From 1e4d80a21f6bce80aff18f6d2f1b2ae41f527dc0 Mon Sep 17 00:00:00 2001 From: Conrad Irwin Date: Thu, 4 Dec 2025 00:29:31 -0700 Subject: [PATCH] Update fancy-regex (#44120) Fancy regex has a max backtracking limit which defaults to 1,000,000 backtracks. This avoids spinning the CPU forever in the case that a match is taking a long time (though does mean that some matches may be missed). Unfortunately the verison we depended on causes an infinite loop when the backtracking limit is hit (https://github.com/fancy-regex/fancy-regex/issues/137), so we got the worse of both worlds: matches were missed *and* we spun the CPU forever. Updating fixes this. Excitingly regex may gain support for lookarounds (https://github.com/rust-lang/regex/pull/1315), which will make fancy-regex much less load bearing. Closes #43821 Release Notes: - Fix a bug where search regexes with look-around or backreferences could hang the CPU. They will now abort after a certain number of match attempts. --- Cargo.lock | 88 +++++++++++++++++++++++++----------------------------- Cargo.toml | 6 ++-- 2 files changed, 43 insertions(+), 51 deletions(-) diff --git a/Cargo.lock b/Cargo.lock index 03b7339856a9adba3538152ac3874fd0dec859b5..5078c79e21ce1a580a6e055a7ce8ab4295f56906 100644 --- a/Cargo.lock +++ b/Cargo.lock @@ -2130,30 +2130,15 @@ dependencies = [ "syn 2.0.106", ] -[[package]] -name = "bit-set" -version = "0.5.3" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "0700ddab506f33b20a03b13996eccd309a48e5ff77d0d95926aa0210fb4e95f1" -dependencies = [ - "bit-vec 0.6.3", -] - [[package]] name = "bit-set" version = "0.8.0" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "08807e080ed7f9d5433fa9b275196cfc35414f66a0c79d864dc51a0d825231a3" dependencies = [ - "bit-vec 0.8.0", + "bit-vec", ] -[[package]] -name = "bit-vec" -version = "0.6.3" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "349f9b6a179ed607305526ca489b34ad0a41aed5f7980fa90eb03160b69598fb" - [[package]] name = "bit-vec" version = "0.8.0" @@ -2332,9 +2317,9 @@ dependencies = [ [[package]] name = "borrow-or-share" -version = "0.2.2" +version = "0.2.4" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "3eeab4423108c5d7c744f4d234de88d18d636100093ae04caf4825134b9c3a32" +checksum = "dc0b364ead1874514c8c2855ab558056ebfeb775653e7ae45ff72f28f8f3166c" [[package]] name = "borsh" @@ -6008,22 +5993,11 @@ checksum = "7360491ce676a36bf9bb3c56c1aa791658183a54d2744120f27285738d90465a" [[package]] name = "fancy-regex" -version = "0.13.0" -source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "531e46835a22af56d1e3b66f04844bed63158bc094a628bec1d321d9b4c44bf2" -dependencies = [ - "bit-set 0.5.3", - "regex-automata", - "regex-syntax", -] - -[[package]] -name = "fancy-regex" -version = "0.14.0" +version = "0.16.2" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "6e24cb5a94bcae1e5408b0effca5cd7172ea3c5755049c5f3af4cd283a165298" +checksum = "998b056554fbe42e03ae0e152895cd1a7e1002aec800fdc6635d20270260c46f" dependencies = [ - "bit-set 0.8.0", + "bit-set", "regex-automata", "regex-syntax", ] @@ -6245,9 +6219,9 @@ checksum = "8bf7cc16383c4b8d58b9905a8509f02926ce3058053c056376248d958c9df1e8" [[package]] name = "fluent-uri" -version = "0.3.2" +version = "0.4.1" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "1918b65d96df47d3591bed19c5cca17e3fa5d0707318e4b5ef2eae01764df7e5" +checksum = "bc74ac4d8359ae70623506d512209619e5cf8f347124910440dbc221714b328e" dependencies = [ "borrow-or-share", "ref-cast", @@ -7543,6 +7517,17 @@ dependencies = [ "serde", ] +[[package]] +name = "hashbrown" +version = "0.16.