mirror of
https://github.com/rzmk/czv.git
synced 2025-12-19 00:09:24 +00:00
feat: add czv, czv-wasm, and czv-python (init release)
This commit is contained in:
rzmk
commit
9799ab694b
40 changed files with 70383 additions and 0 deletions
1
.github/FUNDING.yml
vendored
Normal file
1
.github/FUNDING.yml
vendored
Normal file
|
|
@ -0,0 +1 @@
|
|||
github: [rzmk]
|
||||
1
.gitignore
vendored
Normal file
1
.gitignore
vendored
Normal file
|
|
@ -0,0 +1 @@
|
|||
/target
|
||||
955
Cargo.lock
generated
Normal file
955
Cargo.lock
generated
Normal file
|
|
@ -0,0 +1,955 @@
|
|||
# This file is automatically @generated by Cargo.
|
||||
# It is not intended for manual editing.
|
||||
version = 3
|
||||
|
||||
[[package]]
|
||||
name = "aho-corasick"
|
||||
version = "1.1.3"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "8e60d3430d3a69478ad0993f19238d2df97c507009a52b3c10addcd7f6bcb916"
|
||||
dependencies = [
|
||||
"memchr",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "anes"
|
||||
version = "0.1.6"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "4b46cbb362ab8752921c97e041f5e366ee6297bd428a31275b9fcf1e380f7299"
|
||||
|
||||
[[package]]
|
||||
name = "anyhow"
|
||||
version = "1.0.86"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "b3d1d046238990b9cf5bcde22a3fb3584ee5cf65fb2765f454ed428c7a0063da"
|
||||
|
||||
[[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 = "1.3.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "0c4b4d0bd25bd0b74681c0ad21497610ce1b7c91b1022cd21c80c6fbdd9476b0"
|
||||
|
||||
[[package]]
|
||||
name = "bitflags"
|
||||
version = "1.3.2"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "bef38d45163c2f1dde094a7dfd33ccf595c92905c8f8f4fdc18d06fb1037718a"
|
||||
|
||||
[[package]]
|
||||
name = "bitflags"
|
||||
version = "2.5.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "cf4b9d6a944f767f8e5e0db018570623c85f3d925ac718db4e06d0187adb21c1"
|
||||
|
||||
[[package]]
|
||||
name = "bumpalo"
|
||||
version = "3.16.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "79296716171880943b8470b5f8d03aa55eb2e645a4874bdbb28adb49162e012c"
|
||||
|
||||
[[package]]
|
||||
name = "cast"
|
||||
version = "0.3.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "37b2a672a2cb129a2e41c10b1224bb368f9f37a2b16b612598138befd7b37eb5"
|
||||
|
||||
[[package]]
|
||||
name = "cfg-if"
|
||||
version = "1.0.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "baf1de4339761588bc0619e3cbc0120ee582ebb74b53b4efbf79117bd2da40fd"
|
||||
|
||||
[[package]]
|
||||
name = "ciborium"
|
||||
version = "0.2.2"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "42e69ffd6f0917f5c029256a24d0161db17cea3997d185db0d35926308770f0e"
|
||||
dependencies = [
|
||||
"ciborium-io",
|
||||
"ciborium-ll",
|
||||
"serde",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "ciborium-io"
|
||||
version = "0.2.2"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "05afea1e0a06c9be33d539b876f1ce3692f4afea2cb41f740e7743225ed1c757"
|
||||
|
||||
[[package]]
|
||||
name = "ciborium-ll"
|
||||
version = "0.2.2"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "57663b653d948a338bfb3eeba9bb2fd5fcfaecb9e199e87e1eda4d9e8b240fd9"
|
||||
dependencies = [
|
||||
"ciborium-io",
|
||||
"half",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "clap"
|
||||
version = "3.2.25"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "4ea181bf566f71cb9a5d17a59e1871af638180a18fb0035c92ae62b705207123"
|
||||
dependencies = [
|
||||
"bitflags 1.3.2",
|
||||
"clap_lex",
|
||||
"indexmap",
|
||||
"textwrap",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "clap_lex"
|
||||
version = "0.2.4"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "2850f2f5a82cbf437dd5af4d49848fbdfc27c157c3d010345776f952765261c5"
|
||||
dependencies = [
|
||||
"os_str_bytes",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "console_error_panic_hook"
|
||||
version = "0.1.7"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "a06aeb73f470f66dcdbf7223caeebb85984942f22f1adb2a088cf9668146bbbc"
|
||||
dependencies = [
|
||||
"cfg-if",
|
||||
"wasm-bindgen",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "criterion"
|
||||
version = "0.4.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "e7c76e09c1aae2bc52b3d2f29e13c6572553b30c4aa1b8a49fd70de6412654cb"
|
||||
dependencies = [
|
||||
"anes",
|
||||
"atty",
|
||||
"cast",
|
||||
"ciborium",
|
||||
"clap",
|
||||
"criterion-plot",
|
||||
"itertools",
|
||||
"lazy_static",
|
||||
"num-traits",
|
||||
"oorandom",
|
||||
"plotters",
|
||||
"rayon",
|
||||
"regex",
|
||||
"serde",
|
||||
"serde_derive",
|
||||
"serde_json",
|
||||
"tinytemplate",
|
||||
"walkdir",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "criterion-plot"
|
||||
version = "0.5.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "6b50826342786a51a89e2da3a28f1c32b06e387201bc2d19791f622c673706b1"
|
||||
dependencies = [
|
||||
"cast",
|
||||
"itertools",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "crossbeam-deque"
|
||||
version = "0.8.5"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "613f8cc01fe9cf1a3eb3d7f488fd2fa8388403e97039e2f73692932e291a770d"
|
||||
dependencies = [
|
||||
"crossbeam-epoch",
|
||||
"crossbeam-utils",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "crossbeam-epoch"
|
||||
version = "0.9.18"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "5b82ac4a3c2ca9c3460964f020e1402edd5753411d7737aa39c3714ad1b5420e"
|
||||
dependencies = [
|
||||
"crossbeam-utils",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "crossbeam-utils"
|
||||
version = "0.8.20"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "22ec99545bb0ed0ea7bb9b8e1e9122ea386ff8a48c0922e43f36d45ab09e0e80"
|
||||
|
||||
[[package]]
|
||||
name = "crunchy"
|
||||
version = "0.2.2"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "7a81dae078cea95a014a339291cec439d2f232ebe854a9d672b796c6afafa9b7"
|
||||
|
||||
[[package]]
|
||||
name = "csv"
|
||||
version = "1.3.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "ac574ff4d437a7b5ad237ef331c17ccca63c46479e5b5453eb8e10bb99a759fe"
|
||||
dependencies = [
|
||||
"csv-core",
|
||||
"itoa",
|
||||
"ryu",
|
||||
"serde",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "csv-core"
|
||||
version = "0.1.11"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "5efa2b3d7902f4b634a20cae3c9c4e6209dc4779feb6863329607560143efa70"
|
||||
dependencies = [
|
||||
"memchr",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "czv"
|
||||
version = "0.0.0"
|
||||
dependencies = [
|
||||
"anyhow",
|
||||
"criterion",
|
||||
"csv",
|
||||
"typed-builder",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "czv-python"
|
||||
version = "0.0.0"
|
||||
dependencies = [
|
||||
"anyhow",
|
||||
"csv",
|
||||
"pyo3",
|
||||
"thiserror",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "czv-wasm"
|
||||
version = "0.0.0"
|
||||
dependencies = [
|
||||
"anyhow",
|
||||
"csv",
|
||||
"thiserror",
|
||||
"wasm-bindgen",
|
||||
"wasm-bindgen-test",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "either"
|
||||
version = "1.12.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "3dca9240753cf90908d7e4aac30f630662b02aebaa1b58a3cadabdb23385b58b"
|
||||
|
||||
[[package]]
|
||||
name = "half"
|
||||
version = "2.4.1"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "6dd08c532ae367adf81c312a4580bc67f1d0fe8bc9c460520283f4c0ff277888"
|
||||
dependencies = [
|
||||
"cfg-if",
|
||||
"crunchy",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "hashbrown"
|
||||
version = "0.12.3"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "8a9ee70c43aaf417c914396645a0fa852624801b24ebb7ae78fe8272889ac888"
|
||||
|
||||
[[package]]
|
||||
name = "heck"
|
||||
version = "0.4.1"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "95505c38b4572b2d910cecb0281560f54b440a19336cbbcb27bf6ce6adc6f5a8"
|
||||
|
||||
[[package]]
|
||||
name = "hermit-abi"
|
||||
version = "0.1.19"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "62b467343b94ba476dcb2500d242dadbb39557df889310ac77c5d99100aaac33"
|
||||
dependencies = [
|
||||
"libc",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "indexmap"
|
||||
version = "1.9.3"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "bd070e393353796e801d209ad339e89596eb4c8d430d18ede6a1cced8fafbd99"
|
||||
dependencies = [
|
||||
"autocfg",
|
||||
"hashbrown",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "indoc"
|
||||
version = "2.0.5"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "b248f5224d1d606005e02c97f5aa4e88eeb230488bcc03bc9ca4d7991399f2b5"
|
||||
|
||||
[[package]]
|
||||
name = "itertools"
|
||||
version = "0.10.5"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "b0fd2260e829bddf4cb6ea802289de2f86d6a7a690192fbe91b3f46e0f2c8473"
|
||||
dependencies = [
|
||||
"either",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "itoa"
|
||||
version = "1.0.11"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "49f1f14873335454500d59611f1cf4a4b0f786f9ac11f4312a78e4cf2566695b"
|
||||
|
||||
[[package]]
|
||||
name = "js-sys"
|
||||
