dirstate-tree: optimize HashMap lookups with raw_entry_mut

This switches to using `HashMap` from the hashbrown crate,
in order to use its `raw_entry_mut` method.
The standard library’s `HashMap` is also based on this same crate,
but `raw_entry_mut` is not yet stable there:
https://github.com/rust-lang/rust/issues/56167

Using version 0.9 because 0.10 is yanked and 0.11 requires Rust 1.49

This replaces in `DirstateMap::get_or_insert_node` a call to
`HashMap<K, V>::entry` with `K = WithBasename<Cow<'on_disk, HgPath>>`.

`entry` takes and consumes an "owned" `key: K` parameter, in case a new entry
ends up inserted. This key is converted by `to_cow` from a value that borrows
the `'path` lifetime.

When this function is called by `Dirstate::new_v1`, `'path` is in fact
the same as `'on_disk` so `to_cow` can return an owned key that contains
`Cow::Borrowed`.

For other callers, `to_cow` needs to create a `Cow::Owned` and thus make
a costly heap memory allocation. This is wasteful if this key was already
present in the map. Even when inserting a new node this is typically the case
for its ancestor nodes (assuming most directories have numerous descendants).

Differential Revision: https://phab.mercurial-scm.org/D12317

rust/Cargo.lock

@@ -1,1142 +1,1159 b''
 # This file is automatically @generated by Cargo.
 # It is not intended for manual editing.
 version = 3
 
 [[package]]
 name = "adler"
 version = "0.2.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "ee2a4ec343196209d6594e19543ae87a39f96d5534d7174822a3ad825dd6ed7e"
 
 [[package]]
+name = "ahash"
+version = "0.4.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "739f4a8db6605981345c5654f3a85b056ce52f37a39d34da03f25bf2151ea16e"
+
+[[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 = "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 = "bitmaps"
 version = "2.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "031043d04099746d8db04daf1fa424b2bc8bd69d92b25962dcde24da39ab64a2"
 dependencies = [
  "typenum",
 ]
 
 [[package]]
 name = "block-buffer"
 version = "0.9.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "4152116fd6e9dadb291ae18fc1ec3575ed6d84c29642d97890f4b4a3417297e4"
 dependencies = [
  "generic-array",
 ]
 
 [[package]]
 name = "byteorder"
 version = "1.3.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "08c48aae112d48ed9f069b33538ea9e3e90aa263cfa3d1c24309612b1f7472de"
 
 [[package]]
 name = "bytes-cast"
 version = "0.2.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "0d434f9a4ecbe987e7ccfda7274b6f82ea52c9b63742565a65cb5e8ba0f2c452"
 dependencies = [
  "bytes-cast-derive",
 ]
 
 [[package]]
 name = "bytes-cast-derive"
 version = "0.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "cb936af9de38476664d6b58e529aff30d482e4ce1c5e150293d00730b0d81fdb"
 dependencies = [
  "proc-macro2",
  "quote",
  "syn",
 ]
 
 [[package]]
 name = "cc"
 version = "1.0.66"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "4c0496836a84f8d0495758516b8621a622beb77c0fed418570e50764093ced48"
 dependencies = [
  "jobserver",
 ]
 
 [[package]]
 name = "cfg-if"
 version = "0.1.10"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "4785bdd1c96b2a846b2bd7cc02e86b6b3dbf14e7e53446c4f54c92a361040822"
 
 [[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 = "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 = "const_fn"
 version = "0.4.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "cd51eab21ab4fd6a3bf889e2d0958c0a6e3a61ad04260325e919e652a2a62826"
 
 [[package]]
 name = "cpufeatures"
 version = "0.1.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "ed00c67cb5d0a7d64a44f6ad2668db7e7530311dd53ea79bcd4fb022c64911c8"
 dependencies = [
  "libc",
 ]
 
 [[package]]
 name = "cpython"
 version = "0.7.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "b7d46ba8ace7f3a1d204ac5060a706d0a68de6b42eafb6a586cc08bebcffe664"
 dependencies = [
  "libc",
  "num-traits",
  "paste",
  "python3-sys",
 ]
 
 [[package]]
 name = "crc32fast"
 version = "1.2.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "81156fece84ab6a9f2afdb109ce3ae577e42b1228441eded99bd77f627953b1a"
 dependencies = [
  "cfg-if 1.0.0",
 ]
 
 [[package]]
 name = "crossbeam-channel"
 version = "0.4.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "b153fe7cbef478c567df0f972e02e6d736db11affe43dfc9c56a9374d1adfb87"
 dependencies = [
  "crossbeam-utils 0.7.2",
  "maybe-uninit",
 ]
 
 [[package]]
 name = "crossbeam-channel"
 version = "0.5.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "dca26ee1f8d361640700bde38b2c37d8c22b3ce2d360e1fc1c74ea4b0aa7d775"
 dependencies = [
  "cfg-if 1.0.0",
  "crossbeam-utils 0.8.1",
 ]
 
 [[package]]
 name = "crossbeam-deque"
 version = "0.8.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "94af6efb46fef72616855b036a624cf27ba656ffc9be1b9a3c931cfc7749a9a9"
 dependencies = [
  "cfg-if 1.0.0",
  "crossbeam-epoch",
  "crossbeam-utils 0.8.1",
 ]
 
 [[package]]
 name = "crossbeam-epoch"
 version = "0.9.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "a1aaa739f95311c2c7887a76863f500026092fb1dce0161dab577e559ef3569d"
 dependencies = [
  "cfg-if 1.0.0",
  "const_fn",
  "crossbeam-utils 0.8.1",
  "lazy_static",
  "memoffset",
  "scopeguard",
 ]
 
 [[package]]
 name = "crossbeam-utils"
 version = "0.7.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "c3c7c73a2d1e9fc0886a08b93e98eb643461230d5f1925e4036204d5f2e261a8"
 dependencies = [
  "autocfg",
  "cfg-if 0.1.10",
  "lazy_static",
 ]
 
 [[package]]
 name = "crossbeam-utils"
 version = "0.8.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "02d96d1e189ef58269ebe5b97953da3274d83a93af647c2ddd6f9dab28cedb8d"
 dependencies = [
  "autocfg",
  "cfg-if 1.0.0",
  "lazy_static",
 ]
 
 [[package]]
 name = "ctor"
 version = "0.1.16"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "7fbaabec2c953050352311293be5c6aba8e141ba19d6811862b232d6fd020484"
 dependencies = [
  "quote",
  "syn",
 ]
 
 [[package]]
 name = "derive_more"
 version = "0.99.11"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "41cb0e6161ad61ed084a36ba71fbba9e3ac5aee3606fb607fe08da6acbcf3d8c"
 dependencies = [
  "proc-macro2",
  "quote",
  "syn",
 ]
 
 [[package]]
 name = "difference"
 version = "2.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "524cbf6897b527295dff137cec09ecf3a05f4fddffd7dfcd1585403449e74198"
 
 [[package]]
 name = "digest"
 version = "0.9.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "d3dd60d1080a57a05ab032377049e0591415d2b31afd7028356dbf3cc6dcb066"
 dependencies = [
  "generic-array",
 ]
 
 [[package]]
 name = "either"
 version = "1.6.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "e78d4f1cc4ae33bbfc157ed5d5a5ef3bc29227303d595861deb238fcec4e9457"
 
 [[package]]
 name = "env_logger"
 version = "0.7.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "44533bbbb3bb3c1fa17d9f2e4e38bbbaf8396ba82193c4cb1b6445d711445d36"
 dependencies = [
  "atty",
  "humantime",
  "log",
  "regex",
  "termcolor",
 ]
 
 [[package]]
 name = "flate2"
 version = "1.0.19"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "7411863d55df97a419aa64cb4d2f167103ea9d767e2c54a1868b7ac3f6b47129"
 dependencies = [
  "cfg-if 1.0.0",
  "crc32fast",
  "libc",
  "libz-sys",
  "miniz_oxide",
 ]
 
 [[package]]
 name = "format-bytes"
 version = "0.3.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "48942366ef93975da38e175ac9e10068c6fc08ca9e85930d4f098f4d5b14c2fd"
 dependencies = [
  "format-bytes-macros",
 ]
 
 [[package]]
 name = "format-bytes-macros"
 version = "0.4.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "203aadebefcc73d12038296c228eabf830f99cba991b0032adf20e9fa6ce7e4f"
 dependencies = [
  "proc-macro2",
  "quote",
  "syn",
 ]
 
 [[package]]
 name = "generic-array"
 version = "0.14.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "501466ecc8a30d1d3b7fc9229b122b2ce8ed6e9d9223f1138d4babb253e51817"
 dependencies = [
  "typenum",
  "version_check",
 ]
 
 [[package]]
 name = "getrandom"
 version = "0.1.15"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "fc587bc0ec293155d5bfa6b9891ec18a1e330c234f896ea47fbada4cadbe47e6"
 dependencies = [
  "cfg-if 0.1.10",
  "libc",
  "wasi 0.9.0+wasi-snapshot-preview1",
 ]
 
