "opaque-debug" +version = "0.2.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "2839e79665f131bdb5782e51f2c6c9599c133c6098982a54c794358bf432529c" + +[[package]] +name = "parking_lot" +version = "0.11.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "6d7744ac029df22dca6284efe4e898991d28e3085c706c972bcd7da4a27a15eb" +dependencies = [ + "instant", + "lock_api", + "parking_lot_core", +] + +[[package]] +name = "parking_lot_core" +version = "0.8.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "fa7a782938e745763fe6907fc6ba86946d72f49fe7e21de074e08128a99fb018" +dependencies = [ + "cfg-if", + "instant", + "libc", + "redox_syscall", + "smallvec", + "winapi", +] + +[[package]] +name = "parse-zoneinfo" +version = "0.3.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "c705f256449c60da65e11ff6626e0c16a0a0b96aaa348de61376b249bc340f41" +dependencies = [ + "regex", +] + +[[package]] +name = "percent-encoding" +version = "2.1.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "d4fd5641d01c8f18a23da7b6fe29298ff4b55afcccdf78973b24cf3175fee32e" + +[[package]] +name = "pest" +version = "2.1.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "10f4872ae94d7b90ae48754df22fd42ad52ce740b8f370b03da4835417403e53" +dependencies = [ + "ucd-trie", +] + +[[package]] +name = "pest_derive" +version = "2.1.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "833d1ae558dc601e9a60366421196a8d94bc0ac980476d0b67e1d0988d72b2d0" +dependencies = [ + "pest", + "pest_generator", +] + +[[package]] +name = "pest_generator" +version = "2.1.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "99b8db626e31e5b81787b9783425769681b347011cc59471e33ea46d2ea0cf55" +dependencies = [ + "pest", + "pest_meta", + "proc-macro2", + "quote", + "syn", +] + +[[package]] +name = "pest_meta" +version = "2.1.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "54be6e404f5317079812fc8f9f5279de376d8856929e21c184ecf6bbd692a11d" +dependencies = [ + "maplit", + "pest", + "sha-1", +] + +[[package]] +name = "ppv-lite86" +version = "0.2.10" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "ac74c624d6b2d21f425f752262f42188365d7b8ff1aff74c82e45136510a4857" + +[[package]] +name = "proc-macro2" +version = "1.0.24" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "1e0704ee1a7e00d7bb417d0770ea303c1bccbabf0ef1667dae92b5967f5f8a71" +dependencies = [ + "unicode-xid", +] + +[[package]] +name = "quote" +version = "1.0.9" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "c3d0b9745dc2debf507c8422de05d7226cc1f0644216dfdfead988f9b1ab32a7" +dependencies = [ + "proc-macro2", +] + +[[package]] +name = "rand" +version = "0.8.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "0ef9e7e66b4468674bfcb0c81af8b7fa0bb154fa9f28eb840da5c447baeb8d7e" +dependencies = [ + "libc", + "rand_chacha", + "rand_core", + "rand_hc", +] + +[[package]] +name = "rand_chacha" +version = "0.3.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "e12735cf05c9e10bf21534da50a147b924d555dc7a547c42e6bb2d5b6017ae0d" +dependencies = [ + "ppv-lite86", + "rand_core", +] + +[[package]] +name = "rand_core" +version = "0.6.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "34cf66eb183df1c5876e2dcf6b13d57340741e8dc255b48e40a26de954d06ae7" +dependencies = [ + "getrandom", +] + +[[package]] +name = "rand_hc" +version = "0.3.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "3190ef7066a446f2e7f42e239d161e905420ccab01eb967c9eb27d21b2322a73" +dependencies = [ + "rand_core", +] + +[[package]] +name = "rayon" +version = "1.5.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "8b0d8e0819fadc20c74ea8373106ead0600e3a67ef1fe8da56e39b9ae7275674" +dependencies = [ + "autocfg", + "crossbeam-deque", + "either", + "rayon-core", +] + +[[package]] +name = "rayon-core" +version = "1.9.