version = "0.3.69"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "29c15563dc2726973df627357ce0c9ddddbea194836909d655df6a75d2cf296d"
|
||||
dependencies = [
|
||||
"wasm-bindgen",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "lazy_static"
|
||||
version = "1.4.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "e2abad23fbc42b3700f2f279844dc832adb2b2eb069b2df918f455c4e18cc646"
|
||||
|
||||
[[package]]
|
||||
name = "libc"
|
||||
version = "0.2.155"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "97b3888a4aecf77e811145cadf6eef5901f4782c53886191b2f693f24761847c"
|
||||
|
||||
[[package]]
|
||||
name = "lock_api"
|
||||
version = "0.4.12"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "07af8b9cdd281b7915f413fa73f29ebd5d55d0d3f0155584dade1ff18cea1b17"
|
||||
dependencies = [
|
||||
"autocfg",
|
||||
"scopeguard",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "log"
|
||||
version = "0.4.21"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "90ed8c1e510134f979dbc4f070f87d4313098b704861a105fe34231c70a3901c"
|
||||
|
||||
[[package]]
|
||||
name = "memchr"
|
||||
version = "2.7.4"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "78ca9ab1a0babb1e7d5695e3530886289c18cf2f87ec19a575a0abdce112e3a3"
|
||||
|
||||
[[package]]
|
||||
name = "memoffset"
|
||||
version = "0.9.1"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "488016bfae457b036d996092f6cb448677611ce4449e970ceaf42695203f218a"
|
||||
dependencies = [
|
||||
"autocfg",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "num-traits"
|
||||
version = "0.2.19"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "071dfc062690e90b734c0b2273ce72ad0ffa95f0c74596bc250dcfd960262841"
|
||||
dependencies = [
|
||||
"autocfg",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "once_cell"
|
||||
version = "1.19.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "3fdb12b2476b595f9358c5161aa467c2438859caa136dec86c26fdd2efe17b92"
|
||||
|
||||
[[package]]
|
||||
name = "oorandom"
|
||||
version = "11.1.3"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "0ab1bc2a289d34bd04a330323ac98a1b4bc82c9d9fcb1e66b63caa84da26b575"
|
||||
|
||||
[[package]]
|
||||
name = "os_str_bytes"
|
||||
version = "6.6.1"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "e2355d85b9a3786f481747ced0e0ff2ba35213a1f9bd406ed906554d7af805a1"
|
||||
|
||||
[[package]]
|
||||
name = "parking_lot"
|
||||
version = "0.12.3"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "f1bf18183cf54e8d6059647fc3063646a1801cf30896933ec2311622cc4b9a27"
|
||||
dependencies = [
|
||||
"lock_api",
|
||||
"parking_lot_core",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "parking_lot_core"
|
||||
version = "0.9.10"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "1e401f977ab385c9e4e3ab30627d6f26d00e2c73eef317493c4ec6d468726cf8"
|
||||
dependencies = [
|
||||
"cfg-if",
|
||||
"libc",
|
||||
"redox_syscall",
|
||||
"smallvec",
|
||||
"windows-targets",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "plotters"
|
||||
version = "0.3.6"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "a15b6eccb8484002195a3e44fe65a4ce8e93a625797a063735536fd59cb01cf3"
|
||||
dependencies = [
|
||||
"num-traits",
|
||||
"plotters-backend",
|
||||
"plotters-svg",
|
||||
"wasm-bindgen",
|
||||
"web-sys",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "plotters-backend"
|
||||
version = "0.3.6"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "414cec62c6634ae900ea1c56128dfe87cf63e7caece0852ec76aba307cebadb7"
|
||||
|
||||
[[package]]
|
||||
name = "plotters-svg"
|
||||
version = "0.3.6"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "81b30686a7d9c3e010b84284bdd26a29f2138574f52f5eb6f794fc0ad924e705"
|
||||
dependencies = [
|
||||
"plotters-backend",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "portable-atomic"
|
||||
version = "1.6.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "7170ef9988bc169ba16dd36a7fa041e5c4cbeb6a35b76d4c03daded371eae7c0"
|
||||
|
||||
[[package]]
|
||||
name = "proc-macro2"
|
||||
version = "1.0.85"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "22244ce15aa966053a896d1accb3a6e68469b97c7f33f284b99f0d576879fc23"
|
||||
dependencies = [
|
||||
"unicode-ident",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "pyo3"
|
||||
version = "0.21.2"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "a5e00b96a521718e08e03b1a622f01c8a8deb50719335de3f60b3b3950f069d8"
|
||||
dependencies = [
|
||||
"cfg-if",
|
||||
"indoc",
|
||||
"libc",
|
||||
"memoffset",
|
||||
"parking_lot",
|
||||
"portable-atomic",
|
||||
"pyo3-build-config",
|
||||
"pyo3-ffi",
|
||||
"pyo3-macros",
|
||||
"unindent",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "pyo3-build-config"
|
||||
version = "0.21.2"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "7883df5835fafdad87c0d888b266c8ec0f4c9ca48a5bed6bbb592e8dedee1b50"
|
||||
dependencies = [
|
||||
"once_cell",
|
||||
"target-lexicon",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "pyo3-ffi"
|
||||
version = "0.21.2"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "01be5843dc60b916ab4dad1dca6d20b9b4e6ddc8e15f50c47fe6d85f1fb97403"
|
||||
dependencies = [
|
||||
"libc",
|
||||
"pyo3-build-config",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "pyo3-macros"
|
||||
version = "0.21.2"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "77b34069fc0682e11b31dbd10321cbf94808394c56fd996796ce45217dfac53c"
|
||||
dependencies = [
|
||||
"proc-macro2",
|
||||
"pyo3-macros-backend",
|
||||
"quote",
|
||||
"syn",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "pyo3-macros-backend"
|
||||
version = "0.21.2"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "08260721f32db5e1a5beae69a55553f56b99bd0e1c3e6e0a5e8851a9d0f5a85c"
|
||||
dependencies = [
|
||||
"heck",
|
||||
"proc-macro2",
|
||||
"pyo3-build-config",
|
||||
"quote",
|
||||
"syn",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "quote"
|
||||
version = "1.0.36"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "0fa76aaf39101c457836aec0ce2316dbdc3ab723cdda1c6bd4e6ad4208acaca7"
|
||||
dependencies = [
|
||||
"proc-macro2",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "rayon"
|
||||
version = "1.10.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "b418a60154510ca1a002a752ca9714984e21e4241e804d32555251faf8b78ffa"
|
||||
dependencies = [
|
||||
"either",
|
||||
"rayon-core",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "rayon-core"
|
||||
version = "1.12.1"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "1465873a3dfdaa8ae7cb14b4383657caab0b3e8a0aa9ae8e04b044854c8dfce2"
|
||||
dependencies = [
|
||||
"crossbeam-deque",
|
||||
"crossbeam-utils",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "redox_syscall"
|
||||
version = "0.5.2"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "c82cf8cff14456045f55ec4241383baeff27af886adb72ffb2162f99911de0fd"
|
||||
dependencies = [
|
||||
"bitflags 2.5.0",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "regex"
|
||||
version = "1.10.5"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "b91213439dad192326a0d7c6ee3955910425f441d7038e0d6933b0aec5c4517f"
|
||||
dependencies = [
|
||||
"aho-corasick",
|
||||
"memchr",
|
||||
"regex-automata",
|
||||
"regex-syntax",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "regex-automata"
|
||||
version = "0.4.7"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "38caf58cc5ef2fed281f89292ef23f6365465ed9a41b7a7754eb4e26496c92df"
|
||||
dependencies = [
|
||||
"aho-corasick",
|
||||
"memchr",
|
||||
"regex-syntax",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "regex-syntax"
|
||||
version = "0.8.4"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "7a66a03ae7c801facd77a29370b4faec201768915ac14a721ba36f20bc9c209b"
|
||||
|
||||
[[package]]
|
||||
name = "ryu"
|
||||
version = "1.0.18"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "f3cb5ba0dc43242ce17de99c180e96db90b235b8a9fdc9543c96d2209116bd9f"
|
||||
|
||||
[[package]]
|
||||
name = "same-file"
|
||||
version = "1.0.6"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "93fc1dc3aaa9bfed95e02e6eadabb4baf7e3078b0bd1b4d7b6b0b68378900502"
|
||||
dependencies = [
|
||||
"winapi-util",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "scoped-tls"
|
||||
version = "1.0.1"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "e1cf6437eb19a8f4a6cc0f7dca544973b0b78843adbfeb3683d1a94a0024a294"
|
||||
|
||||
[[package]]
|
||||
name = "scopeguard"
|
||||
version = "1.2.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "94143f37725109f92c262ed2cf5e59bce7498c01bcc1502d7b9afe439a4e9f49"
|
||||
|
||||
[[package]]
|
||||
name = "serde"
|
||||
version = "1.0.203"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "7253ab4de971e72fb7be983802300c30b5a7f0c2e56fab8abfc6a214307c0094"
|
||||
dependencies = [
|
||||
"serde_derive",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "serde_derive"
|
||||
version = "1.0.203"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "500cbc0ebeb6f46627f50f3f5811ccf6bf00643be300b4c3eabc0ef55dc5b5ba"
|
||||
dependencies = [
|
||||
"proc-macro2",
|
||||
"quote",
|
||||
"syn",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "serde_json"