 [[package]]
 name = "getrandom"
 version = "0.2.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "418d37c8b1d42553c93648be529cb70f920d3baf8ef469b74b9638df426e0b4c"
 dependencies = [
  "cfg-if 1.0.0",
  "libc",
  "wasi 0.10.0+wasi-snapshot-preview1",
 ]
 
 [[package]]
 name = "glob"
 version = "0.3.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "9b919933a397b79c37e33b77bb2aa3dc8eb6e165ad809e58ff75bc7db2e34574"
 
 [[package]]
+name = "hashbrown"
+version = "0.9.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d7afe4a420e3fe79967a00898cc1f4db7c8a49a9333a29f8a4bd76a253d5cd04"
+dependencies = [
+ "ahash",
+ "rayon",
+]
+
+[[package]]
 name = "hermit-abi"
 version = "0.1.17"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "5aca5565f760fb5b220e499d72710ed156fdb74e631659e99377d9ebfbd13ae8"
 dependencies = [
  "libc",
 ]
 
 [[package]]
 name = "hex"
 version = "0.4.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "7f24254aa9a54b5c858eaee2f5bccdb46aaf0e486a595ed5fd8f86ba55232a70"
 
 [[package]]
 name = "hg-core"
 version = "0.1.0"
 dependencies = [
  "bitflags",
  "byteorder",
  "bytes-cast",
  "clap",
  "crossbeam-channel 0.4.4",
  "derive_more",
  "flate2",
  "format-bytes",
+ "hashbrown",
  "home",
  "im-rc",
  "itertools",
  "lazy_static",
  "libc",
  "log",
  "memmap2",
  "micro-timer",
  "pretty_assertions",
  "rand 0.8.4",
  "rand_distr",
  "rand_pcg",
  "rayon",
  "regex",
  "same-file",
  "sha-1",
  "stable_deref_trait",
  "tempfile",
  "twox-hash",
  "zstd",
 ]
 
 [[package]]
 name = "hg-cpython"
 version = "0.1.0"
 dependencies = [
  "cpython",
  "crossbeam-channel 0.4.4",
  "env_logger",
  "hg-core",
  "libc",
  "log",
  "stable_deref_trait",
  "vcsgraph",
 ]
 
 [[package]]
 name = "home"
 version = "0.5.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "2456aef2e6b6a9784192ae780c0f15bc57df0e918585282325e8c8ac27737654"
 dependencies = [
  "winapi",
 ]
 
 [[package]]
 name = "humantime"
 version = "1.3.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "df004cfca50ef23c36850aaaa59ad52cc70d0e90243c3c7737a4dd32dc7a3c4f"
 dependencies = [
  "quick-error",
 ]
 
 [[package]]
 name = "im-rc"
 version = "15.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "3ca8957e71f04a205cb162508f9326aea04676c8dfd0711220190d6b83664f3f"
 dependencies = [
  "bitmaps",
  "rand_core 0.5.1",
  "rand_xoshiro",
  "sized-chunks",
  "typenum",
  "version_check",
 ]
 
 [[package]]
 name = "itertools"
 version = "0.9.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "284f18f85651fe11e8a991b2adb42cb078325c996ed026d994719efcfca1d54b"
 dependencies = [
  "either",
 ]
 
 [[package]]
 name = "jobserver"
 version = "0.1.21"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "5c71313ebb9439f74b00d9d2dcec36440beaf57a6aa0623068441dd7cd81a7f2"
 dependencies = [
  "libc",
 ]
 
 [[package]]
 name = "lazy_static"
 version = "1.4.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "e2abad23fbc42b3700f2f279844dc832adb2b2eb069b2df918f455c4e18cc646"
 
 [[package]]
 name = "libc"
 version = "0.2.81"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "1482821306169ec4d07f6aca392a4681f66c75c9918aa49641a2595db64053cb"
 
 [[package]]
 name = "libm"
 version = "0.2.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "c7d73b3f436185384286bd8098d17ec07c9a7d2388a6599f824d8502b529702a"
 
 [[package]]
 name = "libz-sys"
 version = "1.1.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "602113192b08db8f38796c4e85c39e960c145965140e918018bcde1952429655"
 dependencies = [
  "cc",
  "pkg-config",
  "vcpkg",
 ]
 
 [[package]]
 name = "log"
 version = "0.4.11"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "4fabed175da42fed1fa0746b0ea71f412aa9d35e76e95e59b192c64b9dc2bf8b"
 dependencies = [
  "cfg-if 0.1.10",
 ]
 
 [[package]]
 name = "maybe-uninit"
 version = "2.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "60302e4db3a61da70c0cb7991976248362f30319e88850c487b9b95bbf059e00"
 
 [[package]]
 name = "memchr"
 version = "2.3.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "0ee1c47aaa256ecabcaea351eae4a9b01ef39ed810004e298d2511ed284b1525"
 
 [[package]]
 name = "memmap2"
 version = "0.4.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "de5d3112c080d58ce560081baeaab7e1e864ca21795ddbf533d5b1842bb1ecf8"
 dependencies = [
  "libc",
  "stable_deref_trait",
 ]
 
 [[package]]
 name = "memoffset"
 version = "0.6.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "157b4208e3059a8f9e78d559edc658e13df41410cb3ae03979c83130067fdd87"
 dependencies = [
  "autocfg",
 ]
 
 [[package]]
 name = "micro-timer"
 version = "0.3.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "2620153e1d903d26b72b89f0e9c48d8c4756cba941c185461dddc234980c298c"
 dependencies = [
  "micro-timer-macros",
  "scopeguard",
 ]
 
 [[package]]
 name = "micro-timer-macros"
 version = "0.3.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "e28a3473e6abd6e9aab36aaeef32ad22ae0bd34e79f376643594c2b152ec1c5d"
 dependencies = [
  "proc-macro2",
  "quote",
  "scopeguard",
  "syn",
 ]
 
 [[package]]
 name = "miniz_oxide"
 version = "0.4.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "0f2d26ec3309788e423cfbf68ad1800f061638098d76a83681af979dc4eda19d"
 dependencies = [
  "adler",
  "autocfg",
 ]
 
 [[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",
  "libm",
 ]
 
 [[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 = "opaque-debug"
 version = "0.3.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "624a8340c38c1b80fd549087862da4ba43e08858af025b236e509b6649fc13d5"
 
 [[package]]
 name = "output_vt100"
 version = "0.1.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "53cdc5b785b7a58c5aad8216b3dfa114df64b0b06ae6e1501cef91df2fbdf8f9"
 dependencies = [
  "winapi",
 ]
 
 [[package]]
 name = "paste"
 version = "1.0.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "acbf547ad0c65e31259204bd90935776d1c693cec2f4ff7abb7a1bbbd40dfe58"
 
 [[package]]
 name = "pkg-config"
 version = "0.3.19"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "3831453b3449ceb48b6d9c7ad7c96d5ea673e9b470a1dc578c2ce6521230884c"
 
 [[package]]
 name = "ppv-lite86"
 version = "0.2.10"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "ac74c624d6b2d21f425f752262f42188365d7b8ff1aff74c82e45136510a4857"
 
 [[package]]
 name = "pretty_assertions"
 version = "0.6.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "3f81e1644e1b54f5a68959a29aa86cde704219254669da328ecfdf6a1f09d427"
 dependencies = [
  "ansi_term",
  "ctor",
  "difference",
  "output_vt100",
 ]
 
 [[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 = "python3-sys"
 version = "0.7.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "b18b32e64c103d5045f44644d7ddddd65336f7a0521f6fde673240a9ecceb77e"
 dependencies = [
  "libc",
  "regex",
 ]
 
 [[package]]
 name = "quick-error"
 version = "1.2.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "a1d01941d82fa2ab50be1e79e6714289dd7cde78eba4c074bc5a4374f650dfe0"
 
 [[package]]
 name = "quote"
 version = "1.0.7"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "aa563d17ecb180e500da1cfd2b028310ac758de548efdd203e18f283af693f37"
 dependencies = [
  "proc-macro2",
 ]
 
 [[package]]
 name = "rand"
 version = "0.7.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "6a6b1679d49b24bbfe0c803429aa1874472f50d9b363131f0e89fc356b544d03"
 dependencies = [
  "getrandom 0.1.15",
  "libc",
  "rand_chacha 0.2.2",
  "rand_core 0.5.1",
  "rand_hc 0.2.0",
 ]
 
 [[package]]
 name = "rand"
 version = "0.8.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "2e7573632e6454cf6b99d7aac4ccca54be06da05aca2ef7423d22d27d4d4bcd8"
 dependencies = [
  "libc",
  "rand_chacha 0.3.1",
  "rand_core 0.6.3",
  "rand_hc 0.3.1",
 ]
 