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "9ab346ac5921dc62ffa9f89b7a773907511cdfa5490c572ae9be1be33e8afa4a" +dependencies = [ + "crossbeam-channel", + "crossbeam-deque", + "crossbeam-utils", + "lazy_static", + "num_cpus", +] + +[[package]] +name = "redox_syscall" +version = "0.2.5" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "94341e4e44e24f6b591b59e47a8a027df12e008d73fd5672dbea9cc22f4507d9" +dependencies = [ + "bitflags", +] + +[[package]] +name = "redox_users" +version = "0.4.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "528532f3d801c87aec9def2add9ca802fe569e44a544afe633765267840abe64" +dependencies = [ + "getrandom", + "redox_syscall", +] + +[[package]] +name = "regex" +version = "1.4.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "d9251239e129e16308e70d853559389de218ac275b515068abc96829d05b948a" +dependencies = [ + "aho-corasick", + "memchr", + "regex-syntax", + "thread_local", +] + +[[package]] +name = "regex-syntax" +version = "0.6.22" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "b5eb417147ba9860a96cfe72a0b93bf88fee1744b5636ec99ab20c1aa9376581" + +[[package]] +name = "rustversion" +version = "1.0.4" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "cb5d2a036dc6d2d8fd16fde3498b04306e29bd193bf306a57427019b823d5acd" + +[[package]] +name = "ryu" +version = "1.0.5" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "71d301d4193d031abdd79ff7e3dd721168a9572ef3fe51a1517aba235bd8f86e" + +[[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 = "scoped-tls" +version = "1.0.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "ea6a9290e3c9cf0f18145ef7ffa62d68ee0bf5fcd651017e586dc7fd5da448c2" + +[[package]] +name = "scopeguard" +version = "1.1.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "d29ab0c6d3fc0ee92fe66e2d99f700eab17a8d57d1c1d3b748380fb20baa78cd" + +[[package]] +name = "serde" +version = "1.0.123" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "92d5161132722baa40d802cc70b15262b98258453e85e5d1d365c757c73869ae" +dependencies = [ + "serde_derive", +] + +[[package]] +name = "serde_derive" +version = "1.0.123" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "9391c295d64fc0abb2c556bad848f33cb8296276b1ad2677d1ae1ace4f258f31" +dependencies = [ + "proc-macro2", + "quote", + "syn", +] + +[[package]] +name = "serde_json" +version = "1.0.62" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "ea1c6153794552ea7cf7cf63b1231a25de00ec90db326ba6264440fa08e31486" +dependencies = [ + "itoa", + "ryu", + "serde", +] + +[[package]] +name = "sha-1" +version = "0.8.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "f7d94d0bede923b3cea61f3f1ff57ff8cdfd77b400fb8f9998949e0cf04163df" +dependencies = [ + "block-buffer", + "digest", + "fake-simd", + "opaque-debug", +] + +[[package]] +name = "slug" +version = "0.1.4" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "b3bc762e6a4b6c6fcaade73e77f9ebc6991b676f88bb2358bddb56560f073373" +dependencies = [ + "deunicode", +] + +[[package]] +name = "smallvec" +version = "1.6.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "fe0f37c9e8f3c5a4a66ad655a93c74daac4ad00c441533bf5c6e7990bb42604e" + +[[package]] +name = "strsim" +version = "0.8.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "8ea5119cdb4c55b55d432abb513a0429384878c15dde60cc77b1c99de1a95a6a" + +[[package]] +name = "syn" +version = "1.0.60" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "c700597eca8a5a762beb35753ef6b94df201c81cca676604f547495a0d7f0081" +dependencies = [ + "proc-macro2", + "quote", + "unicode-xid", +] + +[[package]] +name = "tera" +version = "1.6.