dirstate-tree: Add the new `status()` algorithm

With the dirstate organized in a tree that mirrors the structure of the
filesystem tree, we can traverse both trees at the same time in order to
compare them. This is hopefully more efficient that building multiple
big hashmaps for all of the repository’s contents.

Differential Revision: https://phab.mercurial-scm.org/D10547

rust/Cargo.lock

@@ -1,1104 +1,1105 b''
 # This file is automatically @generated by Cargo.
 # It is not intended for manual editing.
 [[package]]
 name = "adler"
 version = "0.2.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "ee2a4ec343196209d6594e19543ae87a39f96d5534d7174822a3ad825dd6ed7e"
 
 [[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 = "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 = "cpython"
 version = "0.5.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "0f11357af68648b6a227e7e2384d439cec8595de65970f45e3f7f4b2600be472"
 dependencies = [
  "libc",
  "num-traits",
  "paste",
  "python27-sys",
  "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 = "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 = "0.2.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "1c4e89040c7fd7b4e6ba2820ac705a45def8a0c098ec78d170ae88f1ef1d5762"
 dependencies = [
  "format-bytes-macros",
  "proc-macro-hack",
 ]
 
 [[package]]
 name = "format-bytes-macros"
 version = "0.3.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "b05089e341a0460449e2210c3bf7b61597860b07f0deae58da38dbed0a4c6b6d"
 dependencies = [
  "proc-macro-hack",
  "proc-macro2",
  "quote",
  "syn",
 ]
 
 [[package]]
 name = "fuchsia-cprng"
 version = "0.1.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "a06f77d526c1a601b7c4cdd98f54b5eaabffc14d5f2f0296febdc7f357c6d3ba"
 
 [[package]]
 name = "gcc"
 version = "0.3.55"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "8f5f3913fa0bfe7ee1fd8248b6b9f42a5af4b9d65ec2dd2c3c26132b950ecfc2"
 
 [[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 = "glob"
 version = "0.3.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "9b919933a397b79c37e33b77bb2aa3dc8eb6e165ad809e58ff75bc7db2e34574"
 
 [[package]]
 name = "hermit-abi"
 version = "0.1.17"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "5aca5565f760fb5b220e499d72710ed156fdb74e631659e99377d9ebfbd13ae8"
 dependencies = [
  "libc",
 ]
 
 [[package]]
 name = "hg-core"
 version = "0.1.0"
 dependencies = [
  "byteorder",
  "bytes-cast",
  "clap",
  "crossbeam-channel 0.4.4",
  "derive_more",
  "flate2",
  "format-bytes",
  "home",
  "im-rc",
+ "itertools",
  "lazy_static",
  "log",
  "memmap",
  "micro-timer",
  "pretty_assertions",
  "rand 0.7.3",
  "rand_distr",
  "rand_pcg",
  "rayon",
  "regex",
  "rust-crypto",
  "same-file",
  "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",
 ]
 
 [[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 = "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 = "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 = "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",
 ]
 
 [[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 = "output_vt100"
 version = "0.1.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "53cdc5b785b7a58c5aad8216b3dfa114df64b0b06ae6e1501cef91df2fbdf8f9"
 dependencies = [
  "winapi",
 ]
 
 [[package]]
 name = "paste"
 version = "0.1.18"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "45ca20c77d80be666aef2b45486da86238fabe33e38306bd3118fe4af33fa880"
 dependencies = [
  "paste-impl",
  "proc-macro-hack",
 ]
 
 [[package]]
 name = "paste-impl"
 version = "0.1.18"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "d95a7db200b97ef370c8e6de0088252f7e0dfff7d047a28528e47456c0fc98b6"
 dependencies = [
  "proc-macro-hack",
 ]
 
 [[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-macro-hack"
 version = "0.5.19"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "dbf0c48bc1d91375ae5c3cd81e3722dff1abcf81a30960240640d223f59fe0e5"
 
 [[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 = "python27-sys"
 version = "0.5.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "f485897ed7048f5032317c4e427800ef9f2053355516524d73952b8b07032054"
 dependencies = [
  "libc",
  "regex",
 ]
 
 [[package]]
 name = "python3-sys"
 version = "0.5.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "5b29b99c6868eb02beb3bf6ed025c8bcdf02efc149b8e80347d3e5d059a806db"
 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 = "0.3.23"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "64ac302d8f83c0c1974bf758f6b041c6c8ada916fbb44a609158ca8b064cc76c"
 dependencies = [
  "libc",
  "rand 0.4.6",
 ]
 
 [[package]]
 name = "rand"
 version = "0.4.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "552840b97013b1a26992c11eac34bdd778e464601a4c2054b5f0bff7c6761293"
 dependencies = [
  "fuchsia-cprng",
  "libc",
  "rand_core 0.3.1",
  "rdrand",
  "winapi",
 ]
 
 [[package]]
 name = "rand"
 version = "0.7.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "6a6b1679d49b24bbfe0c803429aa1874472f50d9b363131f0e89fc356b544d03"
 dependencies = [
  "getrandom",
  "libc",
  "rand_chacha",
  "rand_core 0.5.1",
  "rand_hc",
 ]
 
 [[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_core"
 version = "0.3.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "7a6fdeb83b075e8266dcc8762c22776f6877a63111121f5f8c7411e5be7eed4b"
 dependencies = [
  "rand_core 0.4.2",
 ]
 
 [[package]]
 name = "rand_core"
 version = "0.4.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "9c33a3c44ca05fa6f1807d8e6743f3824e8509beca625669633be0acbdf509dc"
 
 [[package]]
 name = "rand_core"
 version = "0.5.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "90bde5296fc891b0cef12a6d03ddccc162ce7b2aff54160af9338f8d40df6d19"
 dependencies = [
  "getrandom",
 ]
 
 [[package]]
 name = "rand_distr"
 version = "0.2.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "96977acbdd3a6576fb1d27391900035bf3863d4a16422973a409b488cf29ffb2"
 dependencies = [
  "rand 0.7.3",
 ]
 
 [[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_pcg"
 version = "0.2.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "16abd0c1b639e9eb4d7c50c0b8100b0d0f849be2349829c740fe8e6eb4816429"
 dependencies = [
  "rand_core 0.5.1",
 ]
 
 [[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 = "rdrand"
 version = "0.4.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "678054eb77286b51581ba43620cc911abf02758c91f93f479767aed0f90458b2"
 dependencies = [
  "rand_core 0.3.1",
 ]
 
 [[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 = [
  "chrono",
  "clap",
  "derive_more",
  "env_logger",
  "format-bytes",
  "hg-core",
  "lazy_static",
  "log",
  "micro-timer",
  "regex",
  "users",
 ]
 
 [[package]]
 name = "rust-crypto"
 version = "0.2.36"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "f76d05d3993fd5f4af9434e8e436db163a12a9d40e1a58a726f27a01dfd12a2a"
 dependencies = [
  "gcc",
  "libc",
  "rand 0.3.23",
  "rustc-serialize",
  "time",
 ]
 
 [[package]]
 name = "rustc-serialize"
 version = "0.3.24"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "dcf128d1287d2ea9d80910b5f1120d0b8eede3fbf1abe91c40d39ea7d51e6fda"
 
 [[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 = "sized-chunks"
 version = "0.6.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "1ec31ceca5644fa6d444cc77548b88b67f46db6f7c71683b0f9336e671830d2f"
 dependencies = [
  "bitmaps",
  "typenum",
 ]
 
 [[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 = "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

@@ -1,43 +1,44 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]
 bytes-cast = "0.2"
 byteorder = "1.3.4"
 derive_more = "0.99"
 home = "0.5"
 im-rc = "15.0.*"
+itertools = "0.9"
 lazy_static = "1.4.0"
 rand = "0.7.3"
 rand_pcg = "0.2.1"
 rand_distr = "0.2.2"
 rayon = "1.3.0"
 regex = "1.3.9"
 twox-hash = "1.5.0"
 same-file = "1.0.6"
 crossbeam-channel = "0.4"
 micro-timer = "0.3.0"
 log = "0.4.8"
 memmap = "0.7.0"
 zstd = "0.5.3"
 rust-crypto = "0.2.36"
 format-bytes = "0.2.2"
 
 # 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"
 tempfile = "3.1.0"

rust/hg-core/src/dirstate.rs

@@ -1,119 +1,132 b''
 // dirstate module
 //
 // Copyright 2019 Raphaël Gomès <[e-mail]>
 //
 // This software may be used and distributed according to the terms of the
 // GNU General Public License version 2 or any later version.
 
 use crate::errors::HgError;
 use crate::revlog::Node;
 use crate::{utils::hg_path::HgPathBuf, FastHashMap};
 use bytes_cast::{unaligned, BytesCast};
 use std::convert::TryFrom;
 
 pub mod dirs_multiset;
 pub mod dirstate_map;
 pub mod parsers;
 pub mod status;
 
 #[derive(Debug, PartialEq, Clone, BytesCast)]
 #[repr(C)]
 pub struct DirstateParents {
     pub p1: Node,
     pub p2: Node,
 }
 
 /// The C implementation uses all signed types. This will be an issue
 /// either when 4GB+ source files are commonplace or in 2038, whichever
 /// comes first.
 #[derive(Debug, PartialEq, Copy, Clone)]
 pub struct DirstateEntry {
     pub state: EntryState,
     pub mode: i32,
     pub mtime: i32,
     pub size: i32,
 }
 
 impl DirstateEntry {
     pub fn is_non_normal(&self) -> bool {
         self.state != EntryState::Normal || self.mtime == MTIME_UNSET
     }
 
     pub fn is_from_other_parent(&self) -> bool {
         self.state == EntryState::Normal && self.size == SIZE_FROM_OTHER_PARENT
     }
+
+    // TODO: other platforms
+    #[cfg(unix)]
+    pub fn mode_changed(
+        &self,
+        filesystem_metadata: &std::fs::Metadata,
+    ) -> bool {
+        use std::os::unix::fs::MetadataExt;
+        const EXEC_BIT_MASK: u32 = 0o100;
+        let dirstate_exec_bit = (self.mode as u32) & EXEC_BIT_MASK;
+        let fs_exec_bit = filesystem_metadata.mode() & EXEC_BIT_MASK;
+        dirstate_exec_bit != fs_exec_bit
+    }
 }
 
 #[derive(BytesCast)]
 #[repr(C)]
 struct RawEntry {
     state: u8,
     mode: unaligned::I32Be,
     size: unaligned::I32Be,
     mtime: unaligned::I32Be,
     length: unaligned::I32Be,
 }
 
 const MTIME_UNSET: i32 = -1;
 
 /// A `DirstateEntry` with a size of `-2` means that it was merged from the
 /// other parent. This allows revert to pick the right status back during a
 /// merge.
 pub const SIZE_FROM_OTHER_PARENT: i32 = -2;
 
 pub type StateMap = FastHashMap<HgPathBuf, DirstateEntry>;
 pub type StateMapIter<'a> =
     Box<dyn Iterator<Item = (&'a HgPathBuf, &'a DirstateEntry)> + Send + 'a>;
 
 pub type CopyMap = FastHashMap<HgPathBuf, HgPathBuf>;
 pub type CopyMapIter<'a> =
     Box<dyn Iterator<Item = (&'a HgPathBuf, &'a HgPathBuf)> + Send + 'a>;
 
 #[derive(Copy, Clone, Debug, Eq, PartialEq)]
 pub enum EntryState {
     Normal,
     Added,
     Removed,
     Merged,
     Unknown,
 }
 
 impl EntryState {
     pub fn is_tracked(self) -> bool {
         use EntryState::*;
         match self {
             Normal | Added | Merged => true,
             Removed | Unknown => false,
         }
     }
 }
 
 impl TryFrom<u8> for EntryState {
     type Error = HgError;
 
     fn try_from(value: u8) -> Result<Self, Self::Error> {
         match value {
             b'n' => Ok(EntryState::Normal),
             b'a' => Ok(EntryState::Added),
             b'r' => Ok(EntryState::Removed),
             b'm' => Ok(EntryState::Merged),
             b'?' => Ok(EntryState::Unknown),
             _ => Err(HgError::CorruptedRepository(format!(
                 "Incorrect dirstate entry state {}",
                 value
             ))),
         }
     }
 }
 
 impl Into<u8> for EntryState {
     fn into(self) -> u8 {
         match self {
             EntryState::Normal => b'n',
             EntryState::Added => b'a',
             EntryState::Removed => b'r',
             EntryState::Merged => b'm',
             EntryState::Unknown => b'?',
         }
     }
 }

rust/hg-core/src/dirstate/status.rs

@@ -1,934 +1,934 b''
 // status.rs
 //
 // Copyright 2019 Raphaël Gomès <[e-mail]>
 //
 // This software may be used and distributed according to the terms of the
 // GNU General Public License version 2 or any later version.
 