 [[package]]
 name = "rand_chacha"
 version = "0.2.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "f4c8ed856279c9737206bf725bf36935d8666ead7aa69b52be55af369d193402"
 dependencies = [
  "ppv-lite86",
  "rand_core 0.5.1",
 ]
 
 [[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 0.6.3",
 ]
 
 [[package]]
 name = "rand_core"
 version = "0.5.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "90bde5296fc891b0cef12a6d03ddccc162ce7b2aff54160af9338f8d40df6d19"
 dependencies = [
  "getrandom 0.1.15",
 ]
 
 [[package]]
 name = "rand_core"
 version = "0.6.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "d34f1408f55294453790c48b2f1ebbb1c5b4b7563eb1f418bcfcfdbb06ebb4e7"
 dependencies = [
  "getrandom 0.2.4",
 ]
 
 [[package]]
 name = "rand_distr"
 version = "0.4.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "964d548f8e7d12e102ef183a0de7e98180c9f8729f555897a857b96e48122d2f"
 dependencies = [
  "num-traits",
  "rand 0.8.4",
 ]
 
 [[package]]
 name = "rand_hc"
 version = "0.2.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "ca3129af7b92a17112d59ad498c6f81eaf463253766b90396d39ea7a39d6613c"
 dependencies = [
  "rand_core 0.5.1",
 ]
 
 [[package]]
 name = "rand_hc"
 version = "0.3.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "d51e9f596de227fda2ea6c84607f5558e196eeaf43c986b724ba4fb8fdf497e7"
 dependencies = [
  "rand_core 0.6.3",
 ]
 
 [[package]]
 name = "rand_pcg"
 version = "0.3.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "59cad018caf63deb318e5a4586d99a24424a364f40f1e5778c29aca23f4fc73e"
 dependencies = [
  "rand_core 0.6.3",
 ]
 
 [[package]]
 name = "rand_xoshiro"
 version = "0.4.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "a9fcdd2e881d02f1d9390ae47ad8e5696a9e4be7b547a1da2afbc61973217004"
 dependencies = [
  "rand_core 0.5.1",
 ]
 
 [[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 0.5.0",
  "crossbeam-deque",
  "crossbeam-utils 0.8.1",
  "lazy_static",
  "num_cpus",
 ]
 
 [[package]]
 name = "redox_syscall"
 version = "0.1.57"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "41cc0f7e4d5d4544e8861606a285bb08d3e70712ccc7d2b84d7c0ccfaf4b05ce"
 
 [[package]]
 name = "regex"
 version = "1.4.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "38cf2c13ed4745de91a5eb834e11c00bcc3709e773173b2ce4c56c9fbde04b9c"
 dependencies = [
  "aho-corasick",
  "memchr",
  "regex-syntax",
  "thread_local",
 ]
 
 [[package]]
 name = "regex-syntax"
 version = "0.6.21"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "3b181ba2dcf07aaccad5448e8ead58db5b742cf85dfe035e2227f137a539a189"
 
 [[package]]
 name = "remove_dir_all"
 version = "0.5.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "3acd125665422973a33ac9d3dd2df85edad0f4ae9b00dafb1a05e43a9f5ef8e7"
 dependencies = [
  "winapi",
 ]
 
 [[package]]
 name = "rhg"
 version = "0.1.0"
 dependencies = [
  "atty",
  "chrono",
  "clap",
  "derive_more",
  "env_logger",
  "format-bytes",
  "hg-core",
  "home",
  "lazy_static",
  "log",
  "micro-timer",
  "regex",
  "users",
 ]
 
 [[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 = "1.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "d29ab0c6d3fc0ee92fe66e2d99f700eab17a8d57d1c1d3b748380fb20baa78cd"
 
 [[package]]
 name = "sha-1"
 version = "0.9.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "8c4cfa741c5832d0ef7fab46cabed29c2aae926db0b11bb2069edd8db5e64e16"
 dependencies = [
  "block-buffer",
  "cfg-if 1.0.0",
  "cpufeatures",
  "digest",
  "opaque-debug",
 ]
 
 [[package]]
 name = "sized-chunks"
 version = "0.6.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "1ec31ceca5644fa6d444cc77548b88b67f46db6f7c71683b0f9336e671830d2f"
 dependencies = [
  "bitmaps",
  "typenum",
 ]
 
 [[package]]
 name = "stable_deref_trait"
 version = "1.2.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "a8f112729512f8e442d81f95a8a7ddf2b7c6b8a1a6f509a95864142b30cab2d3"
 
 [[package]]
 name = "static_assertions"
 version = "1.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "a2eb9349b6444b326872e140eb1cf5e7c522154d69e7a0ffb0fb81c06b37543f"
 
 [[package]]
 name = "strsim"
 version = "0.8.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "8ea5119cdb4c55b55d432abb513a0429384878c15dde60cc77b1c99de1a95a6a"
 
 [[package]]
 name = "syn"
 version = "1.0.54"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "9a2af957a63d6bd42255c359c93d9bfdb97076bd3b820897ce55ffbfbf107f44"
 dependencies = [
  "proc-macro2",
  "quote",
  "unicode-xid",
 ]
 
 [[package]]
 name = "tempfile"
 version = "3.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "7a6e24d9338a0a5be79593e2fa15a648add6138caa803e2d5bc782c371732ca9"
 dependencies = [
  "cfg-if 0.1.10",
  "libc",
  "rand 0.7.3",
  "redox_syscall",
  "remove_dir_all",
  "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 = "1.0.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "d40c6d1b69745a6ec6fb1ca717914848da4b44ae29d9b3080cbee91d72a69b14"
 dependencies = [
  "lazy_static",
 ]
 
 [[package]]
 name = "time"
 version = "0.1.44"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "6db9e6914ab8b1ae1c260a4ae7a49b6c5611b40328a735b21862567685e73255"
 dependencies = [
  "libc",
  "wasi 0.10.0+wasi-snapshot-preview1",
  "winapi",
 ]
 
 [[package]]
 name = "twox-hash"
 version = "1.6.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "04f8ab788026715fa63b31960869617cba39117e520eb415b0139543e325ab59"
 dependencies = [
  "cfg-if 0.1.10",
  "rand 0.7.3",
  "static_assertions",
 ]
 
 [[package]]
 name = "typenum"
 version = "1.12.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "373c8a200f9e67a0c95e62a4f52fbf80c23b4381c05a17845531982fa99e6b33"
 
 [[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 = "users"
 version = "0.11.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "24cc0f6d6f267b73e5a2cadf007ba8f9bc39c6a6f9666f8cf25ea809a153b032"
 dependencies = [
  "libc",
  "log",
 ]
 
 [[package]]
 name = "vcpkg"
 version = "0.2.11"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "b00bca6106a5e23f3eee943593759b7fcddb00554332e856d990c893966879fb"
 
 [[package]]
 name = "vcsgraph"
 version = "0.2.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "4cb68c231e2575f7503a7c19213875f9d4ec2e84e963a56ce3de4b6bee351ef7"
 dependencies = [
  "hex",
  "rand 0.7.3",
  "sha-1",
 ]
 
 [[package]]
 name = "vec_map"
 version = "0.8.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "f1bddf1187be692e79c5ffeab891132dfb0f236ed36a43c7ed39f1165ee20191"
 
 [[package]]
 name = "version_check"
 version = "0.9.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "b5a972e5669d67ba988ce3dc826706fb0a8b01471c088cb0b6110b805cc36aed"
 
 [[package]]
 name = "wasi"
 version = "0.9.0+wasi-snapshot-preview1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "cccddf32554fecc6acb585f82a32a72e28b48f8c4c1883ddfeeeaa96f7d8e519"
 
 [[package]]
 name = "wasi"
 version = "0.10.0+wasi-snapshot-preview1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "1a143597ca7c7793eff794def352d41792a93c481eb1042423ff7ff72ba2c31f"
 
 [[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"
 
 [[package]]
 name = "zstd"
 version = "0.5.3+zstd.1.4.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "01b32eaf771efa709e8308605bbf9319bf485dc1503179ec0469b611937c0cd8"
 dependencies = [
  "zstd-safe",
 ]
 
 [[package]]
 name = "zstd-safe"
 version = "2.0.5+zstd.1.4.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "1cfb642e0d27f64729a639c52db457e0ae906e7bc6f5fe8f5c453230400f1055"
 dependencies = [
  "libc",
  "zstd-sys",
 ]
 
 [[package]]
 name = "zstd-sys"
 version = "1.4.17+zstd.1.4.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "b89249644df056b522696b1bb9e7c18c87e8ffa3e2f0dc3b0155875d6498f01b"
 dependencies = [
  "cc",
  "glob",
  "itertools",
  "libc",
 ]

rust/hg-core/Cargo.toml

@@ -1,47 +1,48 b''
 [package]
 name = "hg-core"
 version = "0.1.0"
 authors = ["Georges Racinet <[e-mail]>"]
 description = "Mercurial pure Rust core library, with no assumption on Python bindings (FFI)"
 edition = "2018"
 