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "841d1cc9bed7f9236f321df977030373f4a4163ae1a7dbfe1a51a2c1a51d9100" +dependencies = [ + "allocator-api2", + "equivalent", + "foldhash 0.2.0", +] + [[package]] name = "hashlink" version = "0.8.4" @@ -8632,21 +8617,21 @@ dependencies = [ [[package]] name = "jsonschema" -version = "0.30.0" +version = "0.37.4" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "f1b46a0365a611fbf1d2143104dcf910aada96fafd295bab16c60b802bf6fa1d" +checksum = "73c9ffb2b5c56d58030e1b532d8e8389da94590515f118cf35b5cb68e4764a7e" dependencies = [ "ahash 0.8.12", - "base64 0.22.1", "bytecount", + "data-encoding", "email_address", - "fancy-regex 0.14.0", + "fancy-regex", "fraction", + "getrandom 0.3.4", "idna", "itoa", "num-cmp", "num-traits", - "once_cell", "percent-encoding", "referencing", "regex", @@ -8654,6 +8639,7 @@ dependencies = [ "reqwest 0.12.24", "serde", "serde_json", + "unicode-general-category", "uuid-simd", ] @@ -10202,7 +10188,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "2b977c445f26e49757f9aca3631c3b8b836942cb278d69a92e7b80d3b24da632" dependencies = [ "arrayvec", - "bit-set 0.8.0", + "bit-set", "bitflags 2.9.4", "cfg_aliases 0.2.1", "codespan-reporting 0.12.0", @@ -13058,7 +13044,7 @@ dependencies = [ "dap", "dap_adapters", "extension", - "fancy-regex 0.14.0", + "fancy-regex", "fs", "futures 0.3.31", "fuzzy", @@ -13929,13 +13915,14 @@ dependencies = [ [[package]] name = "referencing" -version = "0.30.0" +version = "0.37.4" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "c8eff4fa778b5c2a57e85c5f2fe3a709c52f0e60d23146e2151cbef5893f420e" +checksum = "4283168a506f0dcbdce31c9f9cce3129c924da4c6bca46e46707fcb746d2d70c" dependencies = [ "ahash 0.8.12", "fluent-uri", - "once_cell", + "getrandom 0.3.4", + "hashbrown 0.16.1", "parking_lot", "percent-encoding", "serde_json", @@ -17129,7 +17116,7 @@ dependencies = [ "alacritty_terminal", "anyhow", "collections", - "fancy-regex 0.14.0", + "fancy-regex", "futures 0.3.31", "gpui", "itertools 0.14.0", @@ -17363,12 +17350,12 @@ dependencies = [ [[package]] name = "tiktoken-rs" version = "0.9.1" -source = "git+https://github.com/zed-industries/tiktoken-rs?rev=7249f999c5fdf9bf3cc5c288c964454e4dac0c00#7249f999c5fdf9bf3cc5c288c964454e4dac0c00" +source = "git+https://github.com/zed-industries/tiktoken-rs?rev=2570c4387a8505fb8f1d3f3557454b474f1e8271#2570c4387a8505fb8f1d3f3557454b474f1e8271" dependencies = [ "anyhow", "base64 0.22.1", "bstr", - "fancy-regex 0.13.0", + "fancy-regex", "lazy_static", "regex", "rustc-hash 1.1.0", @@ -18500,6 +18487,12 @@ version = "0.4.0" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "ce61d488bcdc9bc8b5d1772c404828b17fc481c0a582b5581e95fb233aef503e" +[[package]] +name = "unicode-general-category" +version = "1.1.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "0b993bddc193ae5bd0d623b49ec06ac3e9312875fdae725a975c51db1cc1677f" + [[package]] name = "unicode-ident" version = "1.0.19" @@ -18734,7 +18727,6 @@ source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "23b082222b4f6619906941c17eb2297fff4c2fb96cb60164170522942a200bd8" dependencies = [ "outref", - "uuid", "vsimd", ] diff --git a/Cargo.toml b/Cargo.toml index e81e53426fc9ee47000e14cb8141ce4e4b6d8b30..59b9a53d4a60b28582625fb90b64b934079cdc40 100644 --- a/Cargo.toml +++ b/Cargo.toml @@ -505,7 +505,7 @@ ec4rs = "1.1" emojis = "0.6.1" env_logger = "0.11" exec = "0.3.1" -fancy-regex = "0.14.0" +fancy-regex = "0.16.0" fork = "0.4.0" futures = "0.3" futures-batch = "0.6.1" @@ -531,7 +531,7 @@ indoc = "2" inventory = "0.3.19" itertools = "0.14.0" json_dotpath = "1.1" -jsonschema = "0.30.0" +jsonschema = "0.37.0" jsonwebtoken = "9.3" jupyter-protocol = "0.10.0" jupyter-websocket-client = "0.15.0" @@ -658,7 +658,7 @@ sysinfo = "0.37.0" take-until = "0.2.0" tempfile = "3.20.0" thiserror = "2.0.12" -tiktoken-rs = { git = "https://github.com/zed-industries/tiktoken-rs", rev = "7249f999c5fdf9bf3cc5c288c964454e4dac0c00" } +tiktoken-rs = { git = "https://github.com/zed-industries/tiktoken-rs", rev = "2570c4387a8505fb8f1d3f3557454b474f1e8271" } time = { version = "0.3", features = [ "macros", "parsing",