 //! Rust implementation of dirstate.status (dirstate.py).
 //! It is currently missing a lot of functionality compared to the Python one
 //! and will only be triggered in narrow cases.
 
 use crate::utils::path_auditor::PathAuditor;
 use crate::{
     dirstate::SIZE_FROM_OTHER_PARENT,
     filepatterns::PatternFileWarning,
     matchers::{get_ignore_function, Matcher, VisitChildrenSet},
     utils::{
         files::{find_dirs, HgMetadata},
         hg_path::{
             hg_path_to_path_buf, os_string_to_hg_path_buf, HgPath, HgPathBuf,
             HgPathError,
         },
     },
     CopyMap, DirstateEntry, DirstateMap, EntryState, FastHashMap,
     PatternError,
 };
 use lazy_static::lazy_static;
 use micro_timer::timed;
 use rayon::prelude::*;
 use std::{
     borrow::Cow,
     collections::HashSet,
     fmt,
     fs::{read_dir, DirEntry},
     io::ErrorKind,
     ops::Deref,
     path::{Path, PathBuf},
 };
 
 /// Wrong type of file from a `BadMatch`
 /// Note: a lot of those don't exist on all platforms.
 #[derive(Debug, Copy, Clone)]
 pub enum BadType {
     CharacterDevice,
     BlockDevice,
     FIFO,
     Socket,
     Directory,
     Unknown,
 }
 
 impl fmt::Display for BadType {
     fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
         f.write_str(match self {
             BadType::CharacterDevice => "character device",
             BadType::BlockDevice => "block device",
             BadType::FIFO => "fifo",
             BadType::Socket => "socket",
             BadType::Directory => "directory",
             BadType::Unknown => "unknown",
         })
     }
 }
 
 /// Was explicitly matched but cannot be found/accessed
 #[derive(Debug, Copy, Clone)]
 pub enum BadMatch {
     OsError(i32),
     BadType(BadType),
 }
 
 /// Enum used to dispatch new status entries into the right collections.
 /// Is similar to `crate::EntryState`, but represents the transient state of
 /// entries during the lifetime of a command.
 #[derive(Debug, Copy, Clone)]
 pub enum Dispatch {
     Unsure,
     Modified,
     Added,
     Removed,
     Deleted,
     Clean,
     Unknown,
     Ignored,
     /// Empty dispatch, the file is not worth listing
     None,
     /// Was explicitly matched but cannot be found/accessed
     Bad(BadMatch),
     Directory {
         /// True if the directory used to be a file in the dmap so we can say
         /// that it's been removed.
         was_file: bool,
     },
 }
 
 type IoResult<T> = std::io::Result<T>;
 
-/// `Box<dyn Trait>` is syntactic sugar for `Box<dyn Trait, 'static>`, so add
+/// `Box<dyn Trait>` is syntactic sugar for `Box<dyn Trait + 'static>`, so add
 /// an explicit lifetime here to not fight `'static` bounds "out of nowhere".
 pub type IgnoreFnType<'a> =
     Box<dyn for<'r> Fn(&'r HgPath) -> bool + Sync + 'a>;
 
 /// We have a good mix of owned (from directory traversal) and borrowed (from
 /// the dirstate/explicit) paths, this comes up a lot.
 pub type HgPathCow<'a> = Cow<'a, HgPath>;
 
 /// A path with its computed ``Dispatch`` information
 type DispatchedPath<'a> = (HgPathCow<'a>, Dispatch);
 
 /// The conversion from `HgPath` to a real fs path failed.
 /// `22` is the error code for "Invalid argument"
 const INVALID_PATH_DISPATCH: Dispatch = Dispatch::Bad(BadMatch::OsError(22));
 
 /// Dates and times that are outside the 31-bit signed range are compared
 /// modulo 2^31. This should prevent hg from behaving badly with very large
 /// files or corrupt dates while still having a high probability of detecting
 /// changes. (issue2608)
 /// TODO I haven't found a way of having `b` be `Into<i32>`, since `From<u64>`
 /// is not defined for `i32`, and there is no `As` trait. This forces the
 /// caller to cast `b` as `i32`.
 fn mod_compare(a: i32, b: i32) -> bool {
     a & i32::max_value() != b & i32::max_value()
 }
 
 /// Return a sorted list containing information about the entries
 /// in the directory.
 ///
 /// * `skip_dot_hg` - Return an empty vec if `path` contains a `.hg` directory
 fn list_directory(
     path: impl AsRef<Path>,
     skip_dot_hg: bool,
 ) -> std::io::Result<Vec<(HgPathBuf, DirEntry)>> {
     let mut results = vec![];
     let entries = read_dir(path.as_ref())?;
 
     for entry in entries {
         let entry = entry?;
         let filename = os_string_to_hg_path_buf(entry.file_name())?;
         let file_type = entry.file_type()?;
         if skip_dot_hg && filename.as_bytes() == b".hg" && file_type.is_dir() {
             return Ok(vec![]);
         } else {
             results.push((filename, entry))
         }
     }
 
     results.sort_unstable_by_key(|e| e.0.clone());
     Ok(results)
 }
 
 /// The file corresponding to the dirstate entry was found on the filesystem.
 fn dispatch_found(
     filename: impl AsRef<HgPath>,
     entry: DirstateEntry,
     metadata: HgMetadata,
     copy_map: &CopyMap,
     options: StatusOptions,
 ) -> Dispatch {
     let DirstateEntry {
         state,
         mode,
         mtime,
         size,
     } = entry;
 
     let HgMetadata {
         st_mode,
         st_size,
         st_mtime,
         ..
     } = metadata;
 
     match state {
         EntryState::Normal => {
             let size_changed = mod_compare(size, st_size as i32);
             let mode_changed =
                 (mode ^ st_mode as i32) & 0o100 != 0o000 && options.check_exec;
             let metadata_changed = size >= 0 && (size_changed || mode_changed);
             let other_parent = size == SIZE_FROM_OTHER_PARENT;
 
             if metadata_changed
                 || other_parent
                 || copy_map.contains_key(filename.as_ref())
             {
                 if metadata.is_symlink() && size_changed {
                     // issue6456: Size returned may be longer due to encryption
                     // on EXT-4 fscrypt. TODO maybe only do it on EXT4?
                     Dispatch::Unsure
                 } else {
                     Dispatch::Modified
                 }
             } else if mod_compare(mtime, st_mtime as i32)
                 || st_mtime == options.last_normal_time
             {
                 // the file may have just been marked as normal and
                 // it may have changed in the same second without
                 // changing its size. This can happen if we quickly
                 // do multiple commits. Force lookup, so we don't
                 // miss such a racy file change.
                 Dispatch::Unsure
             } else if options.list_clean {
                 Dispatch::Clean
             } else {
                 Dispatch::None
             }
         }
         EntryState::Merged => Dispatch::Modified,
         EntryState::Added => Dispatch::Added,
         EntryState::Removed => Dispatch::Removed,
         EntryState::Unknown => Dispatch::Unknown,
     }
 }
 
 /// The file corresponding to this Dirstate entry is missing.
 fn dispatch_missing(state: EntryState) -> Dispatch {
     match state {
         // File was removed from the filesystem during commands
         EntryState::Normal | EntryState::Merged | EntryState::Added => {
             Dispatch::Deleted
         }
         // File was removed, everything is normal
         EntryState::Removed => Dispatch::Removed,
         // File is unknown to Mercurial, everything is normal
         EntryState::Unknown => Dispatch::Unknown,
     }
 }
 
 fn dispatch_os_error(e: &std::io::Error) -> Dispatch {
     Dispatch::Bad(BadMatch::OsError(
         e.raw_os_error().expect("expected real OS error"),
     ))
 }
 
 lazy_static! {
     static ref DEFAULT_WORK: HashSet<&'static HgPath> = {
         let mut h = HashSet::new();
         h.insert(HgPath::new(b""));
         h
     };
 }
 
 #[derive(Debug, Copy, Clone)]
 pub struct StatusOptions {
     /// Remember the most recent modification timeslot for status, to make
     /// sure we won't miss future size-preserving file content modifications
     /// that happen within the same timeslot.
     pub last_normal_time: i64,
     /// Whether we are on a filesystem with UNIX-like exec flags
     pub check_exec: bool,
     pub list_clean: bool,
     pub list_unknown: bool,
     pub list_ignored: bool,
     /// Whether to collect traversed dirs for applying a callback later.
     /// Used by `hg purge` for example.
     pub collect_traversed_dirs: bool,
 }
 
-#[derive(Debug)]
+#[derive(Debug, Default)]
 pub struct DirstateStatus<'a> {
     /// Tracked files whose contents have changed since the parent revision
     pub modified: Vec<HgPathCow<'a>>,
 
     /// Newly-tracked files that were not present in the parent
     pub added: Vec<HgPathCow<'a>>,
 
     /// Previously-tracked files that have been (re)moved with an hg command
     pub removed: Vec<HgPathCow<'a>>,
 
     /// (Still) tracked files that are missing, (re)moved with an non-hg
     /// command
     pub deleted: Vec<HgPathCow<'a>>,
 
     /// Tracked files that are up to date with the parent.
     /// Only pupulated if `StatusOptions::list_clean` is true.
     pub clean: Vec<HgPathCow<'a>>,
 
     /// Files in the working directory that are ignored with `.hgignore`.
     /// Only pupulated if `StatusOptions::list_ignored` is true.
     pub ignored: Vec<HgPathCow<'a>>,
 
     /// Files in the working directory that are neither tracked nor ignored.
     /// Only pupulated if `StatusOptions::list_unknown` is true.
     pub unknown: Vec<HgPathCow<'a>>,
 
     /// Was explicitly matched but cannot be found/accessed
     pub bad: Vec<(HgPathCow<'a>, BadMatch)>,
 
     /// Either clean or modified, but we can’t tell from filesystem metadata
     /// alone. The file contents need to be read and compared with that in
     /// the parent.
     pub unsure: Vec<HgPathCow<'a>>,
 
     /// Only filled if `collect_traversed_dirs` is `true`
     pub traversed: Vec<HgPathBuf>,
 }
 
 #[derive(Debug, derive_more::From)]
 pub enum StatusError {
     /// Generic IO error
     IO(std::io::Error),
     /// An invalid path that cannot be represented in Mercurial was found
     Path(HgPathError),
     /// An invalid "ignore" pattern was found
     Pattern(PatternError),
 }
 
 pub type StatusResult<T> = Result<T, StatusError>;
 
 impl fmt::Display for StatusError {
     fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
         match self {
             StatusError::IO(error) => error.fmt(f),
             StatusError::Path(error) => error.fmt(f),
             StatusError::Pattern(error) => error.fmt(f),
         }
     }
 }
 
 /// Gives information about which files are changed in the working directory
 /// and how, compared to the revision we're based on
 pub struct Status<'a, M: ?Sized + Matcher + Sync> {
     dmap: &'a DirstateMap,
     pub(crate) matcher: &'a M,
     root_dir: PathBuf,
     pub(crate) options: StatusOptions,
     ignore_fn: IgnoreFnType<'a>,
 }
 
 impl<'a, M> Status<'a, M>
 where
     M: ?Sized + Matcher + Sync,
 {
     pub fn new(
         dmap: &'a DirstateMap,
         matcher: &'a M,
         root_dir: PathBuf,
         ignore_files: Vec<PathBuf>,
         options: StatusOptions,
     ) -> StatusResult<(Self, Vec<PatternFileWarning>)> {
         // Needs to outlive `dir_ignore_fn` since it's captured.
 
         let (ignore_fn, warnings): (IgnoreFnType, _) =
             if options.list_ignored || options.list_unknown {
                 get_ignore_function(ignore_files, &root_dir)?
             } else {
                 (Box::new(|&_| true), vec![])
             };
 
         Ok((
             Self {
                 dmap,
                 matcher,
                 root_dir,
                 options,
                 ignore_fn,
             },
             warnings,
         ))
     }
 
     /// Is the path ignored?
     pub fn is_ignored(&self, path: impl AsRef<HgPath>) -> bool {
         (self.ignore_fn)(path.as_ref())
     }
 
     /// Is the path or one of its ancestors ignored?
     pub fn dir_ignore(&self, dir: impl AsRef<HgPath>) -> bool {
         // Only involve ignore mechanism if we're listing unknowns or ignored.
         if self.options.list_ignored || self.options.list_unknown {
             if self.is_ignored(&dir) {
                 true
             } else {
                 for p in find_dirs(dir.as_ref()) {
                     if self.is_ignored(p) {
                         return true;
                     }
                 }
                 false
             }
         } else {
             true
         }
     }
 
     /// Get stat data about the files explicitly specified by the matcher.
     /// Returns a tuple of the directories that need to be traversed and the
     /// files with their corresponding `Dispatch`.
     /// TODO subrepos
     #[timed]
     pub fn walk_explicit(
         &self,
         traversed_sender: crossbeam_channel::Sender<HgPathBuf>,
     ) -> (Vec<DispatchedPath<'a>>, Vec<DispatchedPath<'a>>) {
         self.matcher
             .file_set()
             .unwrap_or(&DEFAULT_WORK)
             .par_iter()
             .flat_map(|&filename| -> Option<_> {
                 // TODO normalization
                 let normalized = filename;
 
                 let buf = match hg_path_to_path_buf(normalized) {
                     Ok(x) => x,
                     Err(_) => {
                         return Some((
                             Cow::Borrowed(normalized),
                             INVALID_PATH_DISPATCH,
                         ))
                     }
                 };
                 let target = self.root_dir.join(buf);
                 let st = target.symlink_metadata();
                 let in_dmap = self.dmap.get(normalized);
                 match st {
                     Ok(meta) => {
                         let file_type = meta.file_type();
                         return if file_type.is_file() || file_type.is_symlink()
                         {
                             if let Some(entry) = in_dmap {
                                 return Some((
                                     Cow::Borrowed(normalized),
                                     dispatch_found(
                                         &normalized,
                                         *entry,
                                         HgMetadata::from_metadata(meta),
                                         &self.dmap.copy_map,
                                         self.options,
                                     ),
                                 ));
                             }
                             Some((
                                 Cow::Borrowed(normalized),
                                 Dispatch::Unknown,
                             ))
                         } else if file_type.is_dir() {
                             if self.options.collect_traversed_dirs {
                                 traversed_sender
                                     .send(normalized.to_owned())
                                     .expect("receiver should outlive sender");
                             }
                             Some((
                                 Cow::Borrowed(normalized),
                                 Dispatch::Directory {
                                     was_file: in_dmap.is_some(),
                                 },
                             ))
                         } else {
                             Some((
                                 Cow::Borrowed(normalized),
                                 Dispatch::Bad(BadMatch::BadType(
                                     // TODO do more than unknown
                                     // Support for all `BadType` variant
                                     // varies greatly between platforms.
                                     // So far, no tests check the type and
                                     // this should be good enough for most
                                     // users.
                                     BadType::Unknown,
                                 )),
                             ))
                         };
                     }
                     Err(_) => {
                         if let Some(entry) = in_dmap {
                             return Some((
                                 Cow::Borrowed(normalized),
                                 dispatch_missing(entry.state),
                             ));
                         }
                     }
                 };
                 None
             })
             .partition(|(_, dispatch)| match dispatch {
                 Dispatch::Directory { .. } => true,
                 _ => false,
             })
     }
 
     /// Walk the working directory recursively to look for changes compared to
     /// the current `DirstateMap`.
     ///
     /// This takes a mutable reference to the results to account for the
     /// `extend` in timings
     #[timed]
     pub fn traverse(
         &self,
         path: impl AsRef<HgPath>,
         old_results: &FastHashMap<HgPathCow<'a>, Dispatch>,
         results: &mut Vec<DispatchedPath<'a>>,
         traversed_sender: crossbeam_channel::Sender<HgPathBuf>,
     ) {
         // The traversal is done in parallel, so use a channel to gather
         // entries. `crossbeam_channel::Sender` is `Sync`, while `mpsc::Sender`
         // is not.
         let (files_transmitter, files_receiver) =
             crossbeam_channel::unbounded();
 
         self.traverse_dir(
             &files_transmitter,
             path,
             &old_results,
             traversed_sender,
         );
 
