1
0
mirror of https://github.com/BurntSushi/ripgrep.git synced 2024-12-12 19:18:24 +02:00
ripgrep/Cargo.lock
Andrew Gallant 8bbe58d623 Add support for additional text encodings.
This includes, but is not limited to, UTF-16, latin-1, GBK, EUC-JP and
Shift_JIS. (Courtesy of the `encoding_rs` crate.)

Specifically, this feature enables ripgrep to search files that are
encoded in an encoding other than UTF-8. The list of available encodings
is tied directly to what the `encoding_rs` crate supports, which is in
turn tied to the Encoding Standard. The full list of available encodings
can be found here: https://encoding.spec.whatwg.org/#concept-encoding-get

This pull request also introduces the notion that text encodings can be
automatically detected on a best effort basis. Currently, the only
support for this is checking for a UTF-16 bom. In all other cases, a
text encoding of `auto` (the default) implies a UTF-8 or ASCII
compatible source encoding. When a text encoding is otherwise specified,
it is unconditionally used for all files searched.

Since ripgrep's regex engine is fundamentally built on top of UTF-8,
this feature works by transcoding the files to be searched from their
source encoding to UTF-8. This transcoding only happens when:

1. `auto` is specified and a non-UTF-8 encoding is detected.
2. A specific encoding is given by end users (including UTF-8).

When transcoding occurs, errors are handled by automatically inserting
the Unicode replacement character. In this case, ripgrep's output is
guaranteed to be valid UTF-8 (excluding non-UTF-8 file paths, if they
are printed).

In all other cases, the source text is searched directly, which implies
an assumption that it is at least ASCII compatible, but where UTF-8 is
most useful. In this scenario, encoding errors are not detected. In this
case, ripgrep's output will match the input exactly, byte-for-byte.

This design may not be optimal in all cases, but it has some advantages:

1. In the happy path ("UTF-8 everywhere") remains happy. I have not been
   able to witness any performance regressions.
2. In the non-UTF-8 path, implementation complexity is kept relatively
   low. The cost here is transcoding itself. A potentially superior
   implementation might build decoding of any encoding into the regex
   engine itself. In particular, the fundamental problem with
   transcoding everything first is that literal optimizations are nearly
   negated.

Future work should entail improving the user experience. For example, we
might want to auto-detect more text encodings. A more elaborate UX
experience might permit end users to specify multiple text encodings,
although this seems hard to pull off in an ergonomic way.