|
||||
version = "1.0.117"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "455182ea6142b14f93f4bc5320a2b31c1f266b66a4a5c858b013302a5d8cbfc3"
|
||||
dependencies = [
|
||||
"itoa",
|
||||
"ryu",
|
||||
"serde",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "smallvec"
|
||||
version = "1.13.2"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "3c5e1a9a646d36c3599cd173a41282daf47c44583ad367b8e6837255952e5c67"
|
||||
|
||||
[[package]]
|
||||
name = "syn"
|
||||
version = "2.0.66"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "c42f3f41a2de00b01c0aaad383c5a45241efc8b2d1eda5661812fda5f3cdcff5"
|
||||
dependencies = [
|
||||
"proc-macro2",
|
||||
"quote",
|
||||
"unicode-ident",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "target-lexicon"
|
||||
version = "0.12.14"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "e1fc403891a21bcfb7c37834ba66a547a8f402146eba7265b5a6d88059c9ff2f"
|
||||
|
||||
[[package]]
|
||||
name = "textwrap"
|
||||
version = "0.16.1"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "23d434d3f8967a09480fb04132ebe0a3e088c173e6d0ee7897abbdf4eab0f8b9"
|
||||
|
||||
[[package]]
|
||||
name = "thiserror"
|
||||
version = "1.0.61"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "c546c80d6be4bc6a00c0f01730c08df82eaa7a7a61f11d656526506112cc1709"
|
||||
dependencies = [
|
||||
"thiserror-impl",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "thiserror-impl"
|
||||
version = "1.0.61"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "46c3384250002a6d5af4d114f2845d37b57521033f30d5c3f46c4d70e1197533"
|
||||
dependencies = [
|
||||
"proc-macro2",
|
||||
"quote",
|
||||
"syn",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "tinytemplate"
|
||||
version = "1.2.1"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "be4d6b5f19ff7664e8c98d03e2139cb510db9b0a60b55f8e8709b689d939b6bc"
|
||||
dependencies = [
|
||||
"serde",
|
||||
"serde_json",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "typed-builder"
|
||||
version = "0.18.2"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "77739c880e00693faef3d65ea3aad725f196da38b22fdc7ea6ded6e1ce4d3add"
|
||||
dependencies = [
|
||||
"typed-builder-macro",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "typed-builder-macro"
|
||||
version = "0.18.2"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "1f718dfaf347dcb5b983bfc87608144b0bad87970aebcbea5ce44d2a30c08e63"
|
||||
dependencies = [
|
||||
"proc-macro2",
|
||||
"quote",
|
||||
"syn",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "unicode-ident"
|
||||
version = "1.0.12"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "3354b9ac3fae1ff6755cb6db53683adb661634f67557942dea4facebec0fee4b"
|
||||
|
||||
[[package]]
|
||||
name = "unindent"
|
||||
version = "0.2.3"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "c7de7d73e1754487cb58364ee906a499937a0dfabd86bcb980fa99ec8c8fa2ce"
|
||||
|
||||
[[package]]
|
||||
name = "walkdir"
|
||||
version = "2.5.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "29790946404f91d9c5d06f9874efddea1dc06c5efe94541a7d6863108e3a5e4b"
|
||||
dependencies = [
|
||||
"same-file",
|
||||
"winapi-util",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "wasm-bindgen"
|
||||
version = "0.2.92"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "4be2531df63900aeb2bca0daaaddec08491ee64ceecbee5076636a3b026795a8"
|
||||
dependencies = [
|
||||
"cfg-if",
|
||||
"wasm-bindgen-macro",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "wasm-bindgen-backend"
|
||||
version = "0.2.92"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "614d787b966d3989fa7bb98a654e369c762374fd3213d212cfc0251257e747da"
|
||||
dependencies = [
|
||||
"bumpalo",
|
||||
"log",
|
||||
"once_cell",
|
||||
"proc-macro2",
|
||||
"quote",
|
||||
"syn",
|
||||
"wasm-bindgen-shared",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "wasm-bindgen-futures"
|
||||
version = "0.4.42"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "76bc14366121efc8dbb487ab05bcc9d346b3b5ec0eaa76e46594cabbe51762c0"
|
||||
dependencies = [
|
||||
"cfg-if",
|
||||
"js-sys",
|
||||
"wasm-bindgen",
|
||||
"web-sys",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "wasm-bindgen-macro"
|
||||
version = "0.2.92"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "a1f8823de937b71b9460c0c34e25f3da88250760bec0ebac694b49997550d726"
|
||||
dependencies = [
|
||||
"quote",
|
||||
"wasm-bindgen-macro-support",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "wasm-bindgen-macro-support"
|
||||
version = "0.2.92"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "e94f17b526d0a461a191c78ea52bbce64071ed5c04c9ffe424dcb38f74171bb7"
|
||||
dependencies = [
|
||||
"proc-macro2",
|
||||
"quote",
|
||||
"syn",
|
||||
"wasm-bindgen-backend",
|
||||
"wasm-bindgen-shared",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "wasm-bindgen-shared"
|
||||
version = "0.2.92"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "af190c94f2773fdb3729c55b007a722abb5384da03bc0986df4c289bf5567e96"
|
||||
|
||||
[[package]]
|
||||
name = "wasm-bindgen-test"
|
||||
version = "0.3.42"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "d9bf62a58e0780af3e852044583deee40983e5886da43a271dd772379987667b"
|
||||
dependencies = [
|
||||
"console_error_panic_hook",
|
||||
"js-sys",
|
||||
"scoped-tls",
|
||||
"wasm-bindgen",
|
||||
"wasm-bindgen-futures",
|
||||
"wasm-bindgen-test-macro",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "wasm-bindgen-test-macro"
|
||||
version = "0.3.42"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "b7f89739351a2e03cb94beb799d47fb2cac01759b40ec441f7de39b00cbf7ef0"
|
||||
dependencies = [
|
||||
"proc-macro2",
|
||||
"quote",
|
||||
"syn",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "web-sys"
|
||||
version = "0.3.69"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "77afa9a11836342370f4817622a2f0f418b134426d91a82dfb48f532d2ec13ef"
|
||||
dependencies = [
|
||||
"js-sys",
|
||||
"wasm-bindgen",
|
||||
]
|
||||
|
||||
[[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 = "0.1.8"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "4d4cc384e1e73b93bafa6fb4f1df8c41695c8a91cf9c4c64358067d15a7b6c6b"
|
||||
dependencies = [
|
||||
"windows-sys",
|
||||
]
|
||||
|
||||
[[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 = "windows-sys"
|
||||
version = "0.52.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "282be5f36a8ce781fad8c8ae18fa3f9beff57ec1b52cb3de0789201425d9a33d"
|
||||
dependencies = [
|
||||
"windows-targets",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "windows-targets"
|
||||
version = "0.52.5"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "6f0713a46559409d202e70e28227288446bf7841d3211583a4b53e3f6d96e7eb"
|
||||
dependencies = [
|
||||
"windows_aarch64_gnullvm",
|
||||
"windows_aarch64_msvc",
|
||||
"windows_i686_gnu",
|
||||
"windows_i686_gnullvm",
|
||||
"windows_i686_msvc",
|
||||
"windows_x86_64_gnu",
|
||||
"windows_x86_64_gnullvm",
|
||||
"windows_x86_64_msvc",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "windows_aarch64_gnullvm"
|
||||
version = "0.52.5"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "7088eed71e8b8dda258ecc8bac5fb1153c5cffaf2578fc8ff5d61e23578d3263"
|
||||
|
||||
[[package]]
|
||||
name = "windows_aarch64_msvc"
|
||||
version = "0.52.5"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "9985fd1504e250c615ca5f281c3f7a6da76213ebd5ccc9561496568a2752afb6"
|
||||
|
||||
[[package]]
|
||||
name = "windows_i686_gnu"
|
||||
version = "0.52.5"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "88ba073cf16d5372720ec942a8ccbf61626074c6d4dd2e745299726ce8b89670"
|
||||
|
||||
[[package]]
|
||||
name = "windows_i686_gnullvm"
|
||||
version = "0.52.5"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "87f4261229030a858f36b459e748ae97545d6f1ec60e5e0d6a3d32e0dc232ee9"
|
||||
|
||||
[[package]]
|
||||
name = "windows_i686_msvc"
|
||||
version = "0.52.5"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "db3c2bf3d13d5b658be73463284eaf12830ac9a26a90c717b7f771dfe97487bf"
|
||||
|
||||
[[package]]
|
||||
name = "windows_x86_64_gnu"
|
||||
version = "0.52.5"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "4e4246f76bdeff09eb48875a0fd3e2af6aada79d409d33011886d3e1581517d9"
|
||||
|
||||
[[package]]
|
||||
name = "windows_x86_64_gnullvm"
|
||||
version = "0.52.5"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "852298e482cd67c356ddd9570386e2862b5673c85bd5f88df9ab6802b334c596"
|
||||
|
||||
[[package]]
|
||||
name = "windows_x86_64_msvc"
|
||||
version = "0.52.5"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "bec47e5bfd1bff0eeaf6d8b485cc1074891a197ab4225d504cb7a1ab88b02bf0"
|
||||
7
Cargo.toml
Normal file
7
Cargo.toml
Normal file
|
|
@ -0,0 +1,7 @@
|
|||
[workspace]
|
||||
members = [
|
||||
"czv",
|
||||
"czv-wasm",
|
||||
"czv-python"
|
||||
]
|
||||
resolver = "2"
|
||||
108
README.md
Normal file
108
README.md
Normal file
|
|
@ -0,0 +1,108 @@
|
|||
# czv
|
||||
|
||||
czv is CSV content manipulation/analysis libraries with support for Rust, Python, and WebAssembly (JavaScript and TypeScript).