 [lib]
 name = "hg"
 
 [dependencies]
 bitflags = "1.2"
 bytes-cast = "0.2"
 byteorder = "1.3.4"
 derive_more = "0.99"
+hashbrown = {version = "0.9.1", features = ["rayon"]}
 home = "0.5"
 im-rc = "15.0.*"
 itertools = "0.9"
 lazy_static = "1.4.0"
 libc = "0.2"
 rand = "0.8.4"
 rand_pcg = "0.3.1"
 rand_distr = "0.4.2"
 rayon = "1.3.0"
 regex = "1.3.9"
 sha-1 = "0.9.6"
 twox-hash = "1.5.0"
 same-file = "1.0.6"
 stable_deref_trait = "1.2.0"
 tempfile = "3.1.0"
 crossbeam-channel = "0.4"
 micro-timer = "0.3.0"
 log = "0.4.8"
 memmap2 = {version = "0.4", features = ["stable_deref_trait"]}
 zstd = "0.5.3"
 format-bytes = "0.3.0"
 
 # We don't use the `miniz-oxide` backend to not change rhg benchmarks and until
 # we have a clearer view of which backend is the fastest.
 [dependencies.flate2]
 version = "1.0.16"
 features = ["zlib"]
 default-features = false
 
 [dev-dependencies]
 clap = "*"
 pretty_assertions = "0.6.1"

rust/hg-core/src/dirstate_tree/dirstate_map.rs

@@ -1,1158 +1,1156 b''
 use bytes_cast::BytesCast;
 use micro_timer::timed;
 use std::borrow::Cow;
 use std::path::PathBuf;
 
 use super::on_disk;
 use super::on_disk::DirstateV2ParseError;
 use super::owning::OwningDirstateMap;
 use super::path_with_basename::WithBasename;
 use crate::dirstate::parsers::pack_entry;
 use crate::dirstate::parsers::packed_entry_size;
 use crate::dirstate::parsers::parse_dirstate_entries;
 use crate::dirstate::CopyMapIter;
 use crate::dirstate::StateMapIter;
 use crate::dirstate::TruncatedTimestamp;
 use crate::dirstate::SIZE_FROM_OTHER_PARENT;
 use crate::dirstate::SIZE_NON_NORMAL;
 use crate::matchers::Matcher;
 use crate::utils::hg_path::{HgPath, HgPathBuf};
 use crate::DirstateEntry;
 use crate::DirstateError;
 use crate::DirstateParents;
 use crate::DirstateStatus;
 use crate::EntryState;
-use crate::FastHashMap;
+use crate::FastHashbrownMap as FastHashMap;
 use crate::PatternFileWarning;
 use crate::StatusError;
 use crate::StatusOptions;
 
 /// Append to an existing data file if the amount of unreachable data (not used
 /// anymore) is less than this fraction of the total amount of existing data.
 const ACCEPTABLE_UNREACHABLE_BYTES_RATIO: f32 = 0.5;
 
 pub struct DirstateMap<'on_disk> {
     /// Contents of the `.hg/dirstate` file
     pub(super) on_disk: &'on_disk [u8],
 
     pub(super) root: ChildNodes<'on_disk>,
 
     /// Number of nodes anywhere in the tree that have `.entry.is_some()`.
     pub(super) nodes_with_entry_count: u32,
 
     /// Number of nodes anywhere in the tree that have
     /// `.copy_source.is_some()`.
     pub(super) nodes_with_copy_source_count: u32,
 
     /// See on_disk::Header
     pub(super) ignore_patterns_hash: on_disk::IgnorePatternsHash,
 
     /// How many bytes of `on_disk` are not used anymore
     pub(super) unreachable_bytes: u32,
 }
 
 /// Using a plain `HgPathBuf` of the full path from the repository root as a
 /// map key would also work: all paths in a given map have the same parent
 /// path, so comparing full paths gives the same result as comparing base
 /// names. However `HashMap` would waste time always re-hashing the same
 /// string prefix.
 pub(super) type NodeKey<'on_disk> = WithBasename<Cow<'on_disk, HgPath>>;
 
 /// Similar to `&'tree Cow<'on_disk, HgPath>`, but can also be returned
 /// for on-disk nodes that don’t actually have a `Cow` to borrow.
 pub(super) enum BorrowedPath<'tree, 'on_disk> {
     InMemory(&'tree HgPathBuf),
     OnDisk(&'on_disk HgPath),
 }
 
 pub(super) enum ChildNodes<'on_disk> {
     InMemory(FastHashMap<NodeKey<'on_disk>, Node<'on_disk>>),
     OnDisk(&'on_disk [on_disk::Node]),
 }
 
 pub(super) enum ChildNodesRef<'tree, 'on_disk> {
     InMemory(&'tree FastHashMap<NodeKey<'on_disk>, Node<'on_disk>>),
     OnDisk(&'on_disk [on_disk::Node]),
 }
 
 pub(super) enum NodeRef<'tree, 'on_disk> {
     InMemory(&'tree NodeKey<'on_disk>, &'tree Node<'on_disk>),
     OnDisk(&'on_disk on_disk::Node),
 }
 
 impl<'tree, 'on_disk> BorrowedPath<'tree, 'on_disk> {
     pub fn detach_from_tree(&self) -> Cow<'on_disk, HgPath> {
         match *self {
             BorrowedPath::InMemory(in_memory) => Cow::Owned(in_memory.clone()),
             BorrowedPath::OnDisk(on_disk) => Cow::Borrowed(on_disk),
         }
     }
 }
 
 impl<'tree, 'on_disk> std::ops::Deref for BorrowedPath<'tree, 'on_disk> {
     type Target = HgPath;
 
     fn deref(&self) -> &HgPath {
         match *self {
             BorrowedPath::InMemory(in_memory) => in_memory,
             BorrowedPath::OnDisk(on_disk) => on_disk,
         }
     }
 }
 
 impl Default for ChildNodes<'_> {
     fn default() -> Self {
         ChildNodes::InMemory(Default::default())
     }
 }
 
 impl<'on_disk> ChildNodes<'on_disk> {
     pub(super) fn as_ref<'tree>(
         &'tree self,
     ) -> ChildNodesRef<'tree, 'on_disk> {
         match self {
             ChildNodes::InMemory(nodes) => ChildNodesRef::InMemory(nodes),
             ChildNodes::OnDisk(nodes) => ChildNodesRef::OnDisk(nodes),
         }
     }
 
     pub(super) fn is_empty(&self) -> bool {
         match self {
             ChildNodes::InMemory(nodes) => nodes.is_empty(),
             ChildNodes::OnDisk(nodes) => nodes.is_empty(),
         }
     }
 
     fn make_mut(
         &mut self,
         on_disk: &'on_disk [u8],
         unreachable_bytes: &mut u32,
     ) -> Result<
         &mut FastHashMap<NodeKey<'on_disk>, Node<'on_disk>>,
         DirstateV2ParseError,
     > {
         match self {
             ChildNodes::InMemory(nodes) => Ok(nodes),
             ChildNodes::OnDisk(nodes) => {
                 *unreachable_bytes +=
                     std::mem::size_of_val::<[on_disk::Node]>(nodes) as u32;
                 let nodes = nodes
                     .iter()
                     .map(|node| {
                         Ok((
                             node.path(on_disk)?,
                             node.to_in_memory_node(on_disk)?,
                         ))
                     })
                     .collect::<Result<_, _>>()?;
                 *self = ChildNodes::InMemory(nodes);
                 match self {
                     ChildNodes::InMemory(nodes) => Ok(nodes),
                     ChildNodes::OnDisk(_) => unreachable!(),
                 }
             }
         }
     }
 }
 
 impl<'tree, 'on_disk> ChildNodesRef<'tree, 'on_disk> {
     pub(super) fn get(
         &self,
         base_name: &HgPath,
         on_disk: &'on_disk [u8],
     ) -> Result<Option<NodeRef<'tree, 'on_disk>>, DirstateV2ParseError> {
         match self {
             ChildNodesRef::InMemory(nodes) => Ok(nodes
                 .get_key_value(base_name)
                 .map(|(k, v)| NodeRef::InMemory(k, v))),
             ChildNodesRef::OnDisk(nodes) => {
                 let mut parse_result = Ok(());
                 let search_result = nodes.binary_search_by(|node| {
                     match node.base_name(on_disk) {
                         Ok(node_base_name) => node_base_name.cmp(base_name),
                         Err(e) => {
                             parse_result = Err(e);
                             // Dummy comparison result, `search_result` won’t
                             // be used since `parse_result` is an error
                             std::cmp::Ordering::Equal
                         }
                     }
                 });
                 parse_result.map(|()| {
                     search_result.ok().map(|i| NodeRef::OnDisk(&nodes[i]))
                 })
             }
         }
     }
 