         // Disconnect the channel so the receiver stops waiting
         drop(files_transmitter);
 
         let new_results = files_receiver
             .into_iter()
             .par_bridge()
             .map(|(f, d)| (Cow::Owned(f), d));
 
         results.par_extend(new_results);
     }
 
     /// Dispatch a single entry (file, folder, symlink...) found during
     /// `traverse`. If the entry is a folder that needs to be traversed, it
     /// will be handled in a separate thread.
     fn handle_traversed_entry<'b>(
         &'a self,
         scope: &rayon::Scope<'b>,
         files_sender: &'b crossbeam_channel::Sender<(HgPathBuf, Dispatch)>,
         old_results: &'a FastHashMap<Cow<HgPath>, Dispatch>,
         filename: HgPathBuf,
         dir_entry: DirEntry,
         traversed_sender: crossbeam_channel::Sender<HgPathBuf>,
     ) -> IoResult<()>
     where
         'a: 'b,
     {
         let file_type = dir_entry.file_type()?;
         let entry_option = self.dmap.get(&filename);
 
         if filename.as_bytes() == b".hg" {
             // Could be a directory or a symlink
             return Ok(());
         }
 
         if file_type.is_dir() {
             self.handle_traversed_dir(
                 scope,
                 files_sender,
                 old_results,
                 entry_option,
                 filename,
                 traversed_sender,
             );
         } else if file_type.is_file() || file_type.is_symlink() {
             if let Some(entry) = entry_option {
                 if self.matcher.matches_everything()
                     || self.matcher.matches(&filename)
                 {
                     let metadata = dir_entry.metadata()?;
                     files_sender
                         .send((
                             filename.to_owned(),
                             dispatch_found(
                                 &filename,
                                 *entry,
                                 HgMetadata::from_metadata(metadata),
                                 &self.dmap.copy_map,
                                 self.options,
                             ),
                         ))
                         .unwrap();
                 }
             } else if (self.matcher.matches_everything()
                 || self.matcher.matches(&filename))
                 && !self.is_ignored(&filename)
             {
                 if (self.options.list_ignored
                     || self.matcher.exact_match(&filename))
                     && self.dir_ignore(&filename)
                 {
                     if self.options.list_ignored {
                         files_sender
                             .send((filename.to_owned(), Dispatch::Ignored))
                             .unwrap();
                     }
                 } else if self.options.list_unknown {
                     files_sender
                         .send((filename.to_owned(), Dispatch::Unknown))
                         .unwrap();
                 }
             } else if self.is_ignored(&filename) && self.options.list_ignored {
                 files_sender
                     .send((filename.to_owned(), Dispatch::Ignored))
                     .unwrap();
             }
         } else if let Some(entry) = entry_option {
             // Used to be a file or a folder, now something else.
             if self.matcher.matches_everything()
                 || self.matcher.matches(&filename)
             {
                 files_sender
                     .send((filename.to_owned(), dispatch_missing(entry.state)))
                     .unwrap();
             }
         }
 
         Ok(())
     }
 
     /// A directory was found in the filesystem and needs to be traversed
     fn handle_traversed_dir<'b>(
         &'a self,
         scope: &rayon::Scope<'b>,
         files_sender: &'b crossbeam_channel::Sender<(HgPathBuf, Dispatch)>,
         old_results: &'a FastHashMap<Cow<HgPath>, Dispatch>,
         entry_option: Option<&'a DirstateEntry>,
         directory: HgPathBuf,
         traversed_sender: crossbeam_channel::Sender<HgPathBuf>,
     ) where
         'a: 'b,
     {
         scope.spawn(move |_| {
             // Nested `if` until `rust-lang/rust#53668` is stable
             if let Some(entry) = entry_option {
                 // Used to be a file, is now a folder
                 if self.matcher.matches_everything()
                     || self.matcher.matches(&directory)
                 {
                     files_sender
                         .send((
                             directory.to_owned(),
                             dispatch_missing(entry.state),
                         ))
                         .unwrap();
                 }
             }
             // Do we need to traverse it?
             if !self.is_ignored(&directory) || self.options.list_ignored {
                 self.traverse_dir(
                     files_sender,
                     directory,
                     &old_results,
                     traversed_sender,
                 )
             }
         });
     }
 
     /// Decides whether the directory needs to be listed, and if so handles the
     /// entries in a separate thread.
     fn traverse_dir(
         &self,
         files_sender: &crossbeam_channel::Sender<(HgPathBuf, Dispatch)>,
         directory: impl AsRef<HgPath>,
         old_results: &FastHashMap<Cow<HgPath>, Dispatch>,
         traversed_sender: crossbeam_channel::Sender<HgPathBuf>,
     ) {
         let directory = directory.as_ref();
 
         if self.options.collect_traversed_dirs {
             traversed_sender
                 .send(directory.to_owned())
                 .expect("receiver should outlive sender");
         }
 
         let visit_entries = match self.matcher.visit_children_set(directory) {
             VisitChildrenSet::Empty => return,
             VisitChildrenSet::This | VisitChildrenSet::Recursive => None,
             VisitChildrenSet::Set(set) => Some(set),
         };
         let buf = match hg_path_to_path_buf(directory) {
             Ok(b) => b,
             Err(_) => {
                 files_sender
                     .send((directory.to_owned(), INVALID_PATH_DISPATCH))
                     .expect("receiver should outlive sender");
                 return;
             }
         };
         let dir_path = self.root_dir.join(buf);
 
         let skip_dot_hg = !directory.as_bytes().is_empty();
         let entries = match list_directory(dir_path, skip_dot_hg) {
             Err(e) => {
                 files_sender
                     .send((directory.to_owned(), dispatch_os_error(&e)))
                     .expect("receiver should outlive sender");
                 return;
             }
             Ok(entries) => entries,
         };
 
         rayon::scope(|scope| {
             for (filename, dir_entry) in entries {
                 if let Some(ref set) = visit_entries {
                     if !set.contains(filename.deref()) {
                         continue;
                     }
                 }
                 // TODO normalize
                 let filename = if directory.is_empty() {
                     filename.to_owned()
                 } else {
                     directory.join(&filename)
                 };
 
                 if !old_results.contains_key(filename.deref()) {
                     match self.handle_traversed_entry(
                         scope,
                         files_sender,
                         old_results,
                         filename,
                         dir_entry,
                         traversed_sender.clone(),
                     ) {
                         Err(e) => {
                             files_sender
                                 .send((
                                     directory.to_owned(),
                                     dispatch_os_error(&e),
                                 ))
                                 .expect("receiver should outlive sender");
                         }
                         Ok(_) => {}
                     }
                 }
             }
         })
     }
 
     /// Add the files in the dirstate to the results.
     ///
     /// This takes a mutable reference to the results to account for the
     /// `extend` in timings
     #[timed]
     pub fn extend_from_dmap(&self, results: &mut Vec<DispatchedPath<'a>>) {
         results.par_extend(
             self.dmap
                 .par_iter()
                 .filter(|(path, _)| self.matcher.matches(path))
                 .map(move |(filename, entry)| {
                     let filename: &HgPath = filename;
                     let filename_as_path = match hg_path_to_path_buf(filename)
                     {
                         Ok(f) => f,
                         Err(_) => {
                             return (
                                 Cow::Borrowed(filename),
                                 INVALID_PATH_DISPATCH,
                             )
                         }
                     };
                     let meta = self
                         .root_dir
                         .join(filename_as_path)
                         .symlink_metadata();
                     match meta {
                         Ok(m)
                             if !(m.file_type().is_file()
                                 || m.file_type().is_symlink()) =>
                         {
                             (
                                 Cow::Borrowed(filename),
                                 dispatch_missing(entry.state),
                             )
                         }
                         Ok(m) => (
                             Cow::Borrowed(filename),
                             dispatch_found(
                                 filename,
                                 *entry,
                                 HgMetadata::from_metadata(m),
                                 &self.dmap.copy_map,
                                 self.options,
                             ),
                         ),
                         Err(e)
                             if e.kind() == ErrorKind::NotFound
                                 || e.raw_os_error() == Some(20) =>
                         {
                             // Rust does not yet have an `ErrorKind` for
                             // `NotADirectory` (errno 20)
                             // It happens if the dirstate contains `foo/bar`
                             // and foo is not a
                             // directory
                             (
                                 Cow::Borrowed(filename),
                                 dispatch_missing(entry.state),
                             )
                         }
                         Err(e) => {
                             (Cow::Borrowed(filename), dispatch_os_error(&e))
                         }
                     }
                 }),
         );
     }
 
     /// Checks all files that are in the dirstate but were not found during the
     /// working directory traversal. This means that the rest must
     /// be either ignored, under a symlink or under a new nested repo.
     ///
     /// This takes a mutable reference to the results to account for the
     /// `extend` in timings
     #[timed]
     pub fn handle_unknowns(&self, results: &mut Vec<DispatchedPath<'a>>) {
         let to_visit: Vec<(&HgPath, &DirstateEntry)> =
             if results.is_empty() && self.matcher.matches_everything() {
                 self.dmap.iter().map(|(f, e)| (f.deref(), e)).collect()
             } else {
                 // Only convert to a hashmap if needed.
                 let old_results: FastHashMap<_, _> =
                     results.iter().cloned().collect();
                 self.dmap
                     .iter()
                     .filter_map(move |(f, e)| {
                         if !old_results.contains_key(f.deref())
                             && self.matcher.matches(f)
                         {
                             Some((f.deref(), e))
                         } else {
                             None
                         }
                     })
                     .collect()
             };
 
         let path_auditor = PathAuditor::new(&self.root_dir);
 
         let new_results = to_visit.into_par_iter().filter_map(
             |(filename, entry)| -> Option<_> {
                 // Report ignored items in the dmap as long as they are not
                 // under a symlink directory.
                 if path_auditor.check(filename) {
                     // TODO normalize for case-insensitive filesystems
                     let buf = match hg_path_to_path_buf(filename) {
                         Ok(x) => x,
                         Err(_) => {
                             return Some((
                                 Cow::Owned(filename.to_owned()),
                                 INVALID_PATH_DISPATCH,
                             ));
                         }
                     };
                     Some((
                         Cow::Owned(filename.to_owned()),
                         match self.root_dir.join(&buf).symlink_metadata() {
                             // File was just ignored, no links, and exists
                             Ok(meta) => {
                                 let metadata = HgMetadata::from_metadata(meta);
                                 dispatch_found(
                                     filename,
                                     *entry,
                                     metadata,
                                     &self.dmap.copy_map,
                                     self.options,
                                 )
                             }
                             // File doesn't exist
                             Err(_) => dispatch_missing(entry.state),
                         },
                     ))
                 } else {
                     // It's either missing or under a symlink directory which
                     // we, in this case, report as missing.
                     Some((
                         Cow::Owned(filename.to_owned()),
                         dispatch_missing(entry.state),
                     ))
                 }
             },
         );
 
         results.par_extend(new_results);
     }
 }
 
 #[timed]
 pub fn build_response<'a>(
     results: impl IntoIterator<Item = DispatchedPath<'a>>,
     traversed: Vec<HgPathBuf>,
 ) -> DirstateStatus<'a> {
     let mut unsure = vec![];
     let mut modified = vec![];
     let mut added = vec![];
     let mut removed = vec![];
     let mut deleted = vec![];
     let mut clean = vec![];
     let mut ignored = vec![];
     let mut unknown = vec![];
     let mut bad = vec![];
 
     for (filename, dispatch) in results.into_iter() {
         match dispatch {
             Dispatch::Unknown => unknown.push(filename),
             Dispatch::Unsure => unsure.push(filename),
             Dispatch::Modified => modified.push(filename),
             Dispatch::Added => added.push(filename),
             Dispatch::Removed => removed.push(filename),
             Dispatch::Deleted => deleted.push(filename),
             Dispatch::Clean => clean.push(filename),
             Dispatch::Ignored => ignored.push(filename),
             Dispatch::None => {}
             Dispatch::Bad(reason) => bad.push((filename, reason)),
             Dispatch::Directory { .. } => {}
         }
     }
 
     DirstateStatus {
         modified,
         added,
         removed,
         deleted,
         clean,
         ignored,
         unknown,
         bad,
         unsure,
         traversed,
     }
 }
 
 /// Get the status of files in the working directory.
 ///
 /// This is the current entry-point for `hg-core` and is realistically unusable
 /// outside of a Python context because its arguments need to provide a lot of
 /// information that will not be necessary in the future.
 #[timed]
 pub fn status<'a>(
     dmap: &'a DirstateMap,
     matcher: &'a (dyn Matcher + Sync),
     root_dir: PathBuf,
     ignore_files: Vec<PathBuf>,
     options: StatusOptions,
 ) -> StatusResult<(DirstateStatus<'a>, Vec<PatternFileWarning>)> {
     let (status, warnings) =
         Status::new(dmap, matcher, root_dir, ignore_files, options)?;
 
     Ok((status.run()?, warnings))
 }

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

@@ -1,652 +1,656 b''
 use bytes_cast::BytesCast;
 use std::path::PathBuf;
 use std::{collections::BTreeMap, convert::TryInto};
 
 use super::path_with_basename::WithBasename;
 use crate::dirstate::parsers::clear_ambiguous_mtime;
 use crate::dirstate::parsers::pack_entry;
 use crate::dirstate::parsers::packed_entry_size;
 use crate::dirstate::parsers::parse_dirstate_entries;
 use crate::dirstate::parsers::parse_dirstate_parents;
 use crate::dirstate::parsers::Timestamp;
 use crate::matchers::Matcher;
 use crate::revlog::node::NULL_NODE;
 use crate::utils::hg_path::{HgPath, HgPathBuf};
 use crate::CopyMapIter;
 use crate::DirstateEntry;
 use crate::DirstateError;
 use crate::DirstateMapError;
 use crate::DirstateParents;
 use crate::DirstateStatus;
 use crate::EntryState;
 use crate::PatternFileWarning;
 use crate::StateMapIter;
 use crate::StatusError;
 use crate::StatusOptions;
 
 pub struct DirstateMap {
     parents: Option<DirstateParents>,
     dirty_parents: bool,
-    root: ChildNodes,
+    pub(super) root: ChildNodes,
 
     /// Number of nodes anywhere in the tree that have `.entry.is_some()`.
     nodes_with_entry_count: usize,
 
     /// Number of nodes anywhere in the tree that have
     /// `.copy_source.is_some()`.
     nodes_with_copy_source_count: usize,
 }
 
 /// 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 `BTreeMap` would waste time always re-comparing the same
 /// string prefix.
-type ChildNodes = BTreeMap<WithBasename<HgPathBuf>, Node>;
+pub(super) type ChildNodes = BTreeMap<WithBasename<HgPathBuf>, Node>;
 
 /// Represents a file or a directory
 #[derive(Default)]
-struct Node {
+pub(super) struct Node {
     /// `None` for directories
-    entry: Option<DirstateEntry>,
+    pub(super) entry: Option<DirstateEntry>,
 
-    copy_source: Option<HgPathBuf>,
+    pub(super) copy_source: Option<HgPathBuf>,
 