|
||||
|
||||
## Installation and examples
|
||||
|
||||
### Rust
|
||||
|
||||
```bash
|
||||
cargo install czv
|
||||
```
|
||||
|
||||
```rust
|
||||
use czv::{
|
||||
count::RowCount,
|
||||
Result
|
||||
};
|
||||
|
||||
fn main() -> Result<()> {
|
||||
let data = "\
|
||||
fruits,price
|
||||
apple,2.50
|
||||
banana,3.00
|
||||
strawberry,1.50
|
||||
";
|
||||
let output = RowCount::new()
|
||||
.file_data(data)
|
||||
.execute()?;
|
||||
println!("{output}"); // 3
|
||||
Ok(())
|
||||
}
|
||||
```
|
||||
|
||||
### JavaScript/TypeScript (WebAssembly)
|
||||
|
||||
```bash
|
||||
bun install czv
|
||||
```
|
||||
|
||||
Or use `npm`, `pnpm`, or `yarn` instead of `bun`.
|
||||
|
||||
```js
|
||||
import init, * as czv from "czv";
|
||||
// Must run `await init()` or `initSync()` first for web use
|
||||
await init();
|
||||
|
||||
const data = `fruits,price
|
||||
apple,2.50
|
||||
banana,3.00
|
||||
strawberry,1.50`;
|
||||
|
||||
const output = czv.rowCount(data);
|
||||
console.log(output);
|
||||
```
|
||||
|
||||
### Python
|
||||
|
||||
```bash
|
||||
pip install czv
|
||||
```
|
||||
|
||||
```python
|
||||
import czv
|
||||
|
||||
data = """fruits,price
|
||||
apple,2.50
|
||||
banana,3.00
|
||||
strawberry,1.50"""
|
||||
|
||||
output = czv.row_count(data, False)
|
||||
|
||||
print(output)
|
||||
```
|
||||
|
||||
## Available operations
|
||||
|
||||
| czv (Rust) | czv-wasm (JS/TS) | czv-python | Summary |
|
||||
| ---------------------------------------- | -------------------------------------- | ----------------------------------------------- | ------------------------- |
|
||||
| [`count::RowCount`](czv/src/count.rs) | [`rowCount`](czv-wasm/src/count.rs) | [`count.row_count`](czv-python/src/count.rs) | Get the number of rows |
|
||||
| [`count::ColumnCount`](czv/src/count.rs) | [`columnCount`](czv-wasm/src/count.rs) | [`count.column_count`](czv-python/src/count.rs) | Get the number of columns |
|
||||
|
||||
## Development
|
||||
|
||||
Each package has its own `README.md` with more info for that particular package.
|
||||
|
||||
You may generate docs with:
|
||||
|
||||
```bash
|
||||
cargo doc --no-deps --workspace --open
|
||||
```
|
||||
|
||||
## Notes
|
||||
|
||||
czv is inspired by the command-line tools [xsv](https://github.com/BurntSushi/xsv) and [qsv](https://github.com/jqnatividad/qsv), but czv is not intended to cover all of their commands or features.
|
||||
|
||||
Not all provided libraries may be in sync at a given time. See the [available operations table](#available-operations) for a common operation list between libraries (not all implementations for a given operation may be in sync either, for example they may not have the same builder/function arguments).
|
||||
|
||||
Here are a few expected features for each provided operation:
|
||||
|
||||
- czv (Rust)
|
||||
- Provide both a builder (recommended and common for conditional parameters) and a function
|
||||
- Provide documentation (docstrings) in Markdown format
|
||||
- czv-wasm (Web, JavaScript and TypeScript)
|
||||
- Use camelCase for exported functions
|
||||
- Include common browser support to run in-browser
|
||||
- Provide documentation (dosctrings) in TSDoc format
|
||||
- czv-python
|
||||
- Provide documentation (docstrings) and type hints for IDEs when developers are using the Python library (sourced from [czv-python/czv.pyi](czv-python/czv.pyi)) in Markdown format
|
||||
72
czv-python/.gitignore
vendored
Normal file
72
czv-python/.gitignore
vendored
Normal file
|
|
@ -0,0 +1,72 @@
|
|||
/target
|
||||
|
||||
# Byte-compiled / optimized / DLL files
|
||||
__pycache__/
|
||||
.pytest_cache/
|
||||
*.py[cod]
|
||||
|
||||
# C extensions
|
||||
*.so
|
||||
|
||||
# Distribution / packaging
|
||||
.Python
|
||||
.venv/
|
||||
env/
|
||||
bin/
|
||||
build/
|
||||
develop-eggs/
|
||||
dist/
|
||||
eggs/
|
||||
lib/
|
||||
lib64/
|
||||
parts/
|
||||
sdist/
|
||||
var/
|
||||
include/
|
||||
man/
|
||||
venv/
|
||||
*.egg-info/
|
||||
.installed.cfg
|
||||
*.egg
|
||||
|
||||
# Installer logs
|
||||
pip-log.txt
|
||||
pip-delete-this-directory.txt
|
||||
pip-selfcheck.json
|
||||
|
||||
# Unit test / coverage reports
|
||||
htmlcov/
|
||||
.tox/
|
||||
.coverage
|
||||
.cache
|
||||
nosetests.xml
|
||||
coverage.xml
|
||||
|
||||
# Translations
|
||||
*.mo
|
||||
|
||||
# Mr Developer
|
||||
.mr.developer.cfg
|
||||
.project
|
||||
.pydevproject
|
||||
|
||||
# Rope
|
||||
.ropeproject
|
||||
|
||||
# Django stuff:
|
||||
*.log
|
||||
*.pot
|
||||
|
||||
.DS_Store
|
||||
|
||||
# Sphinx documentation
|
||||
docs/_build/
|
||||
|
||||
# PyCharm
|
||||
.idea/
|
||||
|
||||
# VSCode
|
||||
.vscode/
|
||||
|
||||
# Pyenv
|
||||
.python-version
|
||||
16
czv-python/Cargo.toml
Normal file
16
czv-python/Cargo.toml
Normal file
|
|
@ -0,0 +1,16 @@
|
|||
[package]
|
||||
name = "czv-python"
|
||||
version = "0.0.0"
|
||||
authors = ["Mueez Khan"]
|
||||
description = "Python library for performing CSV-related functions for data engineering and analysis."
|
||||
repository = "https://github.com/rzmk/czv"
|
||||
edition = "2021"
|
||||
|
||||
[lib]
|
||||
crate-type = ["cdylib", "rlib"]
|
||||
|
||||
[dependencies]
|
||||
anyhow = "1.0.86"
|
||||
csv = "1.3.0"
|
||||
pyo3 = { version = "0.21.2", features = ["extension-module"] }
|
||||
thiserror = "1.0.61"
|
||||
50
czv-python/README.md
Normal file
50
czv-python/README.md
Normal file
|
|
@ -0,0 +1,50 @@
|
|||
# czv-python
|
||||
|
||||
Python library for [czv](https://github.com/rzmk/czv). czv is a library of utility functions for CSV-related data engineering and analysis tasks.