     /// Iterate in undefined order
     pub(super) fn iter(
         &self,
     ) -> impl Iterator<Item = NodeRef<'tree, 'on_disk>> {
         match self {
             ChildNodesRef::InMemory(nodes) => itertools::Either::Left(
                 nodes.iter().map(|(k, v)| NodeRef::InMemory(k, v)),
             ),
             ChildNodesRef::OnDisk(nodes) => {
                 itertools::Either::Right(nodes.iter().map(NodeRef::OnDisk))
             }
         }
     }
 
     /// Iterate in parallel in undefined order
     pub(super) fn par_iter(
         &self,
     ) -> impl rayon::iter::ParallelIterator<Item = NodeRef<'tree, 'on_disk>>
     {
         use rayon::prelude::*;
         match self {
             ChildNodesRef::InMemory(nodes) => rayon::iter::Either::Left(
                 nodes.par_iter().map(|(k, v)| NodeRef::InMemory(k, v)),
             ),
             ChildNodesRef::OnDisk(nodes) => rayon::iter::Either::Right(
                 nodes.par_iter().map(NodeRef::OnDisk),
             ),
         }
     }
 
     pub(super) fn sorted(&self) -> Vec<NodeRef<'tree, 'on_disk>> {
         match self {
             ChildNodesRef::InMemory(nodes) => {
                 let mut vec: Vec<_> = nodes
                     .iter()
                     .map(|(k, v)| NodeRef::InMemory(k, v))
                     .collect();
                 fn sort_key<'a>(node: &'a NodeRef) -> &'a HgPath {
                     match node {
                         NodeRef::InMemory(path, _node) => path.base_name(),
                         NodeRef::OnDisk(_) => unreachable!(),
                     }
                 }
                 // `sort_unstable_by_key` doesn’t allow keys borrowing from the
                 // value: https://github.com/rust-lang/rust/issues/34162
                 vec.sort_unstable_by(|a, b| sort_key(a).cmp(sort_key(b)));
                 vec
             }
             ChildNodesRef::OnDisk(nodes) => {
                 // Nodes on disk are already sorted
                 nodes.iter().map(NodeRef::OnDisk).collect()
             }
         }
     }
 }
 
 impl<'tree, 'on_disk> NodeRef<'tree, 'on_disk> {
     pub(super) fn full_path(
         &self,
         on_disk: &'on_disk [u8],
     ) -> Result<&'tree HgPath, DirstateV2ParseError> {
         match self {
             NodeRef::InMemory(path, _node) => Ok(path.full_path()),
             NodeRef::OnDisk(node) => node.full_path(on_disk),
         }
     }
 
     /// Returns a `BorrowedPath`, which can be turned into a `Cow<'on_disk,
     /// HgPath>` detached from `'tree`
     pub(super) fn full_path_borrowed(
         &self,
         on_disk: &'on_disk [u8],
     ) -> Result<BorrowedPath<'tree, 'on_disk>, DirstateV2ParseError> {
         match self {
             NodeRef::InMemory(path, _node) => match path.full_path() {
                 Cow::Borrowed(on_disk) => Ok(BorrowedPath::OnDisk(on_disk)),
                 Cow::Owned(in_memory) => Ok(BorrowedPath::InMemory(in_memory)),
             },
             NodeRef::OnDisk(node) => {
                 Ok(BorrowedPath::OnDisk(node.full_path(on_disk)?))
             }
         }
     }
 
     pub(super) fn base_name(
         &self,
         on_disk: &'on_disk [u8],
     ) -> Result<&'tree HgPath, DirstateV2ParseError> {
         match self {
             NodeRef::InMemory(path, _node) => Ok(path.base_name()),
             NodeRef::OnDisk(node) => node.base_name(on_disk),
         }
     }
 
     pub(super) fn children(
         &self,
         on_disk: &'on_disk [u8],
     ) -> Result<ChildNodesRef<'tree, 'on_disk>, DirstateV2ParseError> {
         match self {
             NodeRef::InMemory(_path, node) => Ok(node.children.as_ref()),
             NodeRef::OnDisk(node) => {
                 Ok(ChildNodesRef::OnDisk(node.children(on_disk)?))
             }
         }
     }
 
     pub(super) fn has_copy_source(&self) -> bool {
         match self {
             NodeRef::InMemory(_path, node) => node.copy_source.is_some(),
             NodeRef::OnDisk(node) => node.has_copy_source(),
         }
     }
 
     pub(super) fn copy_source(
         &self,
         on_disk: &'on_disk [u8],
     ) -> Result<Option<&'tree HgPath>, DirstateV2ParseError> {
         match self {
             NodeRef::InMemory(_path, node) => {
                 Ok(node.copy_source.as_ref().map(|s| &**s))
             }
             NodeRef::OnDisk(node) => node.copy_source(on_disk),
         }
     }
     /// Returns a `BorrowedPath`, which can be turned into a `Cow<'on_disk,
     /// HgPath>` detached from `'tree`
     pub(super) fn copy_source_borrowed(
         &self,
         on_disk: &'on_disk [u8],
     ) -> Result<Option<BorrowedPath<'tree, 'on_disk>>, DirstateV2ParseError>
     {
         Ok(match self {
             NodeRef::InMemory(_path, node) => {
                 node.copy_source.as_ref().map(|source| match source {
                     Cow::Borrowed(on_disk) => BorrowedPath::OnDisk(on_disk),
                     Cow::Owned(in_memory) => BorrowedPath::InMemory(in_memory),
                 })
             }
             NodeRef::OnDisk(node) => node
                 .copy_source(on_disk)?
                 .map(|source| BorrowedPath::OnDisk(source)),
         })
     }
 
     pub(super) fn entry(
         &self,
     ) -> Result<Option<DirstateEntry>, DirstateV2ParseError> {
         match self {
             NodeRef::InMemory(_path, node) => {
                 Ok(node.data.as_entry().copied())
             }
             NodeRef::OnDisk(node) => node.entry(),
         }
     }
 
     pub(super) fn state(
         &self,
     ) -> Result<Option<EntryState>, DirstateV2ParseError> {
         Ok(self.entry()?.map(|e| e.state()))
     }
 
     pub(super) fn cached_directory_mtime(
         &self,
     ) -> Result<Option<TruncatedTimestamp>, DirstateV2ParseError> {
         match self {
             NodeRef::InMemory(_path, node) => Ok(match node.data {
                 NodeData::CachedDirectory { mtime } => Some(mtime),
                 _ => None,
             }),
             NodeRef::OnDisk(node) => node.cached_directory_mtime(),
         }
     }
 
     pub(super) fn descendants_with_entry_count(&self) -> u32 {
         match self {
             NodeRef::InMemory(_path, node) => {
                 node.descendants_with_entry_count
             }
             NodeRef::OnDisk(node) => node.descendants_with_entry_count.get(),
         }
     }
 
     pub(super) fn tracked_descendants_count(&self) -> u32 {
         match self {
             NodeRef::InMemory(_path, node) => node.tracked_descendants_count,
             NodeRef::OnDisk(node) => node.tracked_descendants_count.get(),
         }
     }
 }
 
 /// Represents a file or a directory
 #[derive(Default)]
 pub(super) struct Node<'on_disk> {
     pub(super) data: NodeData,
 
     pub(super) copy_source: Option<Cow<'on_disk, HgPath>>,
 
     pub(super) children: ChildNodes<'on_disk>,
 
     /// How many (non-inclusive) descendants of this node have an entry.
     pub(super) descendants_with_entry_count: u32,
 
     /// How many (non-inclusive) descendants of this node have an entry whose
     /// state is "tracked".
     pub(super) tracked_descendants_count: u32,
 }
 
 pub(super) enum NodeData {
     Entry(DirstateEntry),
     CachedDirectory { mtime: TruncatedTimestamp },
     None,
 }
 
 impl Default for NodeData {
     fn default() -> Self {
         NodeData::None
     }
 }
 
 impl NodeData {
     fn has_entry(&self) -> bool {
         match self {
             NodeData::Entry(_) => true,
             _ => false,
         }
     }
 
     fn as_entry(&self) -> Option<&DirstateEntry> {
         match self {
             NodeData::Entry(entry) => Some(entry),
             _ => None,
         }
     }
 }
 
 impl<'on_disk> DirstateMap<'on_disk> {
     pub(super) fn empty(on_disk: &'on_disk [u8]) -> Self {
         Self {
             on_disk,
             root: ChildNodes::default(),
             nodes_with_entry_count: 0,
             nodes_with_copy_source_count: 0,
             ignore_patterns_hash: [0; on_disk::IGNORE_PATTERNS_HASH_LEN],
             unreachable_bytes: 0,
         }
     }
 
     #[timed]
     pub fn new_v2(
         on_disk: &'on_disk [u8],
         data_size: usize,
         metadata: &[u8],
     ) -> Result<Self, DirstateError> {
         if let Some(data) = on_disk.get(..data_size) {
             Ok(on_disk::read(data, metadata)?)
         } else {
             Err(DirstateV2ParseError.into())
         }
     }
 