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "eac6ab7eacf40937241959d540670f06209c38ceadb62116999db4a950fbf8dc" +dependencies = [ + "chrono", + "chrono-tz", + "globwalk", + "humansize", + "lazy_static", + "percent-encoding", + "pest", + "pest_derive", + "rand", + "regex", + "serde", + "serde_json", + "slug", + "unic-segment", +] + +[[package]] +name = "term_size" +version = "0.3.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "1e4129646ca0ed8f45d09b929036bafad5377103edd06e50bf574b353d2b08d9" +dependencies = [ + "libc", + "winapi", +] + +[[package]] +name = "termcolor" +version = "1.1.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "2dfed899f0eb03f32ee8c6a0aabdb8a7949659e3466561fc0adf54e26d88c5f4" +dependencies = [ + "winapi-util", +] + +[[package]] +name = "textwrap" +version = "0.11.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "d326610f408c7a4eb6f51c37c330e496b08506c9457c9d34287ecc38809fb060" +dependencies = [ + "unicode-width", +] + +[[package]] +name = "thread_local" +version = "1.1.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "8018d24e04c95ac8790716a5987d0fec4f8b27249ffa0f7d33f1369bdfb88cbd" +dependencies = [ + "once_cell", +] + +[[package]] +name = "time" +version = "0.1.43" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "ca8a50ef2360fbd1eeb0ecd46795a87a19024eb4b53c5dc916ca1fd95fe62438" +dependencies = [ + "libc", + "winapi", +] + +[[package]] +name = "tokei" +version = "12.1.2" +dependencies = [ + "aho-corasick", + "arbitrary", + "clap", + "crossbeam-channel", + "dashmap", + "dirs-next", + "encoding_rs_io", + "env_logger", + "grep-searcher", + "ignore", + "log", + "num-format", + "once_cell", + "parking_lot", + "rayon", + "regex", + "serde", + "serde_json", + "tera", + "term_size", + "toml", +] + +[[package]] +name = "tokei-fuzz" +version = "0.0.1" +dependencies = [ + "arbitrary", + "libfuzzer-sys", + "tokei", +] + +[[package]] +name = "toml" +version = "0.5.8" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "a31142970826733df8241ef35dc040ef98c679ab14d7c3e54d827099b3acecaa" +dependencies = [ + "serde", +] + +[[package]] +name = "typenum" +version = "1.12.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "373c8a200f9e67a0c95e62a4f52fbf80c23b4381c05a17845531982fa99e6b33" + +[[package]] +name = "ucd-trie" +version = "0.1.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "56dee185309b50d1f11bfedef0fe6d036842e3fb77413abef29f8f8d1c5d4c1c" + +[[package]] +name = "unic-char-property" +version = "0.9.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "a8c57a407d9b6fa02b4795eb81c5b6652060a15a7903ea981f3d723e6c0be221" +dependencies = [ + "unic-char-range", +] + +[[package]] +name = "unic-char-range" +version = "0.9.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "0398022d5f700414f6b899e10b8348231abf9173fa93144cbc1a43b9793c1fbc" + +[[package]] +name = "unic-common" +version = "0.9.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "80d7ff825a6a654ee85a63e80f92f054f904f21e7d12da4e22f9834a4aaa35bc" + +[[package]] +name = "unic-segment" +version = "0.9.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "e4ed5d26be57f84f176157270c112ef57b86debac9cd21daaabbe56db0f88f23" +dependencies = [ + "unic-ucd-segment", +] + +[[package]] +name = "unic-ucd-segment" +version = "0.9.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "2079c122a62205b421f499da10f3ee0f7697f012f55b675e002483c73ea34700" +dependencies = [ + "unic-char-property", + "unic-char-range", + "unic-ucd-version", +] + +[[package]] +name = "unic-ucd-version" +version = "0.9.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "96bd2f2237fe450fcd0a1d2f5f4e91711124f7857ba2e964247776ebeeb7b0c4" +dependencies = [ + "unic-common", +] + +[[package]] +name = "unicode-width" +version = "0.1.8" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "9337591893a19b88d8d87f2cec1e73fad5cdfd10e5a6f349f498ad6ea2ffb1e3" + +[[package]] +name = "unicode-xid" +version = "0.2.