-    children: ChildNodes,
+    pub(super) children: ChildNodes,
 
     /// How many (non-inclusive) descendants of this node are tracked files
     tracked_descendants_count: usize,
 }
 
 impl Node {
     /// Whether this node has a `DirstateEntry` with `.state.is_tracked()`
     fn is_tracked_file(&self) -> bool {
         if let Some(entry) = &self.entry {
             entry.state.is_tracked()
         } else {
             false
         }
     }
+
+    pub(super) fn state(&self) -> Option<EntryState> {
+        self.entry.as_ref().map(|entry| entry.state)
+    }
 }
 
 /// `(full_path, entry, copy_source)`
 type NodeDataMut<'a> = (
     &'a WithBasename<HgPathBuf>,
     &'a mut Option<DirstateEntry>,
     &'a mut Option<HgPathBuf>,
 );
 
 impl DirstateMap {
     pub fn new() -> Self {
         Self {
             parents: None,
             dirty_parents: false,
             root: ChildNodes::new(),
             nodes_with_entry_count: 0,
             nodes_with_copy_source_count: 0,
         }
     }
 
     fn get_node(&self, path: &HgPath) -> Option<&Node> {
         let mut children = &self.root;
         let mut components = path.components();
         let mut component =
             components.next().expect("expected at least one components");
         loop {
             let child = children.get(component)?;
             if let Some(next_component) = components.next() {
                 component = next_component;
                 children = &child.children;
             } else {
                 return Some(child);
             }
         }
     }
 
     /// 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>(
         root: &'tree mut ChildNodes,
         path: &HgPath,
     ) -> Option<&'tree mut Node> {
         Self::each_and_get(root, path, |_| {})
     }
 
     /// Call `each` for each ancestor node of the one at `path` (not including
     /// that node itself), starting from nearest the root.
     ///
     /// Panics (possibly after some calls to `each`) if there is no node at
     /// `path`.
     fn for_each_ancestor_node<'tree>(
         &mut self,
         path: &HgPath,
         each: impl FnMut(&mut Node),
     ) {
         let parent = path.parent();
         if !parent.is_empty() {
             Self::each_and_get(&mut self.root, parent, each)
                 .expect("missing dirstate node");
         }
     }
 
     /// Common implementation detail of `get_node_mut` and
     /// `for_each_ancestor_node`
     fn each_and_get<'tree>(
         root: &'tree mut ChildNodes,
         path: &HgPath,
         mut each: impl FnMut(&mut Node),
     ) -> Option<&'tree mut Node> {
         let mut children = root;
         let mut components = path.components();
         let mut component =
             components.next().expect("expected at least one components");
         loop {
             let child = children.get_mut(component)?;
             each(child);
             if let Some(next_component) = components.next() {
                 component = next_component;
                 children = &mut child.children;
             } else {
                 return Some(child);
             }
         }
     }
 
     fn get_or_insert_node<'tree>(
         root: &'tree mut ChildNodes,
         path: &HgPath,
     ) -> &'tree mut Node {
         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 double lookup in all cases without allocating
             // an owned key in cases where the map already contains that key?
             let child_node =
                 if child_nodes.contains_key(ancestor_path.base_name()) {
                     child_nodes.get_mut(ancestor_path.base_name()).unwrap()
                 } else {
                     // This is always a vacant entry, using `.entry()` lets us
                     // return a `&mut Node` of the newly-inserted node without
                     // yet another lookup. `BTreeMap::insert` doesn’t do this.
                     child_nodes.entry(ancestor_path.to_owned()).or_default()
                 };
             if let Some(next) = inclusive_ancestor_paths.next() {
                 ancestor_path = next;
                 child_nodes = &mut child_node.children;
             } else {
                 return child_node;
             }
         }
     }
 
     /// The meaning of `new_copy_source` is:
     ///
     /// * `Some(Some(x))`: set `Node::copy_source` to `Some(x)`
     /// * `Some(None)`: set `Node::copy_source` to `None`
     /// * `None`: leave `Node::copy_source` unchanged
     fn add_file_node(
         &mut self,
         path: &HgPath,
         new_entry: DirstateEntry,
         new_copy_source: Option<Option<HgPathBuf>>,
     ) {
         let node = Self::get_or_insert_node(&mut self.root, path);
         if node.entry.is_none() {
             self.nodes_with_entry_count += 1
         }
         if let Some(source) = &new_copy_source {
             if node.copy_source.is_none() && source.is_some() {
                 self.nodes_with_copy_source_count += 1
             }
             if node.copy_source.is_some() && source.is_none() {
                 self.nodes_with_copy_source_count -= 1
             }
         }
         let tracked_count_increment =
             match (node.is_tracked_file(), new_entry.state.is_tracked()) {
                 (false, true) => 1,
                 (true, false) => -1,
                 _ => 0,
             };
 
         node.entry = Some(new_entry);
         if let Some(source) = new_copy_source {
             node.copy_source = source
         }
         // Borrow of `self.root` through `node` ends here
 
         match tracked_count_increment {
             1 => self.for_each_ancestor_node(path, |node| {
                 node.tracked_descendants_count += 1
             }),
             // We can’t use `+= -1` because the counter is unsigned
             -1 => self.for_each_ancestor_node(path, |node| {
                 node.tracked_descendants_count -= 1
             }),
             _ => {}
         }
     }
 
     fn iter_nodes<'a>(
         &'a self,
     ) -> impl Iterator<Item = (&'a WithBasename<HgPathBuf>, &'a Node)> + 'a
     {
         // 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.iter();
         std::iter::from_fn(move || {
             while let Some((key, child_node)) = iter.next() {
                 // Pseudo-recursion
                 let new_iter = child_node.children.iter();
                 let old_iter = std::mem::replace(&mut iter, new_iter);
                 stack.push((key, child_node, old_iter));
             }
             // Found the end of a `children.iter()` iterator.
             if let Some((key, child_node, next_iter)) = stack.pop() {
                 // "Return" from pseudo-recursion by restoring state from the
                 // explicit stack
                 iter = next_iter;
 
                 Some((key, child_node))
             } else {
                 // Reached the bottom of the stack, we’re done
                 None
             }
         })
     }
 
     /// Mutable iterator for the `(entry, copy source)` of each node.
     ///
     /// It would not be safe to yield mutable references to nodes themeselves
     /// with `-> impl Iterator<Item = &mut Node>` since child nodes are
     /// reachable from their ancestor nodes, potentially creating multiple
     /// `&mut` references to a given node.
     fn iter_node_data_mut<'a>(
         &'a mut self,
     ) -> impl Iterator<Item = NodeDataMut<'a>> + 'a {
         // Explict stack for pseudo-recursion, see `iter_nodes` above.
         let mut stack = Vec::new();
         let mut iter = self.root.iter_mut();
         std::iter::from_fn(move || {
             while let Some((key, child_node)) = iter.next() {
                 // Pseudo-recursion
                 let data =
                     (key, &mut child_node.entry, &mut child_node.copy_source);
                 let new_iter = child_node.children.iter_mut();
                 let old_iter = std::mem::replace(&mut iter, new_iter);
                 stack.push((data, old_iter));
             }
             // Found the end of a `children.values_mut()` iterator.
             if let Some((data, next_iter)) = stack.pop() {
                 // "Return" from pseudo-recursion by restoring state from the
                 // explicit stack
                 iter = next_iter;
 
                 Some(data)
             } else {
                 // Reached the bottom of the stack, we’re done
                 None
             }
         })
     }
 }
 
 impl super::dispatch::DirstateMapMethods for DirstateMap {
     fn clear(&mut self) {
         self.set_parents(&DirstateParents {
             p1: NULL_NODE,
             p2: NULL_NODE,
         });
         self.root.clear();
         self.nodes_with_entry_count = 0;
         self.nodes_with_copy_source_count = 0;
     }
 
     fn add_file(
         &mut self,
         filename: &HgPath,
         _old_state: EntryState,
         entry: DirstateEntry,
     ) -> Result<(), DirstateMapError> {
         self.add_file_node(filename, entry, None);
         Ok(())
     }
 
     fn remove_file(
         &mut self,
         filename: &HgPath,
         _old_state: EntryState,
         size: i32,
     ) -> Result<(), DirstateMapError> {
         let entry = DirstateEntry {
             state: EntryState::Removed,
             mode: 0,
             size,
             mtime: 0,
         };
         self.add_file_node(filename, entry, None);
         Ok(())
     }
 
     fn drop_file(
         &mut self,
         filename: &HgPath,
         _old_state: EntryState,
     ) -> Result<bool, DirstateMapError> {
         if let Some(node) = Self::get_node_mut(&mut self.root, filename) {
             let was_tracked = node.is_tracked_file();
             let had_entry = node.entry.is_some();
             let had_copy_source = node.copy_source.is_some();
 
             // TODO: this leaves in the tree a "non-file" node. Should we
             // remove the node instead, together with ancestor nodes for
             // directories that become empty?
             node.entry = None;
             node.copy_source = None;
 
             if had_entry {
                 self.nodes_with_entry_count -= 1
             }
             if had_copy_source {
                 self.nodes_with_copy_source_count -= 1
             }
             if was_tracked {
                 self.for_each_ancestor_node(filename, |node| {
                     node.tracked_descendants_count -= 1
                 })
             }
             Ok(had_entry)
         } else {
             Ok(false)
         }
     }
 
     fn clear_ambiguous_times(&mut self, filenames: Vec<HgPathBuf>, now: i32) {
         for filename in filenames {
             if let Some(node) = Self::get_node_mut(&mut self.root, &filename) {
                 if let Some(entry) = node.entry.as_mut() {
                     clear_ambiguous_mtime(entry, now);
                 }
             }
         }
     }
 
     fn non_normal_entries_contains(&mut self, key: &HgPath) -> bool {
         self.get_node(key)
             .and_then(|node| node.entry.as_ref())
             .map_or(false, DirstateEntry::is_non_normal)
     }
 
     fn non_normal_entries_remove(&mut self, _key: &HgPath) {
         // Do nothing, this `DirstateMap` does not have a separate "non normal
         // entries" set that need to be kept up to date
     }
 
     fn non_normal_or_other_parent_paths(
         &mut self,
     ) -> Box<dyn Iterator<Item = &HgPathBuf> + '_> {
         Box::new(self.iter_nodes().filter_map(|(path, node)| {
             node.entry
                 .as_ref()
                 .filter(|entry| {
                     entry.is_non_normal() || entry.is_from_other_parent()
                 })
                 .map(|_| path.full_path())
         }))
     }
 
     fn set_non_normal_other_parent_entries(&mut self, _force: bool) {
         // Do nothing, this `DirstateMap` does not have a separate "non normal
         // entries" and "from other parent" sets that need to be recomputed
     }
 
     fn iter_non_normal_paths(
         &mut self,
     ) -> Box<dyn Iterator<Item = &HgPathBuf> + Send + '_> {
         self.iter_non_normal_paths_panic()
     }
 
     fn iter_non_normal_paths_panic(
         &self,
     ) -> Box<dyn Iterator<Item = &HgPathBuf> + Send + '_> {
         Box::new(self.iter_nodes().filter_map(|(path, node)| {
             node.entry
                 .as_ref()
                 .filter(|entry| entry.is_non_normal())
                 .map(|_| path.full_path())
         }))
     }
 
     fn iter_other_parent_paths(
         &mut self,
     ) -> Box<dyn Iterator<Item = &HgPathBuf> + Send + '_> {
         Box::new(self.iter_nodes().filter_map(|(path, node)| {
             node.entry
                 .as_ref()
                 .filter(|entry| entry.is_from_other_parent())
                 .map(|_| path.full_path())
         }))
     }
 
     fn has_tracked_dir(
         &mut self,
         directory: &HgPath,
     ) -> Result<bool, DirstateMapError> {
         if let Some(node) = self.get_node(directory) {
             // A node without a `DirstateEntry` was created to hold child
             // nodes, and is therefore a directory.
             Ok(node.entry.is_none() && node.tracked_descendants_count > 0)
         } else {
             Ok(false)
         }
     }
 
     fn has_dir(
         &mut self,
         directory: &HgPath,
     ) -> Result<bool, DirstateMapError> {
         if let Some(node) = self.get_node(directory) {
             // A node without a `DirstateEntry` was created to hold child
             // nodes, and is therefore a directory.
             Ok(node.entry.is_none())
         } else {
             Ok(false)
         }
     }
 
     fn parents(
         &mut self,
         file_contents: &[u8],
     ) -> Result<&DirstateParents, DirstateError> {
         if self.parents.is_none() {
             let parents = if !file_contents.is_empty() {
                 parse_dirstate_parents(file_contents)?.clone()
             } else {
                 DirstateParents {
                     p1: NULL_NODE,
                     p2: NULL_NODE,
                 }
             };
             self.parents = Some(parents);
         }
         Ok(self.parents.as_ref().unwrap())
     }
 
     fn set_parents(&mut self, parents: &DirstateParents) {
         self.parents = Some(parents.clone());
         self.dirty_parents = true;
     }
 
     fn read<'a>(
         &mut self,
         file_contents: &'a [u8],
     ) -> Result<Option<&'a DirstateParents>, DirstateError> {
         if file_contents.is_empty() {
             return Ok(None);
         }
 
         let parents = parse_dirstate_entries(
             file_contents,
             |path, entry, copy_source| {
                 self.add_file_node(
                     path,
                     *entry,
                     Some(copy_source.map(HgPath::to_owned)),
                 )
             },
         )?;
 
         if !self.dirty_parents {
             self.set_parents(parents);
         }
 
         Ok(Some(parents))
     }
 
     fn pack(
         &mut self,
         parents: DirstateParents,
         now: Timestamp,
     ) -> Result<Vec<u8>, DirstateError> {
         // Optizimation (to be measured?): pre-compute size to avoid `Vec`
         // reallocations
         let mut size = parents.as_bytes().len();
         for (path, node) in self.iter_nodes() {
             if node.entry.is_some() {
                 size += packed_entry_size(
                     path.full_path(),
                     node.copy_source.as_ref(),
                 )
             }
         }
 
         let mut packed = Vec::with_capacity(size);
         packed.extend(parents.as_bytes());
 
         let now: i32 = now.0.try_into().expect("time overflow");
         for (path, opt_entry, copy_source) in self.iter_node_data_mut() {
             if let Some(entry) = opt_entry {
                 clear_ambiguous_mtime(entry, now);
                 pack_entry(
                     path.full_path(),
                     entry,
                     copy_source.as_ref(),
                     &mut packed,
                 );
             }
         }
         self.dirty_parents = false;
         Ok(packed)
     }
 
     fn set_all_dirs(&mut self) -> Result<(), DirstateMapError> {
         // Do nothing, this `DirstateMap` does not a separate `all_dirs` that
         // needs to be recomputed
         Ok(())
     }
 
     fn set_dirs(&mut self) -> Result<(), DirstateMapError> {
         // Do nothing, this `DirstateMap` does not a separate `dirs` that needs
         // to be recomputed
         Ok(())
     }
 