     #[timed]
     pub fn new_v1(
         on_disk: &'on_disk [u8],
     ) -> Result<(Self, Option<DirstateParents>), DirstateError> {
         let mut map = Self::empty(on_disk);
         if map.on_disk.is_empty() {
             return Ok((map, None));
         }
 
         let parents = parse_dirstate_entries(
             map.on_disk,
             |path, entry, copy_source| {
                 let tracked = entry.state().is_tracked();
                 let node = Self::get_or_insert_node(
                     map.on_disk,
                     &mut map.unreachable_bytes,
                     &mut map.root,
                     path,
                     WithBasename::to_cow_borrowed,
                     |ancestor| {
                         if tracked {
                             ancestor.tracked_descendants_count += 1
                         }
                         ancestor.descendants_with_entry_count += 1
                     },
                 )?;
                 assert!(
                     !node.data.has_entry(),
                     "duplicate dirstate entry in read"
                 );
                 assert!(
                     node.copy_source.is_none(),
                     "duplicate dirstate entry in read"
                 );
                 node.data = NodeData::Entry(*entry);
                 node.copy_source = copy_source.map(Cow::Borrowed);
                 map.nodes_with_entry_count += 1;
                 if copy_source.is_some() {
                     map.nodes_with_copy_source_count += 1
                 }
                 Ok(())
             },
         )?;
         let parents = Some(parents.clone());
 
         Ok((map, parents))
     }
 
     /// Assuming dirstate-v2 format, returns whether the next write should
     /// append to the existing data file that contains `self.on_disk` (true),
     /// or create a new data file from scratch (false).
     pub(super) fn write_should_append(&self) -> bool {
         let ratio = self.unreachable_bytes as f32 / self.on_disk.len() as f32;
         ratio < ACCEPTABLE_UNREACHABLE_BYTES_RATIO
     }
 
     fn get_node<'tree>(
         &'tree self,
         path: &HgPath,
     ) -> Result<Option<NodeRef<'tree, 'on_disk>>, DirstateV2ParseError> {
         let mut children = self.root.as_ref();
         let mut components = path.components();
         let mut component =
             components.next().expect("expected at least one components");
         loop {
             if let Some(child) = children.get(component, self.on_disk)? {
                 if let Some(next_component) = components.next() {
                     component = next_component;
                     children = child.children(self.on_disk)?;
                 } else {
                     return Ok(Some(child));
                 }
             } else {
                 return Ok(None);
             }
         }
     }
 
     /// Returns a mutable reference to the node at `path` if it exists
     ///
     /// This takes `root` instead of `&mut self` so that callers can mutate
     /// other fields while the returned borrow is still valid
     fn get_node_mut<'tree>(
         on_disk: &'on_disk [u8],
         unreachable_bytes: &mut u32,
         root: &'tree mut ChildNodes<'on_disk>,
         path: &HgPath,
     ) -> Result<Option<&'tree mut Node<'on_disk>>, DirstateV2ParseError> {
         let mut children = root;
         let mut components = path.components();
         let mut component =
             components.next().expect("expected at least one components");
         loop {
             if let Some(child) = children
                 .make_mut(on_disk, unreachable_bytes)?
                 .get_mut(component)
             {
                 if let Some(next_component) = components.next() {
                     component = next_component;
                     children = &mut child.children;
                 } else {
                     return Ok(Some(child));
                 }
             } else {
                 return Ok(None);
             }
         }
     }
 
     pub(super) fn get_or_insert<'tree, 'path>(
         &'tree mut self,
         path: &HgPath,
     ) -> Result<&'tree mut Node<'on_disk>, DirstateV2ParseError> {
         Self::get_or_insert_node(
             self.on_disk,
             &mut self.unreachable_bytes,
             &mut self.root,
             path,
             WithBasename::to_cow_owned,
             |_| {},
         )
     }
 
     fn get_or_insert_node<'tree, 'path>(
         on_disk: &'on_disk [u8],
         unreachable_bytes: &mut u32,
         root: &'tree mut ChildNodes<'on_disk>,
         path: &'path HgPath,
         to_cow: impl Fn(
             WithBasename<&'path HgPath>,
         ) -> WithBasename<Cow<'on_disk, HgPath>>,
         mut each_ancestor: impl FnMut(&mut Node),
     ) -> Result<&'tree mut Node<'on_disk>, DirstateV2ParseError> {
         let mut child_nodes = root;
         let mut inclusive_ancestor_paths =
             WithBasename::inclusive_ancestors_of(path);
         let mut ancestor_path = inclusive_ancestor_paths
             .next()
             .expect("expected at least one inclusive ancestor");
         loop {
-            // TODO: can we avoid allocating an owned key in cases where the
-            // map already contains that key, without introducing double
-            // lookup?
-            let child_node = child_nodes
+            let (_, child_node) = child_nodes
                 .make_mut(on_disk, unreachable_bytes)?
-                .entry(to_cow(ancestor_path))
-                .or_default();
+                .raw_entry_mut()
+                .from_key(ancestor_path.base_name())
+                .or_insert_with(|| (to_cow(ancestor_path), Node::default()));
             if let Some(next) = inclusive_ancestor_paths.next() {
                 each_ancestor(child_node);
                 ancestor_path = next;
                 child_nodes = &mut child_node.children;
             } else {
                 return Ok(child_node);
             }
         }
     }
 
     fn add_or_remove_file(
         &mut self,
         path: &HgPath,
         old_state: Option<EntryState>,
         new_entry: DirstateEntry,
     ) -> Result<(), DirstateV2ParseError> {
         let had_entry = old_state.is_some();
         let was_tracked = old_state.map_or(false, |s| s.is_tracked());
         let tracked_count_increment =
             match (was_tracked, new_entry.state().is_tracked()) {
                 (false, true) => 1,
                 (true, false) => -1,
                 _ => 0,
             };
 
         let node = Self::get_or_insert_node(
             self.on_disk,
             &mut self.unreachable_bytes,
             &mut self.root,
             path,
             WithBasename::to_cow_owned,
             |ancestor| {
                 if !had_entry {
                     ancestor.descendants_with_entry_count += 1;
                 }
 
                 // We can’t use `+= increment` because the counter is unsigned,
                 // and we want debug builds to detect accidental underflow
                 // through zero
                 match tracked_count_increment {
                     1 => ancestor.tracked_descendants_count += 1,
                     -1 => ancestor.tracked_descendants_count -= 1,
                     _ => {}
                 }
             },
         )?;
         if !had_entry {
             self.nodes_with_entry_count += 1
         }
         node.data = NodeData::Entry(new_entry);
         Ok(())
     }
 
     fn iter_nodes<'tree>(
         &'tree self,
     ) -> impl Iterator<
         Item = Result<NodeRef<'tree, 'on_disk>, DirstateV2ParseError>,
     > + 'tree {
         // Depth first tree traversal.
         //
         // If we could afford internal iteration and recursion,
         // this would look like:
         //
         // ```
         // fn traverse_children(
         //     children: &ChildNodes,
         //     each: &mut impl FnMut(&Node),
         // ) {
         //     for child in children.values() {
         //         traverse_children(&child.children, each);
         //         each(child);
         //     }
         // }
         // ```
         //
         // However we want an external iterator and therefore can’t use the
         // call stack. Use an explicit stack instead:
         let mut stack = Vec::new();
         let mut iter = self.root.as_ref().iter();
         std::iter::from_fn(move || {
             while let Some(child_node) = iter.next() {
                 let children = match child_node.children(self.on_disk) {
                     Ok(children) => children,
                     Err(error) => return Some(Err(error)),
                 };
                 // Pseudo-recursion
                 let new_iter = children.iter();
                 let old_iter = std::mem::replace(&mut iter, new_iter);
                 stack.push((child_node, old_iter));
             }
             // Found the end of a `children.iter()` iterator.
             if let Some((child_node, next_iter)) = stack.pop() {
                 // "Return" from pseudo-recursion by restoring state from the
                 // explicit stack
                 iter = next_iter;
 
                 Some(Ok(child_node))
             } else {
                 // Reached the bottom of the stack, we’re done
                 None
             }
         })
     }
 
     fn count_dropped_path(unreachable_bytes: &mut u32, path: &Cow<HgPath>) {
         if let Cow::Borrowed(path) = path {
             *unreachable_bytes += path.len() as u32
         }
     }
 }
 