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "f7fe0bb3479651439c9112f72b6c505038574c9fbb575ed1bf3b797fa39dd564" + +[[package]] +name = "vec_map" +version = "0.8.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "f1bddf1187be692e79c5ffeab891132dfb0f236ed36a43c7ed39f1165ee20191" + +[[package]] +name = "walkdir" +version = "2.3.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "777182bc735b6424e1a57516d35ed72cb8019d85c8c9bf536dccb3445c1a2f7d" +dependencies = [ + "same-file", + "winapi", + "winapi-util", +] + +[[package]] +name = "wasi" +version = "0.10.2+wasi-snapshot-preview1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "fd6fbd9a79829dd1ad0cc20627bf1ed606756a7f77edff7b66b7064f9cb327c6" + +[[package]] +name = "winapi" +version = "0.3.9" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "5c839a674fcd7a98952e593242ea400abe93992746761e38641405d28b00f419" +dependencies = [ + "winapi-i686-pc-windows-gnu", + "winapi-x86_64-pc-windows-gnu", +] + +[[package]] +name = "winapi-i686-pc-windows-gnu" +version = "0.4.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "ac3b87c63620426dd9b991e5ce0329eff545bccbbb34f3be09ff6fb6ab51b7b6" + +[[package]] +name = "winapi-util" +version = "0.1.5" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "70ec6ce85bb158151cae5e5c87f95a8e97d2c0c4b001223f33a334e3ce5de178" +dependencies = [ + "winapi", +] + +[[package]] +name = "winapi-x86_64-pc-windows-gnu" +version = "0.4.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "712e227841d057c1ee1cd2fb22fa7e5a5461ae8e48fa2ca79ec42cfc1931183f" diff --git a/fuzz/Cargo.toml b/fuzz/Cargo.toml new file mode 100644 index 0000000..fd165c3 --- /dev/null +++ b/fuzz/Cargo.toml @@ -0,0 +1,33 @@ + +[package] +name = "tokei-fuzz" +version = "0.0.1" +authors = ["Michael Macnair"] +publish = false +edition = "2018" + +[package.metadata] +cargo-fuzz = true + +[dependencies] +libfuzzer-sys = "0.4" +arbitrary = { version = "1.0.0", features = ["derive"] } + +[dependencies.tokei] +path = ".." + +# Prevent this from interfering with workspaces +[workspace] +members = ["."] + +[[bin]] +name = "parse_from_slice_total" +path = "fuzz_targets/parse_from_slice_total.rs" +test = false +doc = false + +[[bin]] +name = "parse_from_slice_panic" +path = "fuzz_targets/parse_from_slice_panic.rs" +test = false +doc = false diff --git a/fuzz/README.md b/fuzz/README.md new file mode 100644 index 0000000..adfcdcf --- /dev/null +++ b/fuzz/README.md @@ -0,0 +1,30 @@ +## Fuzzing Tokei + +Tokei can be fuzzed using libFuzzer, via [cargo-fuzz](https://github.com/rust-fuzz/cargo-fuzz/). + +First install cargo-fuzz: `cargo install cargo-fuzz`. + +To launch a fuzzing job: `cargo +nightly fuzz run ` - it will run until you kill it with ctrl-c. + +To use multiple cores: `cargo +nightly fuzz run --jobs=6` + +To speed things up (at the expensive of missing bugs that only manifest in larger files): +`cargo +nightly fuzz run -- -max_len=200` + +Available fuzz targets: + +- `parse_from_slice_panic` - checks that all of the LanguageType instances' `parse_from_slice` function doesn't panic. +- `parse_from_slice_total` - checks that the language stats pass a basic test of reporting no more total lines than + there are new lines in the file. At the time of writing there are low-hanging bugs here. + +With the two `parse_from_slice` fuzz targets, it makes sense to share a common corpus directory as they have identical +input formats, e.g.: `cargo +nightly fuzz run parse_from_slice_{panic,total} fuzz/corpus/common` + +Potential improvements: + +- Build the fuzz harnesses in CI, so they don't rot. +- Do some coverage analysis to check if we're