     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>
     {
         super::status::status(self, matcher, root_dir, ignore_files, options)
     }
 
     fn copy_map_len(&self) -> usize {
         self.nodes_with_copy_source_count
     }
 
     fn copy_map_iter(&self) -> CopyMapIter<'_> {
         Box::new(self.iter_nodes().filter_map(|(path, node)| {
             node.copy_source
                 .as_ref()
                 .map(|copy_source| (path.full_path(), copy_source))
         }))
     }
 
     fn copy_map_contains_key(&self, key: &HgPath) -> bool {
         if let Some(node) = self.get_node(key) {
             node.copy_source.is_some()
         } else {
             false
         }
     }
 
     fn copy_map_get(&self, key: &HgPath) -> Option<&HgPathBuf> {
         self.get_node(key)?.copy_source.as_ref()
     }
 
     fn copy_map_remove(&mut self, key: &HgPath) -> Option<HgPathBuf> {
         let count = &mut self.nodes_with_copy_source_count;
         Self::get_node_mut(&mut self.root, key).and_then(|node| {
             if node.copy_source.is_some() {
                 *count -= 1
             }
             node.copy_source.take()
         })
     }
 
     fn copy_map_insert(
         &mut self,
         key: HgPathBuf,
         value: HgPathBuf,
     ) -> Option<HgPathBuf> {
         let node = Self::get_or_insert_node(&mut self.root, &key);
         if node.copy_source.is_none() {
             self.nodes_with_copy_source_count += 1
         }
         node.copy_source.replace(value)
     }
 
     fn len(&self) -> usize {
         self.nodes_with_entry_count
     }
 
     fn contains_key(&self, key: &HgPath) -> bool {
         self.get(key).is_some()
     }
 
     fn get(&self, key: &HgPath) -> Option<&DirstateEntry> {
         self.get_node(key)?.entry.as_ref()
     }
 
     fn iter(&self) -> StateMapIter<'_> {
         Box::new(self.iter_nodes().filter_map(|(path, node)| {
             node.entry.as_ref().map(|entry| (path.full_path(), entry))
         }))
     }
 }

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

@@ -1,17 +1,379 b''
+use crate::dirstate::status::IgnoreFnType;
+use crate::dirstate_tree::dirstate_map::ChildNodes;
 use crate::dirstate_tree::dirstate_map::DirstateMap;
+use crate::dirstate_tree::dirstate_map::Node;
+use crate::matchers::get_ignore_function;
 use crate::matchers::Matcher;
+use crate::utils::files::get_bytes_from_os_string;
+use crate::utils::hg_path::HgPath;
 use crate::DirstateStatus;
+use crate::EntryState;
+use crate::HgPathBuf;
 use crate::PatternFileWarning;
 use crate::StatusError;
 use crate::StatusOptions;
+use std::borrow::Cow;
+use std::io;
+use std::path::Path;
 use std::path::PathBuf;
 
-pub fn status<'a>(
-    _dmap: &'a mut DirstateMap,
-    _matcher: &'a (dyn Matcher + Sync),
-    _root_dir: PathBuf,
-    _ignore_files: Vec<PathBuf>,
-    _options: StatusOptions,
-) -> Result<(DirstateStatus<'a>, Vec<PatternFileWarning>), StatusError> {
-    todo!()
+/// Returns the status of the working directory compared to its parent
+/// changeset.
+///
+/// This algorithm is based on traversing the filesystem tree (`fs` in function
+/// and variable names) and dirstate tree at the same time. The core of this
+/// traversal is the recursive `traverse_fs_directory_and_dirstate` function
+/// and its use of `itertools::merge_join_by`. When reaching a path that only
+/// exists in one of the two trees, depending on information requested by
+/// `options` we may need to traverse the remaining subtree.
+pub fn status<'tree>(
+    dmap: &'tree mut DirstateMap,
+    matcher: &(dyn Matcher + Sync),
+    root_dir: PathBuf,
+    ignore_files: Vec<PathBuf>,
+    options: StatusOptions,
+) -> Result<(DirstateStatus<'tree>, Vec<PatternFileWarning>), StatusError> {
+    let (ignore_fn, warnings): (IgnoreFnType, _) =
+        if options.list_ignored || options.list_unknown {
+            get_ignore_function(ignore_files, &root_dir)?
+        } else {
+            (Box::new(|&_| true), vec![])
+        };
+
+    let mut common = StatusCommon {
+        options,
+        matcher,
+        ignore_fn,
+        outcome: DirstateStatus::default(),
+    };
+    let is_at_repo_root = true;
+    let hg_path = HgPath::new("");
+    let has_ignored_ancestor = false;
+    common.traverse_fs_directory_and_dirstate(
+        has_ignored_ancestor,
+        &mut dmap.root,
+        hg_path,
+        &root_dir,
+        is_at_repo_root,
+    );
+    Ok((common.outcome, warnings))
+}
+
+/// Bag of random things needed by various parts of the algorithm. Reduces the
+/// number of parameters passed to functions.
+struct StatusCommon<'tree, 'a> {
+    options: StatusOptions,
+    matcher: &'a (dyn Matcher + Sync),
+    ignore_fn: IgnoreFnType<'a>,
+    outcome: DirstateStatus<'tree>,
 }
+
+impl<'tree, 'a> StatusCommon<'tree, 'a> {
+    fn traverse_fs_directory_and_dirstate(
+        &mut self,
+        has_ignored_ancestor: bool,
+        dirstate_nodes: &'tree mut ChildNodes,
+        directory_hg_path: &HgPath,
+        fs_path: &Path,
+        is_at_repo_root: bool,
+    ) {
+        // TODO: handle I/O errors
+        let mut fs_entries =
+            DirEntry::read_dir(fs_path, is_at_repo_root).unwrap();
+
+        // `merge_join_by` requires both its input iterators to be sorted:
+
+        // * `BTreeMap` iterates according to keys’ ordering by definition
+
+        // `sort_unstable_by_key` doesn’t allow keys borrowing from the value:
+        // https://github.com/rust-lang/rust/issues/34162
+        fs_entries.sort_unstable_by(|e1, e2| e1.base_name.cmp(&e2.base_name));
+
+        for pair in itertools::merge_join_by(
+            dirstate_nodes,
+            &fs_entries,
+            |(full_path, _node), fs_entry| {
+                full_path.base_name().cmp(&fs_entry.base_name)
+            },
+        ) {
+            use itertools::EitherOrBoth::*;
+            match pair {
+                Both((hg_path, dirstate_node), fs_entry) => {
+                    self.traverse_fs_and_dirstate(
+                        fs_entry,
+                        hg_path.full_path(),
+                        dirstate_node,
+                        has_ignored_ancestor,
+                    );
+                }
+                Left((hg_path, dirstate_node)) => self.traverse_dirstate_only(
+                    hg_path.full_path(),
+                    dirstate_node,
+                ),
+                Right(fs_entry) => self.traverse_fs_only(
+                    has_ignored_ancestor,
+                    directory_hg_path,
+                    fs_entry,
+                ),
+            }
+        }
+    }
+
+    fn traverse_fs_and_dirstate(
+        &mut self,
+        fs_entry: &DirEntry,
+        hg_path: &'tree HgPath,
+        dirstate_node: &'tree mut Node,
+        has_ignored_ancestor: bool,
+    ) {
+        if fs_entry.metadata.is_dir() {
+            if self.options.collect_traversed_dirs {
+                self.outcome.traversed.push(hg_path.into())
+            }
+            // If we previously had a file here, it was removed (with
+            // `hg rm` or similar) or deleted before it could be
+            // replaced by a directory.
+            self.mark_removed_or_deleted_if_file(
+                hg_path,
+                dirstate_node.state(),
+            );
+            let is_ignored = has_ignored_ancestor || (self.ignore_fn)(hg_path);
+            let is_at_repo_root = false;
+            self.traverse_fs_directory_and_dirstate(
+                is_ignored,
+                &mut dirstate_node.children,
+                hg_path,
+                &fs_entry.full_path,
+                is_at_repo_root,
+            );
+        } else {
+            if self.matcher.matches(hg_path) {
+                let full_path = Cow::from(hg_path);
+                if let Some(entry) = &dirstate_node.entry {
+                    match entry.state {
+                        EntryState::Added => {
+                            self.outcome.added.push(full_path)
+                        }
+                        EntryState::Removed => {
+                            self.outcome.removed.push(full_path)
+                        }
+                        EntryState::Merged => {
+                            self.outcome.modified.push(full_path)
+                        }
+                        EntryState::Normal => {
+                            self.handle_normal_file(
+                                full_path,
+                                dirstate_node,
+                                entry,
+                                fs_entry,
+                            );
+                        }
+                        // This variant is not used in DirstateMap
+                        // nodes
+                        EntryState::Unknown => unreachable!(),
+                    }
+                } else {
+                    // `node.entry.is_none()` indicates a "directory"
+                    // node, but the filesystem has a file
+                    self.mark_unknown_or_ignored(
+                        has_ignored_ancestor,
+                        full_path,
+                    )
+                }
+            }
+
+            for (child_hg_path, child_node) in &mut dirstate_node.children {
+                self.traverse_dirstate_only(
+                    child_hg_path.full_path(),
+                    child_node,
+                )
+            }
+        }
+    }
+
+    /// A file with `EntryState::Normal` in the dirstate was found in the
+    /// filesystem
+    fn handle_normal_file(
+        &mut self,
+        full_path: Cow<'tree, HgPath>,
+        dirstate_node: &Node,
+        entry: &crate::DirstateEntry,
+        fs_entry: &DirEntry,
+    ) {
+        // Keep the low 31 bits
+        fn truncate_u64(value: u64) -> i32 {
+            (value & 0x7FFF_FFFF) as i32
+        }
+        fn truncate_i64(value: i64) -> i32 {
+            (value & 0x7FFF_FFFF) as i32
+        }
+
+        let mode_changed = || {
+            self.options.check_exec && entry.mode_changed(&fs_entry.metadata)
+        };
+        let size_changed = entry.size != truncate_u64(fs_entry.metadata.len());
+        if entry.size >= 0
+            && size_changed
+            && fs_entry.metadata.file_type().is_symlink()
+        {
+            // issue6456: Size returned may be longer due to encryption
+            // on EXT-4 fscrypt. TODO maybe only do it on EXT4?
+            self.outcome.unsure.push(full_path)
+        } else if dirstate_node.copy_source.is_some()
+            || entry.is_from_other_parent()
+            || (entry.size >= 0 && (size_changed || mode_changed()))
+        {
+            self.outcome.modified.push(full_path)
+        } else {
+            let mtime = mtime_seconds(&fs_entry.metadata);
+            if truncate_i64(mtime) != entry.mtime
+                || mtime == self.options.last_normal_time
+            {
+                self.outcome.unsure.push(full_path)
+            } else if self.options.list_clean {
+                self.outcome.clean.push(full_path)
+            }
+        }
+    }
+
+    /// A node in the dirstate tree has no corresponding filesystem entry
+    fn traverse_dirstate_only(
+        &mut self,
+        hg_path: &'tree HgPath,
+        dirstate_node: &'tree mut Node,
+    ) {
+        self.mark_removed_or_deleted_if_file(hg_path, dirstate_node.state());
+        for (child_hg_path, child_node) in &mut dirstate_node.children {
+            self.traverse_dirstate_only(child_hg_path.full_path(), child_node)
+        }
+    }
+
+    /// A node in the dirstate tree has no corresponding *file* on the
+    /// filesystem
+    ///
+    /// Does nothing on a "directory" node
+    fn mark_removed_or_deleted_if_file(
+        &mut self,
+        hg_path: &'tree HgPath,
+        dirstate_node_state: Option<EntryState>,
+    ) {
+        if let Some(state) = dirstate_node_state {
+            if self.matcher.matches(hg_path) {
+                if let EntryState::Removed = state {
+                    self.outcome.removed.push(hg_path.into())
+                } else {
+                    self.outcome.deleted.push(hg_path.into())
+                }
+            }
+        }
+    }
+
+    /// Something in the filesystem has no corresponding dirstate node
+    fn traverse_fs_only(
+        &mut self,
+        has_ignored_ancestor: bool,
+        directory_hg_path: &HgPath,
+        fs_entry: &DirEntry,
+    ) {
+        let hg_path = directory_hg_path.join(&fs_entry.base_name);
+        if fs_entry.metadata.is_dir() {
+            let is_ignored =
+                has_ignored_ancestor || (self.ignore_fn)(&hg_path);
+            let traverse_children = if is_ignored {
+                // Descendants of an ignored directory are all ignored
+                self.options.list_ignored
+            } else {
+                // Descendants of an unknown directory may be either unknown or
+                // ignored
+                self.options.list_unknown || self.options.list_ignored
+            };
+            if traverse_children {
+                let is_at_repo_root = false;
+                // TODO: handle I/O errors
+                let children_fs_entries =
+                    DirEntry::read_dir(&fs_entry.full_path, is_at_repo_root)
+                        .unwrap();
+                for child_fs_entry in children_fs_entries {
+                    self.traverse_fs_only(
+                        is_ignored,
+                        &hg_path,
+                        &child_fs_entry,
+                    )
+                }
+            }
+            if self.options.collect_traversed_dirs {
+                self.outcome.traversed.push(hg_path.into())
+            }
+        } else if self.matcher.matches(&hg_path) {
+            self.mark_unknown_or_ignored(has_ignored_ancestor, hg_path.into())
+        }
+    }
+
+    fn mark_unknown_or_ignored(
+        &mut self,
+        has_ignored_ancestor: bool,
+        hg_path: Cow<'tree, HgPath>,
+    ) {
+        let is_ignored = has_ignored_ancestor || (self.ignore_fn)(&hg_path);
+        if is_ignored {
+            if self.options.list_ignored {
+                self.outcome.ignored.push(hg_path)
+            }
+        } else {
+            if self.options.list_unknown {
+                self.outcome.unknown.push(hg_path)
+            }
+        }
+    }
+}
+
+#[cfg(unix)] // TODO
+fn mtime_seconds(metadata: &std::fs::Metadata) -> i64 {
+    // Going through `Metadata::modified()` would be portable, but would take
+    // care to construct a `SystemTime` value with sub-second precision just
+    // for us to throw that away here.
+    use std::os::unix::fs::MetadataExt;
+    metadata.mtime()
+}
+
+struct DirEntry {
+    base_name: HgPathBuf,
+    full_path: PathBuf,
+    metadata: std::fs::Metadata,
+}
+
+impl DirEntry {
+    /// Returns **unsorted** entries in the given directory, with name and
+    /// metadata.
+    ///
+    /// If a `.hg` sub-directory is encountered:
+    ///
+    /// * At the repository root, ignore that sub-directory
+    /// * Elsewhere, we’re listing the content of a sub-repo. Return an empty
+    ///   list instead.
+    fn read_dir(path: &Path, is_at_repo_root: bool) -> io::Result<Vec<Self>> {
+        let mut results = Vec::new();
+        for entry in path.read_dir()? {
+            let entry = entry?;
+            let metadata = entry.metadata()?;
+            let name = get_bytes_from_os_string(entry.file_name());
+            // FIXME don't do this when cached
+            if name == b".hg" {
+                if is_at_repo_root {
+                    // Skip the repo’s own .hg (might be a symlink)
+                    continue;
+                } else if metadata.is_dir() {
+                    // A .hg sub-directory at another location means a subrepo,
+                    // skip it entirely.
+                    return Ok(Vec::new());
+                }
+            }
+            results.push(DirEntry {
+                base_name: name.into(),
+                full_path: entry.path(),
+                metadata,
+            })
+        }
+        Ok(results)
+    }
+}

rust/hg-core/src/utils/files.rs

@@ -1,463 +1,469 b''
 // files.rs
 //
 // Copyright 2019
 // Raphaël Gomès <[e-mail]>,
 // Yuya Nishihara <[e-mail]>
 //
 // This software may be used and distributed according to the terms of the
 // GNU General Public License version 2 or any later version.
 