Fixes #1
2017-03-12 19:54:48 -04:00

371 lines
16 KiB
TOML

[root]
name = "ripgrep"
version = "0.4.0"
dependencies = [
"atty 0.2.2 (registry+https://github.com/rust-lang/crates.io-index)",
"bytecount 0.1.6 (registry+https://github.com/rust-lang/crates.io-index)",
"clap 2.20.5 (registry+https://github.com/rust-lang/crates.io-index)",
"encoding_rs 0.5.0 (registry+https://github.com/rust-lang/crates.io-index)",
"env_logger 0.4.2 (registry+https://github.com/rust-lang/crates.io-index)",
"grep 0.1.5",
"ignore 0.1.7",
"lazy_static 0.2.4 (registry+https://github.com/rust-lang/crates.io-index)",
"libc 0.2.21 (registry+https://github.com/rust-lang/crates.io-index)",
"log 0.3.7 (registry+https://github.com/rust-lang/crates.io-index)",
"memchr 1.0.1 (registry+https://github.com/rust-lang/crates.io-index)",
"memmap 0.5.2 (registry+https://github.com/rust-lang/crates.io-index)",
"num_cpus 1.3.0 (registry+https://github.com/rust-lang/crates.io-index)",
"regex 0.2.1 (registry+https://github.com/rust-lang/crates.io-index)",
"same-file 0.1.3 (registry+https://github.com/rust-lang/crates.io-index)",
"termcolor 0.3.0",
]
[[package]]
name = "aho-corasick"
version = "0.6.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"memchr 1.0.1 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "ansi_term"
version = "0.9.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
[[package]]
name = "atty"
version = "0.2.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"kernel32-sys 0.2.2 (registry+https://github.com/rust-lang/crates.io-index)",
"libc 0.2.21 (registry+https://github.com/rust-lang/crates.io-index)",
"winapi 0.2.8 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "bitflags"
version = "0.7.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
[[package]]
name = "bytecount"
version = "0.1.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"simd 0.1.1 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "cfg-if"
version = "0.1.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
[[package]]
name = "clap"
version = "2.20.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"ansi_term 0.9.0 (registry+https://github.com/rust-lang/crates.io-index)",
"bitflags 0.7.0 (registry+https://github.com/rust-lang/crates.io-index)",
"libc 0.2.21 (registry+https://github.com/rust-lang/crates.io-index)",
"strsim 0.6.0 (registry+https://github.com/rust-lang/crates.io-index)",
"term_size 0.2.3 (registry+https://github.com/rust-lang/crates.io-index)",
"unicode-segmentation 1.1.0 (registry+https://github.com/rust-lang/crates.io-index)",
"unicode-width 0.1.4 (registry+https://github.com/rust-lang/crates.io-index)",
"vec_map 0.6.0 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "crossbeam"
version = "0.2.10"
source = "registry+https://github.com/rust-lang/crates.io-index"
[[package]]
name = "encoding_rs"
version = "0.5.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"cfg-if 0.1.0 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "env_logger"
version = "0.4.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"log 0.3.7 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "fnv"
version = "1.0.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
[[package]]
name = "fs2"
version = "0.4.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"kernel32-sys 0.2.2 (registry+https://github.com/rust-lang/crates.io-index)",
"libc 0.2.21 (registry+https://github.com/rust-lang/crates.io-index)",
"winapi 0.2.8 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "globset"
version = "0.1.3"
dependencies = [
"aho-corasick 0.6.2 (registry+https://github.com/rust-lang/crates.io-index)",
"fnv 1.0.5 (registry+https://github.com/rust-lang/crates.io-index)",
"log 0.3.7 (registry+https://github.com/rust-lang/crates.io-index)",
"memchr 1.0.1 (registry+https://github.com/rust-lang/crates.io-index)",
"regex 0.2.1 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "grep"
version = "0.1.5"
dependencies = [
"log 0.3.7 (registry+https://github.com/rust-lang/crates.io-index)",
"memchr 1.0.1 (registry+https://github.com/rust-lang/crates.io-index)",
"regex 0.2.1 (registry+https://github.com/rust-lang/crates.io-index)",
"regex-syntax 0.4.0 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "ignore"
version = "0.1.7"
dependencies = [
"crossbeam 0.2.10 (registry+https://github.com/rust-lang/crates.io-index)",
"globset 0.1.3",
"lazy_static 0.2.4 (registry+https://github.com/rust-lang/crates.io-index)",
"log 0.3.7 (registry+https://github.com/rust-lang/crates.io-index)",
"memchr 1.0.1 (registry+https://github.com/rust-lang/crates.io-index)",
"regex 0.2.1 (registry+https://github.com/rust-lang/crates.io-index)",
"thread_local 0.3.3 (registry+https://github.com/rust-lang/crates.io-index)",
"walkdir 1.0.7 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "kernel32-sys"
version = "0.2.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"winapi 0.2.8 (registry+https://github.com/rust-lang/crates.io-index)",