 /// Like `Iterator::filter_map`, but over a fallible iterator of `Result`s.
 ///
 /// The callback is only called for incoming `Ok` values. Errors are passed
 /// through as-is. In order to let it use the `?` operator the callback is
 /// expected to return a `Result` of `Option`, instead of an `Option` of
 /// `Result`.
 fn filter_map_results<'a, I, F, A, B, E>(
     iter: I,
     f: F,
 ) -> impl Iterator<Item = Result<B, E>> + 'a
 where
     I: Iterator<Item = Result<A, E>> + 'a,
     F: Fn(A) -> Result<Option<B>, E> + 'a,
 {
     iter.filter_map(move |result| match result {
         Ok(node) => f(node).transpose(),
         Err(e) => Some(Err(e)),
     })
 }
 
 impl OwningDirstateMap {
     pub fn clear(&mut self) {
         let map = self.get_map_mut();
         map.root = Default::default();
         map.nodes_with_entry_count = 0;
         map.nodes_with_copy_source_count = 0;
     }
 
     pub fn set_entry(
         &mut self,
         filename: &HgPath,
         entry: DirstateEntry,
     ) -> Result<(), DirstateV2ParseError> {
         let map = self.get_map_mut();
         map.get_or_insert(&filename)?.data = NodeData::Entry(entry);
         Ok(())
     }
 
     pub fn add_file(
         &mut self,
         filename: &HgPath,
         entry: DirstateEntry,
     ) -> Result<(), DirstateError> {
         let old_state = self.get(filename)?.map(|e| e.state());
         let map = self.get_map_mut();
         Ok(map.add_or_remove_file(filename, old_state, entry)?)
     }
 
     pub fn remove_file(
         &mut self,
         filename: &HgPath,
         in_merge: bool,
     ) -> Result<(), DirstateError> {
         let old_entry_opt = self.get(filename)?;
         let old_state = old_entry_opt.map(|e| e.state());
         let mut size = 0;
         if in_merge {
             // XXX we should not be able to have 'm' state and 'FROM_P2' if not
             // during a merge. So I (marmoute) am not sure we need the
             // conditionnal at all. Adding double checking this with assert
             // would be nice.
             if let Some(old_entry) = old_entry_opt {
                 // backup the previous state
                 if old_entry.state() == EntryState::Merged {
                     size = SIZE_NON_NORMAL;
                 } else if old_entry.state() == EntryState::Normal
                     && old_entry.size() == SIZE_FROM_OTHER_PARENT
                 {
                     // other parent
                     size = SIZE_FROM_OTHER_PARENT;
                 }
             }
         }
         if size == 0 {
             self.copy_map_remove(filename)?;
         }
         let map = self.get_map_mut();
         let entry = DirstateEntry::new_removed(size);
         Ok(map.add_or_remove_file(filename, old_state, entry)?)
     }
 
     pub fn drop_entry_and_copy_source(
         &mut self,
         filename: &HgPath,
     ) -> Result<(), DirstateError> {
         let was_tracked = self
             .get(filename)?
             .map_or(false, |e| e.state().is_tracked());
         let map = self.get_map_mut();
         struct Dropped {
             was_tracked: bool,
             had_entry: bool,
             had_copy_source: bool,
         }
 
         /// If this returns `Ok(Some((dropped, removed)))`, then
         ///
         /// * `dropped` is about the leaf node that was at `filename`
         /// * `removed` is whether this particular level of recursion just
         ///   removed a node in `nodes`.
         fn recur<'on_disk>(
             on_disk: &'on_disk [u8],
             unreachable_bytes: &mut u32,
             nodes: &mut ChildNodes<'on_disk>,
             path: &HgPath,
         ) -> Result<Option<(Dropped, bool)>, DirstateV2ParseError> {
             let (first_path_component, rest_of_path) =
                 path.split_first_component();
             let nodes = nodes.make_mut(on_disk, unreachable_bytes)?;
             let node = if let Some(node) = nodes.get_mut(first_path_component)
             {
                 node
             } else {
                 return Ok(None);
             };
             let dropped;
             if let Some(rest) = rest_of_path {
                 if let Some((d, removed)) = recur(
                     on_disk,
                     unreachable_bytes,
                     &mut node.children,
                     rest,
                 )? {
                     dropped = d;
                     if dropped.had_entry {
                         node.descendants_with_entry_count -= 1;
                     }
                     if dropped.was_tracked {
                         node.tracked_descendants_count -= 1;
                     }
 
                     // Directory caches must be invalidated when removing a
                     // child node
                     if removed {
                         if let NodeData::CachedDirectory { .. } = &node.data {
                             node.data = NodeData::None
                         }
                     }
                 } else {
                     return Ok(None);
                 }
             } else {
                 let had_entry = node.data.has_entry();
                 if had_entry {
                     node.data = NodeData::None
                 }
                 if let Some(source) = &node.copy_source {
                     DirstateMap::count_dropped_path(unreachable_bytes, source);
                     node.copy_source = None
                 }
                 dropped = Dropped {
                     was_tracked: node
                         .data
                         .as_entry()
                         .map_or(false, |entry| entry.state().is_tracked()),
                     had_entry,
                     had_copy_source: node.copy_source.take().is_some(),
                 };
             }
             // After recursion, for both leaf (rest_of_path is None) nodes and
             // parent nodes, remove a node if it just became empty.
             let remove = !node.data.has_entry()
                 && node.copy_source.is_none()
                 && node.children.is_empty();
             if remove {
                 let (key, _) =
                     nodes.remove_entry(first_path_component).unwrap();
                 DirstateMap::count_dropped_path(
                     unreachable_bytes,
                     key.full_path(),
                 )
             }
             Ok(Some((dropped, remove)))
         }
 
         if let Some((dropped, _removed)) = recur(
             map.on_disk,
             &mut map.unreachable_bytes,
             &mut map.root,
             filename,
         )? {
             if dropped.had_entry {
                 map.nodes_with_entry_count -= 1
             }
             if dropped.had_copy_source {
                 map.nodes_with_copy_source_count -= 1
             }
         } else {
             debug_assert!(!was_tracked);
         }
         Ok(())
     }
 
     pub fn has_tracked_dir(
         &mut self,
         directory: &HgPath,
     ) -> Result<bool, DirstateError> {
         let map = self.get_map_mut();
         if let Some(node) = map.get_node(directory)? {
             // A node without a `DirstateEntry` was created to hold child
             // nodes, and is therefore a directory.
             let state = node.state()?;
             Ok(state.is_none() && node.tracked_descendants_count() > 0)
         } else {
             Ok(false)
         }
     }
 
     pub fn has_dir(
         &mut self,
         directory: &HgPath,
     ) -> Result<bool, DirstateError> {
         let map = self.get_map_mut();
         if let Some(node) = map.get_node(directory)? {
             // A node without a `DirstateEntry` was created to hold child
             // nodes, and is therefore a directory.
             let state = node.state()?;
             Ok(state.is_none() && node.descendants_with_entry_count() > 0)
         } else {
             Ok(false)
         }
     }
 
     #[timed]
     pub fn pack_v1(
         &self,
         parents: DirstateParents,
     ) -> Result<Vec<u8>, DirstateError> {
         let map = self.get_map();
         // Optizimation (to be measured?): pre-compute size to avoid `Vec`
         // reallocations
         let mut size = parents.as_bytes().len();
         for node in map.iter_nodes() {
             let node = node?;
             if node.entry()?.is_some() {
                 size += packed_entry_size(
                     node.full_path(map.on_disk)?,
                     node.copy_source(map.on_disk)?,
                 );
             }
         }
 
         let mut packed = Vec::with_capacity(size);
         packed.extend(parents.as_bytes());
 
         for node in map.iter_nodes() {
             let node = node?;
             if let Some(entry) = node.entry()? {
                 pack_entry(
                     node.full_path(map.on_disk)?,
                     &entry,
                     node.copy_source(map.on_disk)?,
                     &mut packed,
                 );
             }
         }
         Ok(packed)
     }
 