|
||||
|
||||
## Installation and example
|
||||
|
||||
```bash
|
||||
pip install czv
|
||||
```
|
||||
|
||||
```python
|
||||
import czv
|
||||
|
||||
data = """fruits,price
|
||||
apple,2.50
|
||||
banana,3.00
|
||||
strawberry,1.50"""
|
||||
|
||||
output = czv.row_count(data, False)
|
||||
|
||||
print(output)
|
||||
```
|
||||
|
||||
## Development
|
||||
|
||||
You'll need to have [maturin](https://github.com/PyO3/maturin/) and [uv](https://github.com/astral-sh/uv) installed. Set up a local virtual environment in the `czv-python` folder by running:
|
||||
|
||||
```bash
|
||||
uv venv
|
||||
```
|
||||
|
||||
Make sure to activate the virtual environment (instructions should be provided in your terminal after running the previous command).
|
||||
|
||||
Once you've activated the virtual environment, install dependencies by running:
|
||||
|
||||
```bash
|
||||
uv pip install -r requirements.txt
|
||||
```
|
||||
|
||||
### Build package in local environment
|
||||
|
||||
```bash
|
||||
maturin develop --uv --release
|
||||
```
|
||||
|
||||
### Run tests
|
||||
|
||||
```bash
|
||||
pytest
|
||||
```
|
||||
46
czv-python/czv.pyi
Normal file
46
czv-python/czv.pyi
Normal file
|
|
@ -0,0 +1,46 @@
|
|||
"""
|
||||
# czv
|
||||
|
||||
Python library for [czv](https://github.com/rzmk/czv). CSV content manipulation and analysis.
|
||||
|
||||
## Install
|
||||
|
||||
```bash
|
||||
pip install czv
|
||||
```
|
||||
|
||||
## Example
|
||||
|
||||
```python
|
||||
from czv import row_count
|
||||
|
||||
data = \"""fruits,price
|
||||
apple,2.50
|
||||
banana,3.00
|
||||
strawberry,1.50\"""
|
||||
|
||||
output = row_count(data, False)
|
||||
|
||||
print(output)
|
||||
```
|
||||
|
||||
"""
|
||||
|
||||
from typing import Optional
|
||||
|
||||
def row_count(file_data: str, include_header_row: Optional[bool]) -> int:
|
||||
"""Returns a count of the total number of rows.
|
||||
|
||||
## Arguments
|
||||
|
||||
* `file_data` - CSV file data.
|
||||
* `include_header_row` - Specify whether to include the header row (first row) in the row count. Default is false.
|
||||
"""
|
||||
|
||||
def column_count(file_data: str) -> int:
|
||||
"""Returns a count of the total number of columns (fields).
|
||||
|
||||
## Arguments
|
||||
|
||||
* `file_data` - CSV file data.
|
||||
"""
|
||||
10
czv-python/examples/simple_row_count.py
Normal file
10
czv-python/examples/simple_row_count.py
Normal file
|
|
@ -0,0 +1,10 @@
|
|||
import czv
|
||||
|
||||
data = """fruits,price
|
||||
apple,2.50
|
||||
banana,3.00
|
||||
strawberry,1.50"""
|
||||
|
||||
output = czv.row_count(data, False)
|
||||
|
||||
print(output)
|
||||
15
czv-python/pyproject.toml
Normal file
15
czv-python/pyproject.toml
Normal file
|
|
@ -0,0 +1,15 @@
|
|||
[build-system]
|
||||
requires = ["maturin>=1.6,<2.0"]
|
||||
build-backend = "maturin"
|
||||
|
||||
[project]
|
||||
name = "czv"
|
||||
requires-python = ">=3.8"
|
||||
classifiers = [
|
||||
"Programming Language :: Rust",
|
||||
"Programming Language :: Python :: Implementation :: CPython",
|
||||
"Programming Language :: Python :: Implementation :: PyPy",
|
||||
]
|
||||
dynamic = ["version"]
|
||||
[tool.maturin]
|
||||
features = ["pyo3/extension-module"]
|
||||
2
czv-python/requirements.txt
Normal file
2
czv-python/requirements.txt
Normal file
|
|
@ -0,0 +1,2 @@
|
|||
maturin
|
||||
pytest
|
||||
33
czv-python/src/count.rs
Normal file
33
czv-python/src/count.rs
Normal file
|
|
@ -0,0 +1,33 @@
|
|||
use crate::Result;
|
||||
use csv::ReaderBuilder;
|
||||
use pyo3::pyfunction;
|
||||
|
||||
/// Returns a count of the total number of rows.
|
||||
///
|
||||
/// ## Arguments
|
||||
///
|
||||
/// * `file_data` - CSV file data.
|
||||
/// * `include_header_row` - Specify whether to include the header row (first row) in the row count.
|
||||
#[pyfunction]
|
||||
pub fn row_count(file_data: String, include_header_row: Option<bool>) -> Result<usize> {
|
||||
let mut rdr = ReaderBuilder::new();
|
||||
|
||||
rdr.has_headers(!include_header_row.unwrap_or(false));
|
||||
return Ok(rdr.from_reader(file_data.as_bytes()).records().count());
|
||||
}
|
||||
|
||||
/// Returns a count of the total number of columns (fields).
|
||||
///
|
||||
/// ## Arguments
|
||||
///
|
||||
/// * `file_data` - CSV file data.
|
||||
#[pyfunction]
|
||||
pub fn column_count(file_data: Option<String>) -> Result<usize> {
|
||||
let rdr = ReaderBuilder::new();
|
||||
|
||||
if let Some(file_data) = file_data {
|
||||
return Ok(rdr.from_reader(file_data.as_bytes()).headers()?.len());
|
||||
} else {
|
||||
bail!("Could not determine a file path or file data for column_count_builder.");
|
||||
}
|
||||
}
|
||||
43
czv-python/src/lib.rs
Normal file
43
czv-python/src/lib.rs
Normal file
|
|
@ -0,0 +1,43 @@
|
|||
use pyo3::prelude::*;
|
||||
|
||||
// Error-handling helpers
|
||||
#[derive(thiserror::Error, Debug)]
|
||||
#[error("{0}")]
|
||||
pub struct CzvError(anyhow::Error);
|
||||
|
||||
impl From<pyo3::PyErr> for CzvError {
|
||||
fn from(value: pyo3::PyErr) -> Self {
|
||||
value.into()
|
||||
}
|
||||
}
|
||||
|
||||
impl From<csv::Error> for CzvError {
|
||||
fn from(value: csv::Error) -> Self {
|
||||
value.into()
|
||||
}
|
||||
}
|
||||
|
||||
impl From<CzvError> for pyo3::PyErr {
|
||||
fn from(value: CzvError) -> Self {
|
||||
value.into()
|
||||
}
|
||||
}
|
||||
|
||||
pub type Result<T> = anyhow::Result<T, CzvError>;
|
||||
|
||||
#[allow(unused_macros)]
|
||||
macro_rules! bail {
|
||||
($err:expr $(,)?) => {
|
||||
return Err(crate::CzvError(anyhow::anyhow!($err)))
|
||||
};
|
||||
}
|
||||
|
||||
// Command imports
|
||||
pub mod count;
|
||||
|
||||
#[pymodule]
|
||||
fn czv(m: &Bound<'_, PyModule>) -> PyResult<()> {
|
||||
m.add_function(wrap_pyfunction!(count::row_count, m)?)?;
|
||||
m.add_function(wrap_pyfunction!(count::column_count, m)?)?;
|
||||
Ok(())
|
||||
}
|
||||
0
czv-python/tests/__init__.py
Normal file
0
czv-python/tests/__init__.py
Normal file
33972
czv-python/tests/data/constituents_altnames.csv
Normal file
33972
czv-python/tests/data/constituents_altnames.csv
Normal file
File diff suppressed because it is too large
Load diff
4
czv-python/tests/data/fruits.csv
Normal file
4
czv-python/tests/data/fruits.csv
Normal file
|
|
@ -0,0 +1,4 @@
|
|||
fruit,price
|
||||
apple,2.50
|
||||
banana,3.00
|
||||
strawberry,1.50
|
||||
|
24
czv-python/tests/test_count.py
Normal file
24
czv-python/tests/test_count.py
Normal file
|
|
@ -0,0 +1,24 @@
|
|||
import czv
|
||||
import pytest
|
||||
from .test_data import test_data
|
||||
|
||||
class TestCountFunc:
|
||||
@pytest.mark.parametrize(
|
||||
"file_name,expected",
|
||||
[("fruits.csv", 3), ("constituents_altnames.csv", 33971)],
|
||||
)
|
||||
def test_count(self, file_name, expected):
|
||||
"""Count the total number of non-header rows."""
|
||||
|
||||
result = czv.row_count(test_data[file_name].read_text())
|
||||
assert result == expected
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
"file_name,expected",
|
||||
[("fruits.csv", 4), ("constituents_altnames.csv", 33972)],
|
||||
)
|
||||
def test_include_header_row(self, file_name, expected):
|
||||
"""Count the total number of rows including the header row."""