"winapi-build 0.1.1 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "lazy_static"
version = "0.2.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
[[package]]
name = "libc"
version = "0.2.21"
source = "registry+https://github.com/rust-lang/crates.io-index"
[[package]]
name = "log"
version = "0.3.7"
source = "registry+https://github.com/rust-lang/crates.io-index"
[[package]]
name = "memchr"
version = "1.0.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"libc 0.2.21 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "memmap"
version = "0.5.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"fs2 0.4.1 (registry+https://github.com/rust-lang/crates.io-index)",
"kernel32-sys 0.2.2 (registry+https://github.com/rust-lang/crates.io-index)",
"libc 0.2.21 (registry+https://github.com/rust-lang/crates.io-index)",
"winapi 0.2.8 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "num_cpus"
version = "1.3.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"libc 0.2.21 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "regex"
version = "0.2.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"aho-corasick 0.6.2 (registry+https://github.com/rust-lang/crates.io-index)",
"memchr 1.0.1 (registry+https://github.com/rust-lang/crates.io-index)",
"regex-syntax 0.4.0 (registry+https://github.com/rust-lang/crates.io-index)",
"simd 0.1.1 (registry+https://github.com/rust-lang/crates.io-index)",
"thread_local 0.3.3 (registry+https://github.com/rust-lang/crates.io-index)",
"utf8-ranges 1.0.0 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "regex-syntax"
version = "0.4.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
[[package]]
name = "same-file"
version = "0.1.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"kernel32-sys 0.2.2 (registry+https://github.com/rust-lang/crates.io-index)",
"winapi 0.2.8 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "simd"
version = "0.1.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
[[package]]
name = "strsim"
version = "0.6.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
[[package]]
name = "term_size"
version = "0.2.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"kernel32-sys 0.2.2 (registry+https://github.com/rust-lang/crates.io-index)",
"libc 0.2.21 (registry+https://github.com/rust-lang/crates.io-index)",
"winapi 0.2.8 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "termcolor"
version = "0.3.0"
dependencies = [
"wincolor 0.1.2",
]
[[package]]
name = "thread-id"
version = "3.0.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"kernel32-sys 0.2.2 (registry+https://github.com/rust-lang/crates.io-index)",
"libc 0.2.21 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "thread_local"
version = "0.3.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"thread-id 3.0.0 (registry+https://github.com/rust-lang/crates.io-index)",
"unreachable 0.1.1 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "unicode-segmentation"
version = "1.1.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
[[package]]
name = "unicode-width"
version = "0.1.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
[[package]]
name = "unreachable"
version = "0.1.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"void 1.0.2 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "utf8-ranges"
version = "1.0.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
[[package]]
name = "vec_map"
version = "0.6.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
[[package]]
name = "void"
version = "1.0.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
[[package]]
name = "walkdir"
version = "1.0.7"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"kernel32-sys 0.2.2 (registry+https://github.com/rust-lang/crates.io-index)",
"same-file 0.1.3 (registry+https://github.com/rust-lang/crates.io-index)",
"winapi 0.2.8 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "winapi"
version = "0.2.8"
source = "registry+https://github.com/rust-lang/crates.io-index"
[[package]]
name = "winapi-build"
version = "0.1.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
[[package]]
name = "wincolor"
version = "0.1.2"
dependencies = [
"kernel32-sys 0.2.2 (registry+https://github.com/rust-lang/crates.io-index)",
"winapi 0.2.8 (registry+https://github.com/rust-lang/crates.io-index)",
]
[metadata]
"checksum aho-corasick 0.6.2 (registry+https://github.com/rust-lang/crates.io-index)" = "0638fd549427caa90c499814196d1b9e3725eb4d15d7339d6de073a680ed0ca2"
"checksum ansi_term 0.9.0 (registry+https://github.com/rust-lang/crates.io-index)" = "23ac7c30002a5accbf7e8987d0632fa6de155b7c3d39d0067317a391e00a2ef6"
"checksum atty 0.2.2 (registry+https://github.com/rust-lang/crates.io-index)" = "d912da0db7fa85514874458ca3651fe2cddace8d0b0505571dbdcd41ab490159"
"checksum bitflags 0.7.0 (registry+https://github.com/rust-lang/crates.io-index)" = "aad18937a628ec6abcd26d1489012cc0e18c21798210f491af69ded9b881106d"