     /// Returns new data and metadata together with whether that data should be
     /// appended to the existing data file whose content is at
     /// `map.on_disk` (true), instead of written to a new data file
     /// (false).
     #[timed]
     pub fn pack_v2(
         &self,
         can_append: bool,
     ) -> Result<(Vec<u8>, on_disk::TreeMetadata, bool), DirstateError> {
         let map = self.get_map();
         on_disk::write(map, can_append)
     }
 
     pub fn status<'a>(
         &'a mut self,
         matcher: &'a (dyn Matcher + Sync),
         root_dir: PathBuf,
         ignore_files: Vec<PathBuf>,
         options: StatusOptions,
     ) -> Result<(DirstateStatus<'a>, Vec<PatternFileWarning>), StatusError>
     {
         let map = self.get_map_mut();
         super::status::status(map, matcher, root_dir, ignore_files, options)
     }
 
     pub fn copy_map_len(&self) -> usize {
         let map = self.get_map();
         map.nodes_with_copy_source_count as usize
     }
 
     pub fn copy_map_iter(&self) -> CopyMapIter<'_> {
         let map = self.get_map();
         Box::new(filter_map_results(map.iter_nodes(), move |node| {
             Ok(if let Some(source) = node.copy_source(map.on_disk)? {
                 Some((node.full_path(map.on_disk)?, source))
             } else {
                 None
             })
         }))
     }
 
     pub fn copy_map_contains_key(
         &self,
         key: &HgPath,
     ) -> Result<bool, DirstateV2ParseError> {
         let map = self.get_map();
         Ok(if let Some(node) = map.get_node(key)? {
             node.has_copy_source()
         } else {
             false
         })
     }
 
     pub fn copy_map_get(
         &self,
         key: &HgPath,
     ) -> Result<Option<&HgPath>, DirstateV2ParseError> {
         let map = self.get_map();
         if let Some(node) = map.get_node(key)? {
             if let Some(source) = node.copy_source(map.on_disk)? {
                 return Ok(Some(source));
             }
         }
         Ok(None)
     }
 
     pub fn copy_map_remove(
         &mut self,
         key: &HgPath,
     ) -> Result<Option<HgPathBuf>, DirstateV2ParseError> {
         let map = self.get_map_mut();
         let count = &mut map.nodes_with_copy_source_count;
         let unreachable_bytes = &mut map.unreachable_bytes;
         Ok(DirstateMap::get_node_mut(
             map.on_disk,
             unreachable_bytes,
             &mut map.root,
             key,
         )?
         .and_then(|node| {
             if let Some(source) = &node.copy_source {
                 *count -= 1;
                 DirstateMap::count_dropped_path(unreachable_bytes, source);
             }
             node.copy_source.take().map(Cow::into_owned)
         }))
     }
 
     pub fn copy_map_insert(
         &mut self,
         key: HgPathBuf,
         value: HgPathBuf,
     ) -> Result<Option<HgPathBuf>, DirstateV2ParseError> {
         let map = self.get_map_mut();
         let node = DirstateMap::get_or_insert_node(
             map.on_disk,
             &mut map.unreachable_bytes,
             &mut map.root,
             &key,
             WithBasename::to_cow_owned,
             |_ancestor| {},
         )?;
         if node.copy_source.is_none() {
             map.nodes_with_copy_source_count += 1
         }
         Ok(node.copy_source.replace(value.into()).map(Cow::into_owned))
     }
 
     pub fn len(&self) -> usize {
         let map = self.get_map();
         map.nodes_with_entry_count as usize
     }
 
     pub fn contains_key(
         &self,
         key: &HgPath,
     ) -> Result<bool, DirstateV2ParseError> {
         Ok(self.get(key)?.is_some())
     }
 
     pub fn get(
         &self,
         key: &HgPath,
     ) -> Result<Option<DirstateEntry>, DirstateV2ParseError> {
         let map = self.get_map();
         Ok(if let Some(node) = map.get_node(key)? {
             node.entry()?
         } else {
             None
         })
     }
 
     pub fn iter(&self) -> StateMapIter<'_> {
         let map = self.get_map();
         Box::new(filter_map_results(map.iter_nodes(), move |node| {
             Ok(if let Some(entry) = node.entry()? {
                 Some((node.full_path(map.on_disk)?, entry))
             } else {
                 None
             })
         }))
     }
 
     pub fn iter_tracked_dirs(
         &mut self,
     ) -> Result<
         Box<
             dyn Iterator<Item = Result<&HgPath, DirstateV2ParseError>>
                 + Send
                 + '_,
         >,
         DirstateError,
     > {
         let map = self.get_map_mut();
         let on_disk = map.on_disk;
         Ok(Box::new(filter_map_results(
             map.iter_nodes(),
             move |node| {
                 Ok(if node.tracked_descendants_count() > 0 {
                     Some(node.full_path(on_disk)?)
                 } else {
                     None
                 })
             },
         )))
     }
 
     pub fn debug_iter(
         &self,
         all: bool,
     ) -> Box<
         dyn Iterator<
                 Item = Result<
                     (&HgPath, (u8, i32, i32, i32)),
                     DirstateV2ParseError,
                 >,
             > + Send
             + '_,
     > {
         let map = self.get_map();
         Box::new(filter_map_results(map.iter_nodes(), move |node| {
             let debug_tuple = if let Some(entry) = node.entry()? {
                 entry.debug_tuple()
             } else if !all {
                 return Ok(None);
             } else if let Some(mtime) = node.cached_directory_mtime()? {
                 (b' ', 0, -1, mtime.truncated_seconds() as i32)
             } else {
                 (b' ', 0, -1, -1)
             };
             Ok(Some((node.full_path(map.on_disk)?, debug_tuple)))
         }))
     }
 }

rust/hg-core/src/lib.rs

@@ -1,132 +1,137 b''
 // Copyright 2018-2020 Georges Racinet <[e-mail]>
 //           and Mercurial contributors
 //
 // This software may be used and distributed according to the terms of the
 // GNU General Public License version 2 or any later version.
 
 mod ancestors;
 pub mod dagops;
 pub mod errors;
 pub use ancestors::{AncestorsIterator, MissingAncestors};
 pub mod dirstate;
 pub mod dirstate_tree;
 pub mod discovery;
 pub mod exit_codes;
 pub mod requirements;
 pub mod testing; // unconditionally built, for use from integration tests
 pub use dirstate::{
     dirs_multiset::{DirsMultiset, DirsMultisetIter},
     status::{
         BadMatch, BadType, DirstateStatus, HgPathCow, StatusError,
         StatusOptions,
     },
     DirstateEntry, DirstateParents, EntryState,
 };
 pub mod copy_tracing;
 mod filepatterns;
 pub mod matchers;
 pub mod repo;
 pub mod revlog;
 pub use revlog::*;
 pub mod config;
 pub mod lock;
 pub mod logging;
 pub mod operations;
 pub mod revset;
 pub mod utils;
 pub mod vfs;
 
 use crate::utils::hg_path::{HgPathBuf, HgPathError};
 pub use filepatterns::{
     parse_pattern_syntax, read_pattern_file, IgnorePattern,
     PatternFileWarning, PatternSyntax,
 };
 use std::collections::HashMap;
 use std::fmt;
 use twox_hash::RandomXxHashBuilder64;
 
 /// This is a contract between the `micro-timer` crate and us, to expose
 /// the `log` crate as `crate::log`.
 use log;
 
 pub type LineNumber = usize;
 
 /// Rust's default hasher is too slow because it tries to prevent collision
 /// attacks. We are not concerned about those: if an ill-minded person has
 /// write access to your repository, you have other issues.
 pub type FastHashMap<K, V> = HashMap<K, V, RandomXxHashBuilder64>;
 
+// TODO: should this be the default `FastHashMap` for all of hg-core, not just
+// dirstate_tree? How does XxHash compare with AHash, hashbrown’s default?
+pub type FastHashbrownMap<K, V> =
+    hashbrown::HashMap<K, V, RandomXxHashBuilder64>;
+
 #[derive(Debug, PartialEq)]
 pub enum DirstateMapError {
     PathNotFound(HgPathBuf),
     EmptyPath,
     InvalidPath(HgPathError),
 }
 
 impl fmt::Display for DirstateMapError {
     fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
         match self {
             DirstateMapError::PathNotFound(_) => {
                 f.write_str("expected a value, found none")
             }
             DirstateMapError::EmptyPath => {
                 f.write_str("Overflow in dirstate.")
             }
             DirstateMapError::InvalidPath(path_error) => path_error.fmt(f),
         }
     }
 }
 
 #[derive(Debug, derive_more::From)]
 pub enum DirstateError {
     Map(DirstateMapError),
     Common(errors::HgError),
 }
 
 impl fmt::Display for DirstateError {
     fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
         match self {
             DirstateError::Map(error) => error.fmt(f),
             DirstateError::Common(error) => error.fmt(f),
         }
     }
 }
 
 #[derive(Debug, derive_more::From)]
 pub enum PatternError {
     #[from]
     Path(HgPathError),
     UnsupportedSyntax(String),
     UnsupportedSyntaxInFile(String, String, usize),
     TooLong(usize),
     #[from]
     IO(std::io::Error),
     /// Needed a pattern that can be turned into a regex but got one that
     /// can't. This should only happen through programmer error.
     NonRegexPattern(IgnorePattern),
 }
 
 impl fmt::Display for PatternError {
     fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
         match self {
             PatternError::UnsupportedSyntax(syntax) => {
                 write!(f, "Unsupported syntax {}", syntax)
             }
             PatternError::UnsupportedSyntaxInFile(syntax, file_path, line) => {
                 write!(
                     f,
                     "{}:{}: unsupported syntax {}",
                     file_path, line, syntax
                 )
             }
             PatternError::TooLong(size) => {
                 write!(f, "matcher pattern is too long ({} bytes)", size)
             }
             PatternError::IO(error) => error.fmt(f),
             PatternError::Path(error) => error.fmt(f),
             PatternError::NonRegexPattern(pattern) => {
                 write!(f, "'{:?}' cannot be turned into a regex", pattern)
             }
         }
     }
 }