 //! Functions for fiddling with files.
 
 use crate::utils::{
     hg_path::{path_to_hg_path_buf, HgPath, HgPathBuf, HgPathError},
     path_auditor::PathAuditor,
     replace_slice,
 };
 use lazy_static::lazy_static;
 use same_file::is_same_file;
 use std::borrow::{Cow, ToOwned};
-use std::ffi::OsStr;
+use std::ffi::{OsStr, OsString};
 use std::fs::Metadata;
 use std::iter::FusedIterator;
 use std::ops::Deref;
 use std::path::{Path, PathBuf};
 
 pub fn get_os_str_from_bytes(bytes: &[u8]) -> &OsStr {
     let os_str;
     #[cfg(unix)]
     {
         use std::os::unix::ffi::OsStrExt;
         os_str = std::ffi::OsStr::from_bytes(bytes);
     }
     // TODO Handle other platforms
     // TODO: convert from WTF8 to Windows MBCS (ANSI encoding).
     // Perhaps, the return type would have to be Result<PathBuf>.
     os_str
 }
 
 pub fn get_path_from_bytes(bytes: &[u8]) -> &Path {
     Path::new(get_os_str_from_bytes(bytes))
 }
 
 // TODO: need to convert from WTF8 to MBCS bytes on Windows.
 // that's why Vec<u8> is returned.
 #[cfg(unix)]
 pub fn get_bytes_from_path(path: impl AsRef<Path>) -> Vec<u8> {
     get_bytes_from_os_str(path.as_ref())
 }
 
 #[cfg(unix)]
 pub fn get_bytes_from_os_str(str: impl AsRef<OsStr>) -> Vec<u8> {
     use std::os::unix::ffi::OsStrExt;
     str.as_ref().as_bytes().to_vec()
 }
 
+#[cfg(unix)]
+pub fn get_bytes_from_os_string(str: OsString) -> Vec<u8> {
+    use std::os::unix::ffi::OsStringExt;
+    str.into_vec()
+}
+
 /// An iterator over repository path yielding itself and its ancestors.
 #[derive(Copy, Clone, Debug)]
 pub struct Ancestors<'a> {
     next: Option<&'a HgPath>,
 }
 
 impl<'a> Iterator for Ancestors<'a> {
     type Item = &'a HgPath;
 
     fn next(&mut self) -> Option<Self::Item> {
         let next = self.next;
         self.next = match self.next {
             Some(s) if s.is_empty() => None,
             Some(s) => {
                 let p = s.bytes().rposition(|c| *c == b'/').unwrap_or(0);
                 Some(HgPath::new(&s.as_bytes()[..p]))
             }
             None => None,
         };
         next
     }
 }
 
 impl<'a> FusedIterator for Ancestors<'a> {}
 
 /// An iterator over repository path yielding itself and its ancestors.
 #[derive(Copy, Clone, Debug)]
 pub(crate) struct AncestorsWithBase<'a> {
     next: Option<(&'a HgPath, &'a HgPath)>,
 }
 
 impl<'a> Iterator for AncestorsWithBase<'a> {
     type Item = (&'a HgPath, &'a HgPath);
 
     fn next(&mut self) -> Option<Self::Item> {
         let next = self.next;
         self.next = match self.next {
             Some((s, _)) if s.is_empty() => None,
             Some((s, _)) => Some(s.split_filename()),
             None => None,
         };
         next
     }
 }
 
 impl<'a> FusedIterator for AncestorsWithBase<'a> {}
 
 /// Returns an iterator yielding ancestor directories of the given repository
 /// path.
 ///
 /// The path is separated by '/', and must not start with '/'.
 ///
 /// The path itself isn't included unless it is b"" (meaning the root
 /// directory.)
 pub fn find_dirs(path: &HgPath) -> Ancestors {
     let mut dirs = Ancestors { next: Some(path) };
     if !path.is_empty() {
         dirs.next(); // skip itself
     }
     dirs
 }
 
 /// Returns an iterator yielding ancestor directories of the given repository
 /// path.
 ///
 /// The path is separated by '/', and must not start with '/'.
 ///
 /// The path itself isn't included unless it is b"" (meaning the root
 /// directory.)
 pub(crate) fn find_dirs_with_base(path: &HgPath) -> AncestorsWithBase {
     let mut dirs = AncestorsWithBase {
         next: Some((path, HgPath::new(b""))),
     };
     if !path.is_empty() {
         dirs.next(); // skip itself
     }
     dirs
 }
 
 /// TODO more than ASCII?
 pub fn normalize_case(path: &HgPath) -> HgPathBuf {
     #[cfg(windows)] // NTFS compares via upper()
     return path.to_ascii_uppercase();
     #[cfg(unix)]
     path.to_ascii_lowercase()
 }
 
 lazy_static! {
     static ref IGNORED_CHARS: Vec<Vec<u8>> = {
         [
             0x200c, 0x200d, 0x200e, 0x200f, 0x202a, 0x202b, 0x202c, 0x202d,
             0x202e, 0x206a, 0x206b, 0x206c, 0x206d, 0x206e, 0x206f, 0xfeff,
         ]
         .iter()
         .map(|code| {
             std::char::from_u32(*code)
                 .unwrap()
                 .encode_utf8(&mut [0; 3])
                 .bytes()
                 .collect()
         })
         .collect()
     };
 }
 
 fn hfs_ignore_clean(bytes: &[u8]) -> Vec<u8> {
     let mut buf = bytes.to_owned();
     let needs_escaping = bytes.iter().any(|b| *b == b'\xe2' || *b == b'\xef');
     if needs_escaping {
         for forbidden in IGNORED_CHARS.iter() {
             replace_slice(&mut buf, forbidden, &[])
         }
         buf
     } else {
         buf
     }
 }
 
 pub fn lower_clean(bytes: &[u8]) -> Vec<u8> {
     hfs_ignore_clean(&bytes.to_ascii_lowercase())
 }
 
 #[derive(Eq, PartialEq, Ord, PartialOrd, Copy, Clone)]
 pub struct HgMetadata {
     pub st_dev: u64,
     pub st_mode: u32,
     pub st_nlink: u64,
     pub st_size: u64,
     pub st_mtime: i64,
     pub st_ctime: i64,
 }
 
 // TODO support other plaforms
 #[cfg(unix)]
 impl HgMetadata {
     pub fn from_metadata(metadata: Metadata) -> Self {
         use std::os::unix::fs::MetadataExt;
         Self {
             st_dev: metadata.dev(),
             st_mode: metadata.mode(),
             st_nlink: metadata.nlink(),
             st_size: metadata.size(),
             st_mtime: metadata.mtime(),
             st_ctime: metadata.ctime(),
         }
     }
 
     pub fn is_symlink(&self) -> bool {
         // This is way too manual, but `HgMetadata` will go away in the
         // near-future dirstate rewrite anyway.
         self.st_mode & 0170000 == 0120000
     }
 }
 
 /// Returns the canonical path of `name`, given `cwd` and `root`
 pub fn canonical_path(
     root: impl AsRef<Path>,
     cwd: impl AsRef<Path>,
     name: impl AsRef<Path>,
 ) -> Result<PathBuf, HgPathError> {
     // TODO add missing normalization for other platforms
     let root = root.as_ref();
     let cwd = cwd.as_ref();
     let name = name.as_ref();
 
     let name = if !name.is_absolute() {
         root.join(&cwd).join(&name)
     } else {
         name.to_owned()
     };
     let auditor = PathAuditor::new(&root);
     if name != root && name.starts_with(&root) {
         let name = name.strip_prefix(&root).unwrap();
         auditor.audit_path(path_to_hg_path_buf(name)?)?;
         Ok(name.to_owned())
     } else if name == root {
         Ok("".into())
     } else {
         // Determine whether `name' is in the hierarchy at or beneath `root',
         // by iterating name=name.parent() until it returns `None` (can't
         // check name == '/', because that doesn't work on windows).
         let mut name = name.deref();
         let original_name = name.to_owned();
         loop {
             let same = is_same_file(&name, &root).unwrap_or(false);
             if same {
                 if name == original_name {
                     // `name` was actually the same as root (maybe a symlink)
                     return Ok("".into());
                 }
                 // `name` is a symlink to root, so `original_name` is under
                 // root
                 let rel_path = original_name.strip_prefix(&name).unwrap();
                 auditor.audit_path(path_to_hg_path_buf(&rel_path)?)?;
                 return Ok(rel_path.to_owned());
             }
             name = match name.parent() {
                 None => break,
                 Some(p) => p,
             };
         }
         // TODO hint to the user about using --cwd
         // Bubble up the responsibility to Python for now
         Err(HgPathError::NotUnderRoot {
             path: original_name.to_owned(),
             root: root.to_owned(),
         })
     }
 }
 
 /// Returns the representation of the path relative to the current working
 /// directory for display purposes.
 ///
 /// `cwd` is a `HgPath`, so it is considered relative to the root directory
 /// of the repository.
 ///
 /// # Examples
 ///
 /// ```
 /// use hg::utils::hg_path::HgPath;
 /// use hg::utils::files::relativize_path;
 /// use std::borrow::Cow;
 ///
 /// let file = HgPath::new(b"nested/file");
 /// let cwd = HgPath::new(b"");
 /// assert_eq!(relativize_path(file, cwd), Cow::Borrowed(b"nested/file"));
 ///
 /// let cwd = HgPath::new(b"nested");
 /// assert_eq!(relativize_path(file, cwd), Cow::Borrowed(b"file"));
 ///
 /// let cwd = HgPath::new(b"other");
 /// assert_eq!(relativize_path(file, cwd), Cow::Borrowed(b"../nested/file"));
 /// ```
 pub fn relativize_path(path: &HgPath, cwd: impl AsRef<HgPath>) -> Cow<[u8]> {
     if cwd.as_ref().is_empty() {
         Cow::Borrowed(path.as_bytes())
     } else {
         // This is not all accurate as to how large `res` will actually be, but
         // profiling `rhg files` on a large-ish repo shows it’s better than
         // starting from a zero-capacity `Vec` and letting `extend` reallocate
         // repeatedly.
         let guesstimate = path.as_bytes().len();
 
         let mut res: Vec<u8> = Vec::with_capacity(guesstimate);
         let mut path_iter = path.as_bytes().split(|b| *b == b'/').peekable();
         let mut cwd_iter =
             cwd.as_ref().as_bytes().split(|b| *b == b'/').peekable();
         loop {
             match (path_iter.peek(), cwd_iter.peek()) {
                 (Some(a), Some(b)) if a == b => (),
                 _ => break,
             }
             path_iter.next();
             cwd_iter.next();
         }
         let mut need_sep = false;
         for _ in cwd_iter {
             if need_sep {
                 res.extend(b"/")
             } else {
                 need_sep = true
             };
             res.extend(b"..");
         }
         for c in path_iter {
             if need_sep {
                 res.extend(b"/")
             } else {
                 need_sep = true
             };
             res.extend(c);
         }
         Cow::Owned(res)
     }
 }
 
 #[cfg(test)]
 mod tests {
     use super::*;
     use pretty_assertions::assert_eq;
 
     #[test]
     fn find_dirs_some() {
         let mut dirs = super::find_dirs(HgPath::new(b"foo/bar/baz"));
         assert_eq!(dirs.next(), Some(HgPath::new(b"foo/bar")));
         assert_eq!(dirs.next(), Some(HgPath::new(b"foo")));
         assert_eq!(dirs.next(), Some(HgPath::new(b"")));
         assert_eq!(dirs.next(), None);
         assert_eq!(dirs.next(), None);
     }
 
     #[test]
     fn find_dirs_empty() {
         // looks weird, but mercurial.pathutil.finddirs(b"") yields b""
         let mut dirs = super::find_dirs(HgPath::new(b""));
         assert_eq!(dirs.next(), Some(HgPath::new(b"")));
         assert_eq!(dirs.next(), None);
         assert_eq!(dirs.next(), None);
     }
 
     #[test]
     fn test_find_dirs_with_base_some() {
         let mut dirs = super::find_dirs_with_base(HgPath::new(b"foo/bar/baz"));
         assert_eq!(
             dirs.next(),
             Some((HgPath::new(b"foo/bar"), HgPath::new(b"baz")))
         );
         assert_eq!(
             dirs.next(),
             Some((HgPath::new(b"foo"), HgPath::new(b"bar")))
         );
         assert_eq!(dirs.next(), Some((HgPath::new(b""), HgPath::new(b"foo"))));
         assert_eq!(dirs.next(), None);
         assert_eq!(dirs.next(), None);
     }
 
     #[test]
     fn test_find_dirs_with_base_empty() {
         let mut dirs = super::find_dirs_with_base(HgPath::new(b""));
         assert_eq!(dirs.next(), Some((HgPath::new(b""), HgPath::new(b""))));
         assert_eq!(dirs.next(), None);
         assert_eq!(dirs.next(), None);
     }
 