|
||||
|
||||
result = czv.row_count(test_data[file_name].read_text(), include_header_row=True)
|
||||
assert result == expected
|
||||
7
czv-python/tests/test_data.py
Normal file
7
czv-python/tests/test_data.py
Normal file
|
|
@ -0,0 +1,7 @@
|
|||
import pathlib
|
||||
|
||||
data_path = pathlib.Path(__file__).parent.resolve().joinpath("data")
|
||||
test_data = {
|
||||
file_name: data_path.joinpath(file_name)
|
||||
for file_name in ["fruits.csv", "constituents_altnames.csv"]
|
||||
}
|
||||
17
czv-wasm/Cargo.toml
Normal file
17
czv-wasm/Cargo.toml
Normal file
|
|
@ -0,0 +1,17 @@
|
|||
[package]
|
||||
name = "czv-wasm"
|
||||
version = "0.0.0"
|
||||
authors = ["Mueez Khan"]
|
||||
description = "WASM library for performing CSV-related functions for data engineering and analysis."
|
||||
repository = "https://github.com/rzmk/czv"
|
||||
edition = "2021"
|
||||
|
||||
[lib]
|
||||
crate-type = ["cdylib", "rlib"]
|
||||
|
||||
[dependencies]
|
||||
anyhow = "1.0.86"
|
||||
csv = "1.3.0"
|
||||
thiserror = "1.0.61"
|
||||
wasm-bindgen = { version = "0.2" }
|
||||
wasm-bindgen-test = { version = "0.3.42" }
|
||||
47
czv-wasm/README.md
Normal file
47
czv-wasm/README.md
Normal file
|
|
@ -0,0 +1,47 @@
|
|||
# czv-wasm
|
||||
|
||||
WebAssembly (JavaScript and TypeScript) library for [czv](https://github.com/rzmk/czv). czv is a library of utility functions for CSV-related data engineering and analysis tasks.
|
||||
|
||||
## Installation and example
|
||||
|
||||
```bash
|
||||
bun install czv
|
||||
```
|
||||
|
||||
Or use `npm`, `pnpm`, or `yarn` instead of `bun`.
|
||||
|
||||
```js
|
||||
import init, * as czv from "czv";
|
||||
// Must run `await init()` or `initSync()` first for web use
|
||||
await init();
|
||||
|
||||
const data = `fruits,price
|
||||
apple,2.50
|
||||
banana,3.00
|
||||
strawberry,1.50`;
|
||||
|
||||
const output = czv.rowCount(data);
|
||||
console.log(output);
|
||||
```
|
||||
|
||||
## Development
|
||||
|
||||
You must have [wasm-pack](https://rustwasm.github.io/wasm-pack/installer/) installed. If you have Cargo installed you may run:
|
||||
|
||||
```bash
|
||||
cargo install wasm-pack
|
||||
```
|
||||
|
||||
### Build WASM for web
|
||||
|
||||
```bash
|
||||
wasm-pack build --release --target web
|
||||
```
|
||||
|
||||
### Test WASM for browser
|
||||
|
||||
```bash
|
||||
wasm-pack test --firefox --release
|
||||
```
|
||||
|
||||
You may replace `--firefox` with another browser such as `--chrome` and `--safari`.
|
||||
69
czv-wasm/examples/basic-demo/index.html
Normal file
69
czv-wasm/examples/basic-demo/index.html
Normal file
|
|
@ -0,0 +1,69 @@
|
|||
<!DOCTYPE html>
|
||||
<html id="html" lang="en">
|
||||
|
||||
<head>
|
||||
<meta charset="UTF-8">
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
||||
<link rel="stylesheet" href="pico.min.css" />
|
||||
<title>czv demo</title>
|
||||
</head>
|
||||
|
||||
<body style="padding:1rem">
|
||||
<div style="display: flex; gap: 2rem; justify-content: space-between;">
|
||||
<h1>czv playground</h1>
|
||||
<button class="outline secondary" style="height: fit-content; padding: 0.25rem;" onclick="const html = document.getElementById('html');
|
||||
if (html.getAttribute('data-theme') === 'light')
|
||||
html.setAttribute('data-theme', 'dark')
|
||||
else
|
||||
html.setAttribute('data-theme', 'light')">Switch
|
||||
page theme</button>
|
||||
</div>
|
||||
<p>Import a CSV file and get statistical data from running <a href="https://github.com/rzmk/czv">czv</a> in your
|
||||
browser using WASM.</p>
|
||||
<input type="file" id="upload" accept=".csv" class="hidden" />
|
||||
<label for="upload" style="display: none;" id="progress">Loading...</label>
|
||||
<table style="width: 100%;" class="striped">
|
||||
<thead>
|
||||
<tr>
|
||||
<th style="width: 10rem">Output type</th>
|
||||
<th>Output</th>
|
||||
</tr>
|
||||
</thead>
|
||||
<tbody>
|
||||
<tr>
|
||||
<td>Row count</td>
|
||||
<td id="row-count"></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>Column count</td>
|
||||
<td id="column-count"></td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
<script type="module">
|
||||
const input = document.getElementById("upload")
|
||||
const progress = document.getElementById("progress")
|
||||
|
||||
import init, * as czv from "../../pkg/czv.js";
|
||||
// Must run `await init()` or `initSync()` first for web use
|
||||
await init();
|
||||
|
||||
const fileReader = new FileReader()
|
||||
|
||||
fileReader.onloadstart = () => {
|
||||
progress.style.display = "block";
|
||||
}
|
||||
|
||||
fileReader.onloadend = () => {
|
||||
document.getElementById("column-count").innerText = czv.columnCount(fileReader.result)
|
||||
document.getElementById("row-count").innerText = czv.rowCount(fileReader.result)
|
||||
progress.style.display = "none";
|
||||
}
|
||||
|
||||
input.addEventListener("change", () => {
|
||||
fileReader.readAsText(input.files[0])
|
||||
})
|
||||
</script>
|
||||
</body>
|
||||
|
||||
</html>
|
||||
4
czv-wasm/examples/basic-demo/pico.min.css
vendored
Normal file
4
czv-wasm/examples/basic-demo/pico.min.css
vendored
Normal file
File diff suppressed because one or more lines are too long
32
czv-wasm/src/count.rs
Normal file
32
czv-wasm/src/count.rs
Normal file
|
|
@ -0,0 +1,32 @@
|
|||
use crate::Result;
|
||||
use csv::ReaderBuilder;
|
||||
use wasm_bindgen::prelude::*;
|
||||
|
||||
/// Returns a count of the total number of rows.
|
||||
///
|
||||
/// @param {string} `file_data` CSV file data.
|
||||
/// @param {boolean | undefined} `include_header_row` Specify whether to include the header row (first row) in the row count. Default is false.
|
||||
/// @returns {number}
|
||||
#[wasm_bindgen(skip_jsdoc, js_name = rowCount)]
|
||||
pub fn row_count(file_data: String, include_header_row: Option<bool>) -> Result<usize> {
|
||||
let mut rdr = ReaderBuilder::new();
|
||||
|
||||
rdr.has_headers(!include_header_row.unwrap_or(false));
|
||||
return Ok(rdr.from_reader(file_data.as_bytes()).records().count());
|
||||
}
|
||||
|
||||
/// Returns a count of the total number of columns (fields).
|
||||
///
|
||||
/// ## Arguments
|
||||
///
|
||||
/// @param {string} `file_data` CSV file data.
|
||||
#[wasm_bindgen(skip_jsdoc, js_name = columnCount)]
|
||||
pub fn column_count(file_data: Option<String>) -> Result<usize> {
|
||||
let rdr = ReaderBuilder::new();
|
||||
|
||||
if let Some(file_data) = file_data {
|
||||
return Ok(rdr.from_reader(file_data.as_bytes()).headers()?.len());
|
||||
} else {
|
||||
bail!("Could not determine a file path or file data for column_count_builder.");
|
||||
}
|
||||
}
|
||||
30
czv-wasm/src/lib.rs
Normal file
30
czv-wasm/src/lib.rs
Normal file
|
|
@ -0,0 +1,30 @@
|
|||
use wasm_bindgen::JsValue;
|
||||
|
||||
// Error-handling helpers
|
||||
#[derive(thiserror::Error, Debug)]
|
||||
#[error("{0}")]
|
||||
pub struct CzvError(anyhow::Error);
|
||||
|
||||
impl From<csv::Error> for CzvError {
|
||||
fn from(value: csv::Error) -> Self {
|
||||
value.into()
|
||||
}
|
||||
}
|
||||
|
||||
impl Into<JsValue> for CzvError {
|
||||
fn into(self) -> JsValue {
|
||||
JsValue::from_str(self.to_string().as_str())
|
||||
}
|
||||
}
|
||||
|
||||
pub type Result<T> = anyhow::Result<T, CzvError>;
|
||||
|
||||
#[allow(unused_macros)]
|
||||
macro_rules! bail {
|
||||
($err:expr $(,)?) => {
|
||||
return Err(crate::CzvError(anyhow::anyhow!($err)))
|
||||
};
|
||||
}
|
||||
|
||||
// Command imports
|
||||
pub mod count;
|
||||
19
czv-wasm/tests/count.rs
Normal file
19
czv-wasm/tests/count.rs
Normal file
|
|
@ -0,0 +1,19 @@
|
|||
use czv_wasm;
|
||||
use czv_wasm::Result;
|
||||
use wasm_bindgen_test::*;
|
||||
wasm_bindgen_test::wasm_bindgen_test_configure!(run_in_browser);
|
||||
|
||||
#[test]
|
||||
#[wasm_bindgen_test]
|
||||
fn basic() -> Result<()> {
|
||||
let result = czv_wasm::count::row_count(
|
||||
"fruit,price
|
||||
apple,2.00
|
||||
banana,1.50
|
||||
strawberry,3.00"
|
||||
.to_string(),
|
||||
Some(false),
|
||||
)?;
|
||||
assert_eq!(result, 3);
|
||||
Ok(())
|
||||
}
|
||||
1
czv-wasm/tests/tests.rs
Normal file
1
czv-wasm/tests/tests.rs
Normal file
|
|
@ -0,0 +1 @@
|
|||
mod count;
|
||||
3
czv/.gitignore
vendored
Normal file
3
czv/.gitignore
vendored
Normal file
|
|
@ -0,0 +1,3 @@
|
|||
/target
|
||||
/.venv
|
||||
/pkg
|
||||
22
czv/Cargo.toml
Normal file
22
czv/Cargo.toml
Normal file
|
|
@ -0,0 +1,22 @@
|
|||
[package]
|
||||
name = "czv"
|
||||
version = "0.0.0"
|
||||
authors = ["Mueez Khan"]
|
||||
description = "Rust library for performing CSV-related operations for data engineering and analysis."