"checksum bytecount 0.1.6 (registry+https://github.com/rust-lang/crates.io-index)" = "1e8f09fbc8c6726a4b616dcfbd4f54491068d6bb1b93ac03c78ac18ff9a5924a"
"checksum cfg-if 0.1.0 (registry+https://github.com/rust-lang/crates.io-index)" = "de1e760d7b6535af4241fca8bd8adf68e2e7edacc6b29f5d399050c5e48cf88c"
"checksum clap 2.20.5 (registry+https://github.com/rust-lang/crates.io-index)" = "7db281b0520e97fbd15cd615dcd8f8bcad0c26f5f7d5effe705f090f39e9a758"
"checksum crossbeam 0.2.10 (registry+https://github.com/rust-lang/crates.io-index)" = "0c5ea215664ca264da8a9d9c3be80d2eaf30923c259d03e870388eb927508f97"
"checksum encoding_rs 0.5.0 (registry+https://github.com/rust-lang/crates.io-index)" = "7a1cca0a26f904955d80d70b9bff1019e4f4cbc06f2fcbccf8bd3d889cc1c9b7"
"checksum env_logger 0.4.2 (registry+https://github.com/rust-lang/crates.io-index)" = "e3856f1697098606fc6cb97a93de88ca3f3bc35bb878c725920e6e82ecf05e83"
"checksum fnv 1.0.5 (registry+https://github.com/rust-lang/crates.io-index)" = "6cc484842f1e2884faf56f529f960cc12ad8c71ce96cc7abba0a067c98fee344"
"checksum fs2 0.4.1 (registry+https://github.com/rust-lang/crates.io-index)" = "34edaee07555859dc13ca387e6ae05686bb4d0364c95d649b6dab959511f4baf"
"checksum kernel32-sys 0.2.2 (registry+https://github.com/rust-lang/crates.io-index)" = "7507624b29483431c0ba2d82aece8ca6cdba9382bff4ddd0f7490560c056098d"
"checksum lazy_static 0.2.4 (registry+https://github.com/rust-lang/crates.io-index)" = "7291b1dd97d331f752620b02dfdbc231df7fc01bf282a00769e1cdb963c460dc"
"checksum libc 0.2.21 (registry+https://github.com/rust-lang/crates.io-index)" = "88ee81885f9f04bff991e306fea7c1c60a5f0f9e409e99f6b40e3311a3363135"
"checksum log 0.3.7 (registry+https://github.com/rust-lang/crates.io-index)" = "5141eca02775a762cc6cd564d8d2c50f67c0ea3a372cbf1c51592b3e029e10ad"
"checksum memchr 1.0.1 (registry+https://github.com/rust-lang/crates.io-index)" = "1dbccc0e46f1ea47b9f17e6d67c5a96bd27030519c519c9c91327e31275a47b4"
"checksum memmap 0.5.2 (registry+https://github.com/rust-lang/crates.io-index)" = "46f3c7359028b31999287dae4e5047ddfe90a23b7dca2282ce759b491080c99b"
"checksum num_cpus 1.3.0 (registry+https://github.com/rust-lang/crates.io-index)" = "a18c392466409c50b87369414a2680c93e739aedeb498eb2bff7d7eb569744e2"
"checksum regex 0.2.1 (registry+https://github.com/rust-lang/crates.io-index)" = "4278c17d0f6d62dfef0ab00028feb45bd7d2102843f80763474eeb1be8a10c01"
"checksum regex-syntax 0.4.0 (registry+https://github.com/rust-lang/crates.io-index)" = "2f9191b1f57603095f105d317e375d19b1c9c5c3185ea9633a99a6dcbed04457"
"checksum same-file 0.1.3 (registry+https://github.com/rust-lang/crates.io-index)" = "d931a44fdaa43b8637009e7632a02adc4f2b2e0733c08caa4cf00e8da4a117a7"
"checksum simd 0.1.1 (registry+https://github.com/rust-lang/crates.io-index)" = "63b5847c2d766ca7ce7227672850955802fabd779ba616aeabead4c2c3877023"
"checksum strsim 0.6.0 (registry+https://github.com/rust-lang/crates.io-index)" = "b4d15c810519a91cf877e7e36e63fe068815c678181439f2f29e2562147c3694"
"checksum term_size 0.2.3 (registry+https://github.com/rust-lang/crates.io-index)" = "07b6c1ac5b3fffd75073276bca1ceed01f67a28537097a2a9539e116e50fb21a"
"checksum thread-id 3.0.0 (registry+https://github.com/rust-lang/crates.io-index)" = "4437c97558c70d129e40629a5b385b3fb1ffac301e63941335e4d354081ec14a"
"checksum thread_local 0.3.3 (registry+https://github.com/rust-lang/crates.io-index)" = "c85048c6260d17cf486ceae3282d9fb6b90be220bf5b28c400f5485ffc29f0c7"
"checksum unicode-segmentation 1.1.0 (registry+https://github.com/rust-lang/crates.io-index)" = "18127285758f0e2c6cf325bb3f3d138a12fee27de4f23e146cd6a179f26c2cf3"
"checksum unicode-width 0.1.4 (registry+https://github.com/rust-lang/crates.io-index)" = "bf3a113775714a22dcb774d8ea3655c53a32debae63a063acc00a91cc586245f"
"checksum unreachable 0.1.1 (registry+https://github.com/rust-lang/crates.io-index)" = "1f2ae5ddb18e1c92664717616dd9549dde73f539f01bd7b77c2edb2446bdff91"
"checksum utf8-ranges 1.0.0 (registry+https://github.com/rust-lang/crates.io-index)" = "662fab6525a98beff2921d7f61a39e7d59e0b425ebc7d0d9e66d316e55124122"
"checksum vec_map 0.6.0 (registry+https://github.com/rust-lang/crates.io-index)" = "cac5efe5cb0fa14ec2f84f83c701c562ee63f6dcc680861b21d65c682adfb05f"
"checksum void 1.0.2 (registry+https://github.com/rust-lang/crates.io-index)" = "6a02e4885ed3bc0f2de90ea6dd45ebcbb66dacffe03547fadbb0eeae2770887d"
"checksum walkdir 1.0.7 (registry+https://github.com/rust-lang/crates.io-index)" = "bb08f9e670fab86099470b97cd2b252d6527f0b3cc1401acdb595ffc9dd288ff"
"checksum winapi 0.2.8 (registry+https://github.com/rust-lang/crates.io-index)" = "167dc9d6949a9b857f3451275e911c3f44255842c1f7a76f33c55103a909087a"
"checksum winapi-build 0.1.1 (registry+https://github.com/rust-lang/crates.io-index)" = "2d315eee3b34aca4797b2da6b13ed88266e6d612562a0c46390af8299fc699bc"