     #[test]
     fn test_canonical_path() {
         let root = Path::new("/repo");
         let cwd = Path::new("/dir");
         let name = Path::new("filename");
         assert_eq!(
             canonical_path(root, cwd, name),
             Err(HgPathError::NotUnderRoot {
                 path: PathBuf::from("/dir/filename"),
                 root: root.to_path_buf()
             })
         );
 
         let root = Path::new("/repo");
         let cwd = Path::new("/");
         let name = Path::new("filename");
         assert_eq!(
             canonical_path(root, cwd, name),
             Err(HgPathError::NotUnderRoot {
                 path: PathBuf::from("/filename"),
                 root: root.to_path_buf()
             })
         );
 
         let root = Path::new("/repo");
         let cwd = Path::new("/");
         let name = Path::new("repo/filename");
         assert_eq!(
             canonical_path(root, cwd, name),
             Ok(PathBuf::from("filename"))
         );
 
         let root = Path::new("/repo");
         let cwd = Path::new("/repo");
         let name = Path::new("filename");
         assert_eq!(
             canonical_path(root, cwd, name),
             Ok(PathBuf::from("filename"))
         );
 
         let root = Path::new("/repo");
         let cwd = Path::new("/repo/subdir");
         let name = Path::new("filename");
         assert_eq!(
             canonical_path(root, cwd, name),
             Ok(PathBuf::from("subdir/filename"))
         );
     }
 
     #[test]
     fn test_canonical_path_not_rooted() {
         use std::fs::create_dir;
         use tempfile::tempdir;
 
         let base_dir = tempdir().unwrap();
         let base_dir_path = base_dir.path();
         let beneath_repo = base_dir_path.join("a");
         let root = base_dir_path.join("a/b");
         let out_of_repo = base_dir_path.join("c");
         let under_repo_symlink = out_of_repo.join("d");
 
         create_dir(&beneath_repo).unwrap();
         create_dir(&root).unwrap();
 
         // TODO make portable
         std::os::unix::fs::symlink(&root, &out_of_repo).unwrap();
 
         assert_eq!(
             canonical_path(&root, Path::new(""), out_of_repo),
             Ok(PathBuf::from(""))
         );
         assert_eq!(
             canonical_path(&root, Path::new(""), &beneath_repo),
             Err(HgPathError::NotUnderRoot {
                 path: beneath_repo.to_owned(),
                 root: root.to_owned()
             })
         );
         assert_eq!(
             canonical_path(&root, Path::new(""), &under_repo_symlink),
             Ok(PathBuf::from("d"))
         );
     }
 }

rust/hg-core/src/utils/hg_path.rs

@@ -1,785 +1,804 b''
 // hg_path.rs
 //
 // Copyright 2019 Raphaël Gomès <[e-mail]>
 //
 // This software may be used and distributed according to the terms of the
 // GNU General Public License version 2 or any later version.
 
 use std::borrow::Borrow;
+use std::borrow::Cow;
 use std::convert::TryFrom;
 use std::ffi::{OsStr, OsString};
 use std::fmt;
 use std::ops::Deref;
 use std::path::{Path, PathBuf};
 
 #[derive(Debug, Eq, PartialEq)]
 pub enum HgPathError {
     /// Bytes from the invalid `HgPath`
     LeadingSlash(Vec<u8>),
     ConsecutiveSlashes {
         bytes: Vec<u8>,
         second_slash_index: usize,
     },
     ContainsNullByte {
         bytes: Vec<u8>,
         null_byte_index: usize,
     },
     /// Bytes
     DecodeError(Vec<u8>),
     /// The rest come from audit errors
     EndsWithSlash(HgPathBuf),
     ContainsIllegalComponent(HgPathBuf),
     /// Path is inside the `.hg` folder
     InsideDotHg(HgPathBuf),
     IsInsideNestedRepo {
         path: HgPathBuf,
         nested_repo: HgPathBuf,
     },
     TraversesSymbolicLink {
         path: HgPathBuf,
         symlink: HgPathBuf,
     },
     NotFsCompliant(HgPathBuf),
     /// `path` is the smallest invalid path
     NotUnderRoot {
         path: PathBuf,
         root: PathBuf,
     },
 }
 
 impl fmt::Display for HgPathError {
     fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
         match self {
             HgPathError::LeadingSlash(bytes) => {
                 write!(f, "Invalid HgPath '{:?}': has a leading slash.", bytes)
             }
             HgPathError::ConsecutiveSlashes {
                 bytes,
                 second_slash_index: pos,
             } => write!(
                 f,
                 "Invalid HgPath '{:?}': consecutive slashes at pos {}.",
                 bytes, pos
             ),
             HgPathError::ContainsNullByte {
                 bytes,
                 null_byte_index: pos,
             } => write!(
                 f,
                 "Invalid HgPath '{:?}': contains null byte at pos {}.",
                 bytes, pos
             ),
             HgPathError::DecodeError(bytes) => write!(
                 f,
                 "Invalid HgPath '{:?}': could not be decoded.",
                 bytes
             ),
             HgPathError::EndsWithSlash(path) => {
                 write!(f, "Audit failed for '{}': ends with a slash.", path)
             }
             HgPathError::ContainsIllegalComponent(path) => write!(
                 f,
                 "Audit failed for '{}': contains an illegal component.",
                 path
             ),
             HgPathError::InsideDotHg(path) => write!(
                 f,
                 "Audit failed for '{}': is inside the '.hg' folder.",
                 path
             ),
             HgPathError::IsInsideNestedRepo {
                 path,
                 nested_repo: nested,
             } => {
                 write!(f,
                 "Audit failed for '{}': is inside a nested repository '{}'.",
                 path, nested
             )
             }
             HgPathError::TraversesSymbolicLink { path, symlink } => write!(
                 f,
                 "Audit failed for '{}': traverses symbolic link '{}'.",
                 path, symlink
             ),
             HgPathError::NotFsCompliant(path) => write!(
                 f,
                 "Audit failed for '{}': cannot be turned into a \
                  filesystem path.",
                 path
             ),
             HgPathError::NotUnderRoot { path, root } => write!(
                 f,
                 "Audit failed for '{}': not under root {}.",
                 path.display(),
                 root.display()
             ),
         }
     }
 }
 
 impl From<HgPathError> for std::io::Error {
     fn from(e: HgPathError) -> Self {
         std::io::Error::new(std::io::ErrorKind::InvalidData, e.to_string())
     }
 }
 
 /// This is a repository-relative path (or canonical path):
 ///     - no null characters
 ///     - `/` separates directories
 ///     - no consecutive slashes
 ///     - no leading slash,
 ///     - no `.` nor `..` of special meaning
 ///     - stored in repository and shared across platforms
 ///
 /// Note: there is no guarantee of any `HgPath` being well-formed at any point
 /// in its lifetime for performance reasons and to ease ergonomics. It is
 /// however checked using the `check_state` method before any file-system
 /// operation.
 ///
 /// This allows us to be encoding-transparent as much as possible, until really
 /// needed; `HgPath` can be transformed into a platform-specific path (`OsStr`
 /// or `Path`) whenever more complex operations are needed:
 /// On Unix, it's just byte-to-byte conversion. On Windows, it has to be
 /// decoded from MBCS to WTF-8. If WindowsUTF8Plan is implemented, the source
 /// character encoding will be determined on a per-repository basis.
 //
 // FIXME: (adapted from a comment in the stdlib)
 // `HgPath::new()` current implementation relies on `Slice` being
 // layout-compatible with `[u8]`.
 // When attribute privacy is implemented, `Slice` should be annotated as
 // `#[repr(transparent)]`.
 // Anyway, `Slice` representation and layout are considered implementation
 // detail, are not documented and must not be relied upon.
 #[derive(Eq, Ord, PartialEq, PartialOrd, Hash)]
 pub struct HgPath {
     inner: [u8],
 }
 
 impl HgPath {
     pub fn new<S: AsRef<[u8]> + ?Sized>(s: &S) -> &Self {
         unsafe { &*(s.as_ref() as *const [u8] as *const Self) }
     }
     pub fn is_empty(&self) -> bool {
         self.inner.is_empty()
     }
     pub fn len(&self) -> usize {
         self.inner.len()
     }
     fn to_hg_path_buf(&self) -> HgPathBuf {
         HgPathBuf {
             inner: self.inner.to_owned(),
         }
     }
     pub fn bytes(&self) -> std::slice::Iter<u8> {
         self.inner.iter()
     }
     pub fn to_ascii_uppercase(&self) -> HgPathBuf {
         HgPathBuf::from(self.inner.to_ascii_uppercase())
     }
     pub fn to_ascii_lowercase(&self) -> HgPathBuf {
         HgPathBuf::from(self.inner.to_ascii_lowercase())
     }
     pub fn as_bytes(&self) -> &[u8] {
         &self.inner
     }
     pub fn contains(&self, other: u8) -> bool {
         self.inner.contains(&other)
     }
     pub fn starts_with(&self, needle: impl AsRef<Self>) -> bool {
         self.inner.starts_with(needle.as_ref().as_bytes())
     }
     pub fn trim_trailing_slash(&self) -> &Self {
         Self::new(if self.inner.last() == Some(&b'/') {
             &self.inner[..self.inner.len() - 1]
         } else {
             &self.inner[..]
         })
     }
     /// Returns a tuple of slices `(base, filename)` resulting from the split
     /// at the rightmost `/`, if any.
     ///
     /// # Examples:
     ///
     /// ```
     /// use hg::utils::hg_path::HgPath;
     ///
     /// let path = HgPath::new(b"cool/hg/path").split_filename();
     /// assert_eq!(path, (HgPath::new(b"cool/hg"), HgPath::new(b"path")));
     ///
     /// let path = HgPath::new(b"pathwithoutsep").split_filename();
     /// assert_eq!(path, (HgPath::new(b""), HgPath::new(b"pathwithoutsep")));
     /// ```
     pub fn split_filename(&self) -> (&Self, &Self) {
         match &self.inner.iter().rposition(|c| *c == b'/') {
             None => (HgPath::new(""), &self),
             Some(size) => (
                 HgPath::new(&self.inner[..*size]),
                 HgPath::new(&self.inner[*size + 1..]),
             ),
         }
     }
     pub fn join<T: ?Sized + AsRef<Self>>(&self, other: &T) -> HgPathBuf {
         let mut inner = self.inner.to_owned();
         if !inner.is_empty() && inner.last() != Some(&b'/') {
             inner.push(b'/');
         }
         inner.extend(other.as_ref().bytes());
         HgPathBuf::from_bytes(&inner)
     }
 
     pub fn components(&self) -> impl Iterator<Item = &HgPath> {
         self.inner.split(|&byte| byte == b'/').map(HgPath::new)
     }
 
     pub fn parent(&self) -> &Self {
         let inner = self.as_bytes();
         HgPath::new(match inner.iter().rposition(|b| *b == b'/') {
             Some(pos) => &inner[..pos],
             None => &[],
         })
     }
     /// Given a base directory, returns the slice of `self` relative to the
     /// base directory. If `base` is not a directory (does not end with a
     /// `b'/'`), returns `None`.
     pub fn relative_to(&self, base: impl AsRef<Self>) -> Option<&Self> {
         let base = base.as_ref();
         if base.is_empty() {
             return Some(self);
         }
         let is_dir = base.as_bytes().ends_with(b"/");
         if is_dir && self.starts_with(base) {
             Some(Self::new(&self.inner[base.len()..]))
         } else {
             None
         }
     }
 
     #[cfg(windows)]
     /// Copied from the Python stdlib's `os.path.splitdrive` implementation.
     ///
     /// Split a pathname into drive/UNC sharepoint and relative path
     /// specifiers. Returns a 2-tuple (drive_or_unc, path); either part may
     /// be empty.
     ///
     /// If you assign
     ///  result = split_drive(p)
     /// It is always true that:
     ///  result[0] + result[1] == p
     ///
     /// If the path contained a drive letter, drive_or_unc will contain
     /// everything up to and including the colon.
     /// e.g. split_drive("c:/dir") returns ("c:", "/dir")
     ///
     /// If the path contained a UNC path, the drive_or_unc will contain the
     /// host name and share up to but not including the fourth directory
     /// separator character.
     /// e.g. split_drive("//host/computer/dir") returns ("//host/computer",
     /// "/dir")
     ///
     /// Paths cannot contain both a drive letter and a UNC path.
     pub fn split_drive<'a>(&self) -> (&HgPath, &HgPath) {
         let bytes = self.as_bytes();
         let is_sep = |b| std::path::is_separator(b as char);
 
         if self.len() < 2 {
             (HgPath::new(b""), &self)
         } else if is_sep(bytes[0])
             && is_sep(bytes[1])
             && (self.len() == 2 || !is_sep(bytes[2]))
         {
             // Is a UNC path:
             // vvvvvvvvvvvvvvvvvvvv drive letter or UNC path
             // \\machine\mountpoint\directory\etc\...
             //           directory ^^^^^^^^^^^^^^^
 
             let machine_end_index = bytes[2..].iter().position(|b| is_sep(*b));
             let mountpoint_start_index = if let Some(i) = machine_end_index {
                 i + 2
             } else {
                 return (HgPath::new(b""), &self);
             };
 
             match bytes[mountpoint_start_index + 1..]
                 .iter()
                 .position(|b| is_sep(*b))
             {
                 // A UNC path can't have two slashes in a row
                 // (after the initial two)
                 Some(0) => (HgPath::new(b""), &self),
                 Some(i) => {
                     let (a, b) =
                         bytes.split_at(mountpoint_start_index + 1 + i);
                     (HgPath::new(a), HgPath::new(b))
                 }
                 None => (&self, HgPath::new(b"")),
             }
         } else if bytes[1] == b':' {
             // Drive path c:\directory
             let (a, b) = bytes.split_at(2);
             (HgPath::new(a), HgPath::new(b))
         } else {
             (HgPath::new(b""), &self)
         }
     }
 
     #[cfg(unix)]
     /// Split a pathname into drive and path. On Posix, drive is always empty.
     pub fn split_drive(&self) -> (&HgPath, &HgPath) {
         (HgPath::new(b""), &self)
     }
 
     /// Checks for errors in the path, short-circuiting at the first one.
     /// This generates fine-grained errors useful for debugging.
     /// To simply check if the path is valid during tests, use `is_valid`.
     pub fn check_state(&self) -> Result<(), HgPathError> {
         if self.is_empty() {
             return Ok(());
         }
         let bytes = self.as_bytes();
         let mut previous_byte = None;
 
         if bytes[0] == b'/' {
             return Err(HgPathError::LeadingSlash(bytes.to_vec()));
         }
         for (index, byte) in bytes.iter().enumerate() {
             match byte {
                 0 => {
                     return Err(HgPathError::ContainsNullByte {
                         bytes: bytes.to_vec(),
                         null_byte_index: index,
                     })
                 }
                 b'/' => {
                     if previous_byte.is_some() && previous_byte == Some(b'/') {
                         return Err(HgPathError::ConsecutiveSlashes {
                             bytes: bytes.to_vec(),
                             second_slash_index: index,
                         });
                     }
                 }
                 _ => (),
             };
             previous_byte = Some(*byte);
         }
         Ok(())
     }
 