|
||||
repository = "https://github.com/rzmk/czv"
|
||||
edition = "2021"
|
||||
license = "MIT OR Apache-2.0"
|
||||
keywords = ["csv", "library"]
|
||||
categories = ["text-processing"]
|
||||
|
||||
[dependencies]
|
||||
anyhow = "1.0.86"
|
||||
csv = "1.3.0"
|
||||
typed-builder = "0.18.2"
|
||||
|
||||
[dev-dependencies]
|
||||
criterion = { version = "0.4", features = ["html_reports"] }
|
||||
|
||||
[[bench]]
|
||||
name = "benches"
|
||||
harness = false
|
||||
56
czv/README.md
Normal file
56
czv/README.md
Normal file
|
|
@ -0,0 +1,56 @@
|
|||
# czv
|
||||
|
||||
Rust library for [czv](https://github.com/rzmk/czv). czv is a library of utility functions for CSV-related data engineering and analysis tasks.
|
||||
|
||||
## Usage
|
||||
|
||||
You must have [Rust](https://www.rust-lang.org/tools/install) and Cargo installed (Cargo may be additionally installed when you install Rust with `rustup`).
|
||||
|
||||
To install `czv`, run:
|
||||
|
||||
```bash
|
||||
cargo install czv
|
||||
```
|
||||
|
||||
Let's say we want to print the total number of rows in a 4x3 CSV file `fruits.csv` including the header row:
|
||||
|
||||
```rust
|
||||
use czv::{count::RowCount, Result};
|
||||
|
||||
fn main() -> Result<()> {
|
||||
let data = r#"fruits,price
|
||||
apple,2.50
|
||||
banana,3.00
|
||||
strawberry,1.50"#;
|
||||
let output = RowCount::new()
|
||||
.file_data(data)
|
||||
.include_header_row(true)
|
||||
.execute()?;
|
||||
println!("{output}"); // 4
|
||||
Ok(())
|
||||
}
|
||||
```
|
||||
|
||||
When ran, this should be the standard output printed in the terminal:
|
||||
|
||||
```console
|
||||
4
|
||||
```
|
||||
|
||||
## Tests
|
||||
|
||||
To run the tests, run:
|
||||
|
||||
```bash
|
||||
cargo test
|
||||
```
|
||||
|
||||
## Benchmarks
|
||||
|
||||
To run the benchmarks, run:
|
||||
|
||||
```bash
|
||||
cargo bench
|
||||
```
|
||||
|
||||
For benchmarks we use [criterion.rs](https://github.com/bheisler/criterion.rs).
|
||||
63
czv/benches/bench_count.rs
Normal file
63
czv/benches/bench_count.rs
Normal file
|
|
@ -0,0 +1,63 @@
|
|||
use criterion::{black_box, criterion_group, Criterion};
|
||||
use czv;
|
||||
use czv::Result;
|
||||
use std::path::PathBuf;
|
||||
|
||||
// macro_rules! get_test_files {
|
||||
// ( $( $x:expr ),* ) => {
|
||||
// {
|
||||
// let test_dir = std::path::PathBuf::from(env!("CARGO_MANIFEST_DIR")).join("tests/resources/");
|
||||
// let mut files = Vec::new();
|
||||
// $(
|
||||
// files.push(test_dir.join($x));
|
||||
// )*
|
||||
// files
|
||||
// }
|
||||
// };
|
||||
// }
|
||||
|
||||
fn bench_row_count(file_path: PathBuf) -> Result<()> {
|
||||
czv::count::row_count(Some(file_path), None, false)?;
|
||||
Ok(())
|
||||
}
|
||||
|
||||
fn bench_row_count_group(c: &mut Criterion) {
|
||||
let mut group = c.benchmark_group("row_count");
|
||||
group.bench_function("fruits.csv", |b| {
|
||||
b.iter(|| bench_row_count(black_box("tests/resources/fruits.csv".into())))
|
||||
});
|
||||
group.bench_function("constituents_altnames.csv", |b| {
|
||||
b.iter(|| {
|
||||
bench_row_count(black_box(
|
||||
"tests/resources/constituents_altnames.csv".into(),
|
||||
))
|
||||
})
|
||||
});
|
||||
group.finish();
|
||||
}
|
||||
|
||||
fn bench_column_count(file_path: PathBuf) -> Result<()> {
|
||||
czv::count::column_count(Some(file_path), None)?;
|
||||
Ok(())
|
||||
}
|
||||
|
||||
fn bench_column_count_group(c: &mut Criterion) {
|
||||
let mut group = c.benchmark_group("column_count");
|
||||
group.bench_function("fruits.csv", |b| {
|
||||
b.iter(|| bench_column_count(black_box("tests/resources/fruits.csv".into())))
|
||||
});
|
||||
group.bench_function("constituents_altnames.csv", |b| {
|
||||
b.iter(|| {
|
||||
bench_column_count(black_box(
|
||||
"tests/resources/constituents_altnames.csv".into(),
|
||||
))
|
||||
})
|
||||
});
|
||||
group.finish();
|
||||
}
|
||||
|
||||
criterion_group!(
|
||||
count_benches,
|
||||
bench_row_count_group,
|
||||
bench_column_count_group
|
||||
);
|
||||
7
czv/benches/benches.rs
Normal file
7
czv/benches/benches.rs
Normal file
|
|
@ -0,0 +1,7 @@
|
|||
// Import benchmarks
|
||||
mod bench_count;
|
||||
use bench_count::count_benches;
|
||||
|
||||
// Run all benchmarks
|
||||
use criterion::criterion_main;
|
||||
criterion_main!(count_benches);
|
||||
13
czv/examples/simple_row_count.rs
Normal file
13
czv/examples/simple_row_count.rs
Normal file
|
|
@ -0,0 +1,13 @@
|
|||
use czv::{count::RowCount, Result};
|
||||
|
||||
fn main() -> Result<()> {
|
||||
let data = "\
|
||||
fruits,price
|
||||
apple,2.50
|
||||
banana,3.00
|
||||
strawberry,1.50
|
||||
";
|
||||
let output = RowCount::new().file_data(data).execute()?;
|
||||
println!("{output}"); // 3
|
||||
Ok(())
|
||||
}
|
||||
188
czv/src/count.rs
Normal file
188
czv/src/count.rs
Normal file
|
|
@ -0,0 +1,188 @@
|
|||
use crate::{bail, Result};
|
||||
use csv::ReaderBuilder;
|
||||
use std::path::PathBuf;
|
||||
use typed_builder::TypedBuilder;
|
||||
|
||||
/// Returns a count of the total number of rows. Recommended alternative: [`czv::count::RowCount`](crate::count::RowCount).
|
||||
///
|
||||
/// See [`czv::count::RowCount`](crate::count::RowCount) for a builder version (recommended) of this function.
|
||||
///
|
||||
/// ## Notes
|
||||
///
|
||||
/// - Specify whether to include the header row in the count with `include_header_row`.
|
||||
/// - You may not use `file_path` and `file_data` together, only one may be specified.
|
||||
///
|
||||
/// ## Arguments
|
||||
///
|
||||
/// * `file_path` - CSV file path (alternative to `file_data`).
|
||||
/// * `file_data` - CSV file data (alternative to `file_path`).
|
||||
/// * `include_header_row` - Specify whether to include the header row (first row) in the row count.