missing any code we would benefit from fuzzing (once it's + [integrated into cargo-fuzz](https://github.com/rust-fuzz/cargo-fuzz/pull/248)) +- Tighten the `parse_from_slice_total` fuzz target to check the total lines exactly matches the number of lines in the + file. Only once any bugs found with the current fuzzer are fixed. +- Check in a minimized corpus, and run regression over it in CI. diff --git a/fuzz/fuzz_targets/parse_from_slice.rs b/fuzz/fuzz_targets/parse_from_slice.rs new file mode 100644 index 0000000..c251a8c --- /dev/null +++ b/fuzz/fuzz_targets/parse_from_slice.rs @@ -0,0 +1,51 @@ +use arbitrary::Arbitrary; +use std::str; + +use tokei::{Config, LanguageType}; + +#[derive(Arbitrary, Debug)] +pub struct FuzzInput<'a> { + lang: LanguageType, + treat_doc_strings_as_comments: bool, + data: &'a [u8], +} + +// The first byte of data is used to select a language; remaining input is parsed +// If check_total is true, asserts that the parsed stats pass a basic sanity test +pub fn parse_from_slice(input: FuzzInput, check_total: bool) { + let config = &Config { + treat_doc_strings_as_comments: Some(input.treat_doc_strings_as_comments), + + // these options don't impact the behaviour of parse_from_slice: + columns: None, + hidden: None, + no_ignore: None, + no_ignore_parent: None, + no_ignore_dot: None, + no_ignore_vcs: None, + sort: None, + types: None, + }; + + // check that parsing doesn't panic + let stats = input.lang.parse_from_slice(input.data, config); + + if check_total { + // verify that the parsed total lines is not more than the total occurences of \n and \r\n. + // if/when all of the current discrepancies are fixed, we could make this stronger by checking it is equal. + if let Ok(s) = str::from_utf8(input.data) { + assert!( + stats.lines() <= s.lines().count(), + "{} got more total lines ({}) than str::lines ({}). Code: {}, Comments: {}, Blanks: {}. treat_doc_strings_as_comments: {}. File contents (as UTF-8):\n{}", + input.lang.name(), + stats.lines(), + s.lines().count(), + stats.code, + stats.comments, + input.treat_doc_strings_as_comments, + stats.blanks, + s + ) + }; + } +} diff --git a/fuzz/fuzz_targets/parse_from_slice_panic.rs b/fuzz/fuzz_targets/parse_from_slice_panic.rs new file mode 100644 index 0000000..d59df84 --- /dev/null +++ b/fuzz/fuzz_targets/parse_from_slice_panic.rs @@ -0,0 +1,9 @@ +#![no_main] +use libfuzzer_sys::fuzz_target; + +mod parse_from_slice; +use parse_from_slice::{parse_from_slice, FuzzInput}; + +fuzz_target!(|data: FuzzInput| { + parse_from_slice(data, false); +}); diff --git a/fuzz/fuzz_targets/parse_from_slice_total.rs b/fuzz/fuzz_targets/parse_from_slice_total.rs new file mode 100644 index 0000000..7754b37 --- /dev/null +++ b/fuzz/fuzz_targets/parse_from_slice_total.rs @@ -0,0 +1,9 @@ +#![no_main] +use libfuzzer_sys::fuzz_target; + +mod parse_from_slice; +use parse_from_slice::{parse_from_slice, FuzzInput}; + +fuzz_target!(|data: FuzzInput| { + parse_from_slice(data, true); +}); diff --git a/src/language/language_type.tera.rs b/src/language/language_type.tera.rs index 45ffa48..73d74bf 100644 --- a/src/language/language_type.tera.rs +++ b/src/language/language_type.tera.rs @@ -1,9 +1,11 @@ +use arbitrary::Arbitrary; + /// Represents a individual programming language. Can be used to provide /// information about the language, such as multi line comments, single line /// comments, string literal syntax, whether a given language allows nesting /// comments. #[derive(Deserialize, Serialize)] -#[derive(Clone, Copy, Debug, Eq, Hash, Ord, PartialEq, PartialOrd)] +#[derive(Arbitrary, Clone, Copy, Debug, Eq, Hash, Ord, PartialEq, PartialOrd)] #[non_exhaustive] pub enum LanguageType { {% for key, _ in languages -%}