     #[cfg(test)]
     /// Only usable during tests to force developers to handle invalid states
     fn is_valid(&self) -> bool {
         self.check_state().is_ok()
     }
 }
 
 impl fmt::Debug for HgPath {
     fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
         write!(f, "HgPath({:?})", String::from_utf8_lossy(&self.inner))
     }
 }
 
 impl fmt::Display for HgPath {
     fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
         write!(f, "{}", String::from_utf8_lossy(&self.inner))
     }
 }
 
 #[derive(
     Default, Eq, Ord, Clone, PartialEq, PartialOrd, Hash, derive_more::From,
 )]
 pub struct HgPathBuf {
     inner: Vec<u8>,
 }
 
 impl HgPathBuf {
     pub fn new() -> Self {
         Default::default()
     }
     pub fn push(&mut self, byte: u8) {
         self.inner.push(byte);
     }
     pub fn from_bytes(s: &[u8]) -> HgPathBuf {
         HgPath::new(s).to_owned()
     }
     pub fn into_vec(self) -> Vec<u8> {
         self.inner
     }
 }
 
 impl fmt::Debug for HgPathBuf {
     fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
         write!(f, "HgPathBuf({:?})", String::from_utf8_lossy(&self.inner))
     }
 }
 
 impl fmt::Display for HgPathBuf {
     fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
         write!(f, "{}", String::from_utf8_lossy(&self.inner))
     }
 }
 
 impl Deref for HgPathBuf {
     type Target = HgPath;
 
     #[inline]
     fn deref(&self) -> &HgPath {
         &HgPath::new(&self.inner)
     }
 }
 
 impl<T: ?Sized + AsRef<HgPath>> From<&T> for HgPathBuf {
     fn from(s: &T) -> HgPathBuf {
         s.as_ref().to_owned()
     }
 }
 
 impl Into<Vec<u8>> for HgPathBuf {
     fn into(self) -> Vec<u8> {
         self.inner
     }
 }
 
 impl Borrow<HgPath> for HgPathBuf {
     fn borrow(&self) -> &HgPath {
         &HgPath::new(self.as_bytes())
     }
 }
 
 impl ToOwned for HgPath {
     type Owned = HgPathBuf;
 
     fn to_owned(&self) -> HgPathBuf {
         self.to_hg_path_buf()
     }
 }
 
 impl AsRef<HgPath> for HgPath {
     fn as_ref(&self) -> &HgPath {
         self
     }
 }
 
 impl AsRef<HgPath> for HgPathBuf {
     fn as_ref(&self) -> &HgPath {
         self
     }
 }
 
 impl Extend<u8> for HgPathBuf {
     fn extend<T: IntoIterator<Item = u8>>(&mut self, iter: T) {
         self.inner.extend(iter);
     }
 }
 
 /// TODO: Once https://www.mercurial-scm.org/wiki/WindowsUTF8Plan is
 /// implemented, these conversion utils will have to work differently depending
 /// on the repository encoding: either `UTF-8` or `MBCS`.
 
 pub fn hg_path_to_os_string<P: AsRef<HgPath>>(
     hg_path: P,
 ) -> Result<OsString, HgPathError> {
     hg_path.as_ref().check_state()?;
     let os_str;
     #[cfg(unix)]
     {
         use std::os::unix::ffi::OsStrExt;
         os_str = std::ffi::OsStr::from_bytes(&hg_path.as_ref().as_bytes());
     }
     // TODO Handle other platforms
     // TODO: convert from WTF8 to Windows MBCS (ANSI encoding).
     Ok(os_str.to_os_string())
 }
 
 pub fn hg_path_to_path_buf<P: AsRef<HgPath>>(
     hg_path: P,
 ) -> Result<PathBuf, HgPathError> {
     Ok(Path::new(&hg_path_to_os_string(hg_path)?).to_path_buf())
 }
 
 pub fn os_string_to_hg_path_buf<S: AsRef<OsStr>>(
     os_string: S,
 ) -> Result<HgPathBuf, HgPathError> {
     let buf;
     #[cfg(unix)]
     {
         use std::os::unix::ffi::OsStrExt;
         buf = HgPathBuf::from_bytes(&os_string.as_ref().as_bytes());
     }
     // TODO Handle other platforms
     // TODO: convert from WTF8 to Windows MBCS (ANSI encoding).
 
     buf.check_state()?;
     Ok(buf)
 }
 
 pub fn path_to_hg_path_buf<P: AsRef<Path>>(
     path: P,
 ) -> Result<HgPathBuf, HgPathError> {
     let buf;
     let os_str = path.as_ref().as_os_str();
     #[cfg(unix)]
     {
         use std::os::unix::ffi::OsStrExt;
         buf = HgPathBuf::from_bytes(&os_str.as_bytes());
     }
     // TODO Handle other platforms
     // TODO: convert from WTF8 to Windows MBCS (ANSI encoding).
 
     buf.check_state()?;
     Ok(buf)
 }
 
 impl TryFrom<PathBuf> for HgPathBuf {
     type Error = HgPathError;
     fn try_from(path: PathBuf) -> Result<Self, Self::Error> {
         path_to_hg_path_buf(path)
     }
 }
 
+impl From<HgPathBuf> for Cow<'_, HgPath> {
+    fn from(path: HgPathBuf) -> Self {
+        Cow::Owned(path)
+    }
+}
+
+impl<'a> From<&'a HgPath> for Cow<'a, HgPath> {
+    fn from(path: &'a HgPath) -> Self {
+        Cow::Borrowed(path)
+    }
+}
+
+impl<'a> From<&'a HgPathBuf> for Cow<'a, HgPath> {
+    fn from(path: &'a HgPathBuf) -> Self {
+        Cow::Borrowed(&**path)
+    }
+}
+
 #[cfg(test)]
 mod tests {
     use super::*;
     use pretty_assertions::assert_eq;
 
     #[test]
     fn test_path_states() {
         assert_eq!(
             Err(HgPathError::LeadingSlash(b"/".to_vec())),
             HgPath::new(b"/").check_state()
         );
         assert_eq!(
             Err(HgPathError::ConsecutiveSlashes {
                 bytes: b"a/b//c".to_vec(),
                 second_slash_index: 4
             }),
             HgPath::new(b"a/b//c").check_state()
         );
         assert_eq!(
             Err(HgPathError::ContainsNullByte {
                 bytes: b"a/b/\0c".to_vec(),
                 null_byte_index: 4
             }),
             HgPath::new(b"a/b/\0c").check_state()
         );
         // TODO test HgPathError::DecodeError for the Windows implementation.
         assert_eq!(true, HgPath::new(b"").is_valid());
         assert_eq!(true, HgPath::new(b"a/b/c").is_valid());
         // Backslashes in paths are not significant, but allowed
         assert_eq!(true, HgPath::new(br"a\b/c").is_valid());
         // Dots in paths are not significant, but allowed
         assert_eq!(true, HgPath::new(b"a/b/../c/").is_valid());
         assert_eq!(true, HgPath::new(b"./a/b/../c/").is_valid());
     }
 
     #[test]
     fn test_iter() {
         let path = HgPath::new(b"a");
         let mut iter = path.bytes();
         assert_eq!(Some(&b'a'), iter.next());
         assert_eq!(None, iter.next_back());
         assert_eq!(None, iter.next());
 
         let path = HgPath::new(b"a");
         let mut iter = path.bytes();
         assert_eq!(Some(&b'a'), iter.next_back());
         assert_eq!(None, iter.next_back());
         assert_eq!(None, iter.next());
 
         let path = HgPath::new(b"abc");
         let mut iter = path.bytes();
         assert_eq!(Some(&b'a'), iter.next());
         assert_eq!(Some(&b'c'), iter.next_back());
         assert_eq!(Some(&b'b'), iter.next_back());
         assert_eq!(None, iter.next_back());
         assert_eq!(None, iter.next());
 
         let path = HgPath::new(b"abc");
         let mut iter = path.bytes();
         assert_eq!(Some(&b'a'), iter.next());
         assert_eq!(Some(&b'b'), iter.next());
         assert_eq!(Some(&b'c'), iter.next());
         assert_eq!(None, iter.next_back());
         assert_eq!(None, iter.next());
 
         let path = HgPath::new(b"abc");
         let iter = path.bytes();
         let mut vec = Vec::new();
         vec.extend(iter);
         assert_eq!(vec![b'a', b'b', b'c'], vec);
 
         let path = HgPath::new(b"abc");
         let mut iter = path.bytes();
         assert_eq!(Some(2), iter.rposition(|c| *c == b'c'));
 
         let path = HgPath::new(b"abc");
         let mut iter = path.bytes();
         assert_eq!(None, iter.rposition(|c| *c == b'd'));
     }
 
     #[test]
     fn test_join() {
         let path = HgPathBuf::from_bytes(b"a").join(HgPath::new(b"b"));
         assert_eq!(b"a/b", path.as_bytes());
 
         let path = HgPathBuf::from_bytes(b"a/").join(HgPath::new(b"b/c"));
         assert_eq!(b"a/b/c", path.as_bytes());
 
         // No leading slash if empty before join
         let path = HgPathBuf::new().join(HgPath::new(b"b/c"));
         assert_eq!(b"b/c", path.as_bytes());
 
         // The leading slash is an invalid representation of an `HgPath`, but
         // it can happen. This creates another invalid representation of
         // consecutive bytes.
         // TODO What should be done in this case? Should we silently remove
         // the extra slash? Should we change the signature to a problematic
         // `Result<HgPathBuf, HgPathError>`, or should we just keep it so and
         // let the error happen upon filesystem interaction?
         let path = HgPathBuf::from_bytes(b"a/").join(HgPath::new(b"/b"));
         assert_eq!(b"a//b", path.as_bytes());
         let path = HgPathBuf::from_bytes(b"a").join(HgPath::new(b"/b"));
         assert_eq!(b"a//b", path.as_bytes());
     }
 
     #[test]
     fn test_relative_to() {
         let path = HgPath::new(b"");
         let base = HgPath::new(b"");
         assert_eq!(Some(path), path.relative_to(base));
 
         let path = HgPath::new(b"path");
         let base = HgPath::new(b"");
         assert_eq!(Some(path), path.relative_to(base));
 
         let path = HgPath::new(b"a");
         let base = HgPath::new(b"b");
         assert_eq!(None, path.relative_to(base));
 
         let path = HgPath::new(b"a/b");
         let base = HgPath::new(b"a");
         assert_eq!(None, path.relative_to(base));
 
         let path = HgPath::new(b"a/b");
         let base = HgPath::new(b"a/");
         assert_eq!(Some(HgPath::new(b"b")), path.relative_to(base));
 
         let path = HgPath::new(b"nested/path/to/b");
         let base = HgPath::new(b"nested/path/");
         assert_eq!(Some(HgPath::new(b"to/b")), path.relative_to(base));
 
         let path = HgPath::new(b"ends/with/dir/");
         let base = HgPath::new(b"ends/");
         assert_eq!(Some(HgPath::new(b"with/dir/")), path.relative_to(base));
     }
 
     #[test]
     #[cfg(unix)]
     fn test_split_drive() {
         // Taken from the Python stdlib's tests
         assert_eq!(
             HgPath::new(br"/foo/bar").split_drive(),
             (HgPath::new(b""), HgPath::new(br"/foo/bar"))
         );
         assert_eq!(
             HgPath::new(br"foo:bar").split_drive(),
             (HgPath::new(b""), HgPath::new(br"foo:bar"))
         );
         assert_eq!(
             HgPath::new(br":foo:bar").split_drive(),
             (HgPath::new(b""), HgPath::new(br":foo:bar"))
         );
         // Also try NT paths; should not split them
         assert_eq!(
             HgPath::new(br"c:\foo\bar").split_drive(),
             (HgPath::new(b""), HgPath::new(br"c:\foo\bar"))
         );
         assert_eq!(
             HgPath::new(b"c:/foo/bar").split_drive(),
             (HgPath::new(b""), HgPath::new(br"c:/foo/bar"))
         );
         assert_eq!(
             HgPath::new(br"\\conky\mountpoint\foo\bar").split_drive(),
             (
                 HgPath::new(b""),
                 HgPath::new(br"\\conky\mountpoint\foo\bar")
             )
         );
     }
 
     #[test]
     #[cfg(windows)]
     fn test_split_drive() {
         assert_eq!(
             HgPath::new(br"c:\foo\bar").split_drive(),
             (HgPath::new(br"c:"), HgPath::new(br"\foo\bar"))
         );
         assert_eq!(
             HgPath::new(b"c:/foo/bar").split_drive(),
             (HgPath::new(br"c:"), HgPath::new(br"/foo/bar"))
         );
         assert_eq!(
             HgPath::new(br"\\conky\mountpoint\foo\bar").split_drive(),
             (
                 HgPath::new(br"\\conky\mountpoint"),
                 HgPath::new(br"\foo\bar")
             )
         );
         assert_eq!(
             HgPath::new(br"//conky/mountpoint/foo/bar").split_drive(),
             (
                 HgPath::new(br"//conky/mountpoint"),
                 HgPath::new(br"/foo/bar")
             )
         );
         assert_eq!(
             HgPath::new(br"\\\conky\mountpoint\foo\bar").split_drive(),
             (
                 HgPath::new(br""),
                 HgPath::new(br"\\\conky\mountpoint\foo\bar")
             )
         );
         assert_eq!(
             HgPath::new(br"///conky/mountpoint/foo/bar").split_drive(),
             (
                 HgPath::new(br""),
                 HgPath::new(br"///conky/mountpoint/foo/bar")
             )
         );
         assert_eq!(
             HgPath::new(br"\\conky\\mountpoint\foo\bar").split_drive(),
             (
                 HgPath::new(br""),
                 HgPath::new(br"\\conky\\mountpoint\foo\bar")
             )
         );
         assert_eq!(
             HgPath::new(br"//conky//mountpoint/foo/bar").split_drive(),
             (
                 HgPath::new(br""),
                 HgPath::new(br"//conky//mountpoint/foo/bar")
             )
         );
         // UNC part containing U+0130
         assert_eq!(
             HgPath::new(b"//conky/MOUNTPO\xc4\xb0NT/foo/bar").split_drive(),
             (
                 HgPath::new(b"//conky/MOUNTPO\xc4\xb0NT"),
                 HgPath::new(br"/foo/bar")
             )
         );
     }
 
     #[test]
     fn test_parent() {
         let path = HgPath::new(b"");
         assert_eq!(path.parent(), path);
 
         let path = HgPath::new(b"a");
         assert_eq!(path.parent(), HgPath::new(b""));
 
         let path = HgPath::new(b"a/b");
         assert_eq!(path.parent(), HgPath::new(b"a"));
 
         let path = HgPath::new(b"a/other/b");
         assert_eq!(path.parent(), HgPath::new(b"a/other"));
     }
 }