|
||||
pub fn row_count(
|
||||
file_path: Option<PathBuf>,
|
||||
file_data: Option<String>,
|
||||
include_header_row: bool,
|
||||
) -> Result<usize> {
|
||||
let mut rdr = ReaderBuilder::new();
|
||||
|
||||
// file_path
|
||||
if let Some(file_path) = file_path {
|
||||
rdr.has_headers(!include_header_row);
|
||||
return Ok(rdr.from_path(file_path)?.records().count());
|
||||
}
|
||||
// file_data
|
||||
else if let Some(file_data) = file_data {
|
||||
rdr.has_headers(!include_header_row);
|
||||
return Ok(rdr.from_reader(file_data.as_bytes()).records().count());
|
||||
}
|
||||
// file_path and file_data were not provided
|
||||
else {
|
||||
bail!("Could not determine a file path or file data for row_count_builder.");
|
||||
}
|
||||
}
|
||||
|
||||
#[derive(TypedBuilder)]
|
||||
#[builder(doc, builder_method(name=new, doc="Returns a `RowCountBuilder` to customize row count options by running other methods before getting the row count with the `execute` method."), build_method(vis="", name=__build))]
|
||||
/// The entry point for setting up a [`czv::count::RowCountBuilder`](crate::count::RowCountBuilder) by running [`RowCount::new()`](crate::count::RowCount::new).
|
||||
///
|
||||
/// For example:
|
||||
///
|
||||
/// ```rust
|
||||
/// use czv::{count::RowCount, Result};
|
||||
///
|
||||
/// fn main() -> Result<()> {
|
||||
/// let data = "\
|
||||
/// fruits,price
|
||||
/// apple,2.50
|
||||
/// banana,3.00
|
||||
/// strawberry,1.50
|
||||
/// ";
|
||||
/// let output = RowCount::new().file_data(data).execute()?;
|
||||
/// println!("{output}"); // 3
|
||||
/// Ok(())
|
||||
/// }
|
||||
/// ```
|
||||
pub struct RowCount {
|
||||
#[builder(
|
||||
default,
|
||||
setter(
|
||||
doc = "CSV file path (alternative to `file_data`).",
|
||||
strip_option,
|
||||
into
|
||||
)
|
||||
)]
|
||||
file_path: Option<PathBuf>,
|
||||
|
||||
#[builder(
|
||||
default,
|
||||
setter(
|
||||
doc = "CSV file data (alternative to `file_path`).",
|
||||
strip_option,
|
||||
into
|
||||
)
|
||||
)]
|
||||
file_data: Option<String>,
|
||||
|
||||
#[builder(
|
||||
default = false,
|
||||
setter(
|
||||
doc = "Specify whether to include the header row (first row) in the row count. Defaults to false."
|
||||
)
|
||||
)]
|
||||
include_header_row: bool,
|
||||
}
|
||||
|
||||
#[allow(non_camel_case_types)]
|
||||
impl<
|
||||
__include_header_row: typed_builder::Optional<bool>,
|
||||
__file_data: typed_builder::Optional<Option<String>>,
|
||||
__file_path: typed_builder::Optional<Option<PathBuf>>,
|
||||
> RowCountBuilder<(__file_path, __file_data, __include_header_row)>
|
||||
{
|
||||
/// Returns the row count.
|
||||
pub fn execute(self) -> Result<usize> {
|
||||
let builder = self.__build();
|
||||
row_count(
|
||||
builder.file_path,
|
||||
builder.file_data,
|
||||
builder.include_header_row,
|
||||
)
|
||||
}
|
||||
}
|
||||
|
||||
/// Returns a count of the total number of columns (fields). Recommended alternative: [`czv::count::ColumnCount`](crate::count::ColumnCount).
|
||||
///
|
||||
/// See [`czv::count::ColumnCount`](crate::count::ColumnCount) for a builder version (recommended) of this function.
|
||||
///
|
||||
/// ## Arguments
|
||||
///
|
||||
/// * `file_path` - CSV file path (alternative to `file_data`).
|
||||
/// * `file_data` - CSV file data (alternative to `file_path`).
|
||||
pub fn column_count(file_path: Option<PathBuf>, file_data: Option<String>) -> Result<usize> {
|
||||
let rdr = ReaderBuilder::new();
|
||||
|
||||
// file_path
|
||||
if let Some(file_path) = file_path {
|
||||
return Ok(rdr.from_path(file_path)?.headers()?.len());
|
||||
}
|
||||
// file_data
|
||||
else if let Some(file_data) = file_data {
|
||||
return Ok(rdr.from_reader(file_data.as_bytes()).headers()?.len());
|
||||
}
|
||||
// file_path and file_data were not provided
|
||||
else {
|
||||
bail!("Could not determine a file path or file data for column_count_builder.");
|
||||
}
|
||||
}
|
||||
|
||||
#[derive(TypedBuilder)]
|
||||
#[builder(doc, builder_method(name=new, doc="Returns a `ColumnCountBuilder` to customize column count options by running other methods before getting the column count with the `execute` method."), build_method(vis="", name=__build))]
|
||||
/// The entry point for setting up a [`czv::count::ColumnCountBuilder`](crate::count::ColumnCountBuilder) by running [`ColumnCount::new()`](crate::count::ColumnCount::new).
|
||||
///
|
||||
/// For example:
|
||||
///
|
||||
/// ```rust
|
||||
/// use czv::{count::ColumnCount, Result};
|
||||
///
|
||||
/// fn main() -> Result<()> {
|
||||
/// let data = r#"fruits,price
|
||||
/// apple,2.50
|
||||
/// banana,3.00
|
||||
/// strawberry,1.50"#;
|
||||
/// let output = ColumnCount::new().file_data(data).execute()?;
|
||||
/// println!("{output}"); // 2
|
||||
/// Ok(())
|
||||
/// }
|
||||
/// ```
|
||||
pub struct ColumnCount {
|
||||
#[builder(
|
||||
default,
|
||||
setter(
|
||||
doc = "CSV file path (alternative to `file_data`).",
|
||||
strip_option,
|
||||
into
|
||||
)
|
||||
)]
|
||||
file_path: Option<PathBuf>,
|
||||
|
||||
#[builder(
|
||||
default,
|
||||
setter(
|
||||
doc = "CSV file path (alternative to `file_path`).",
|
||||
strip_option,
|
||||
into
|
||||
)
|
||||
)]
|
||||
file_data: Option<String>,
|
||||
}
|
||||
|
||||
#[allow(non_camel_case_types)]
|
||||
impl<
|
||||
__file_data: typed_builder::Optional<Option<String>>,
|
||||
__file_path: typed_builder::Optional<Option<PathBuf>>,
|
||||
> ColumnCountBuilder<(__file_path, __file_data)>
|
||||
{
|
||||
pub fn execute(self) -> Result<usize> {
|
||||
let builder = self.__build();
|
||||
column_count(builder.file_path, builder.file_data)
|
||||
}
|
||||
}
|
||||
58
czv/src/lib.rs
Normal file
58
czv/src/lib.rs
Normal file
|
|
@ -0,0 +1,58 @@
|
|||
//! # czv
|
||||
//!
|
||||
//! CSV operations library for data engineering/analysis tasks.
|
||||
//!
|
||||
//! ## Example
|
||||
//!
|
||||
//! ```rust
|
||||
//! use czv::{count::RowCount, Result};
|
||||
//!
|
||||
//! fn main() -> Result<()> {
|
||||
//! let data = "\
|
||||
//! fruits,price
|
||||
//! apple,2.50
|
||||
//! banana,3.00
|
||||
//! strawberry,1.50
|
||||
//! ";
|
||||
//! let output = RowCount::new().file_data(data).execute()?;
|
||||
//! println!("{output}"); // 3
|
||||
//! Ok(())
|
||||
//! }
|
||||
//! ```
|
||||
//!
|
||||
//! ## Links
|
||||
//!
|
||||
//! - Source code: <https://github.com/rzmk/czv>
|
||||
//! - czv-wasm: <https://github.com/rzmk/czv>
|
||||
//! - czv-python: <https://github.com/rzmk/czv>
|
||||
|
||||
/// Counting operations including row count and column count.
|
||||
pub mod count;
|
||||
/// Extract a section of rows.
|
||||
pub mod slice;
|
||||
|
||||
#[allow(dead_code)]
|
||||
#[derive(Debug)]
|
||||
pub struct CzvError(anyhow::Error);
|
||||
|
||||
impl From<anyhow::Error> for CzvError {
|
||||
fn from(value: anyhow::Error) -> Self {
|
||||
value.into()
|
||||
}
|
||||
}
|
||||
|
||||
impl From<csv::Error> for CzvError {
|
||||
fn from(value: csv::Error) -> Self {
|
||||
value.into()
|
||||
}
|
||||
}
|
||||
|
||||
pub type Result<T, E = CzvError> = anyhow::Result<T, E>;
|
||||
|
||||
#[macro_export]
|
||||
#[allow(unused_macros)]
|
||||
macro_rules! bail {
|
||||
($err:expr $(,)?) => {
|
||||
return Err(crate::CzvError(anyhow::anyhow!($err)))
|
||||
};
|
||||
}
|
||||
281
czv/src/slice.rs
Normal file
281
czv/src/slice.rs
Normal file
|
|
@ -0,0 +1,281 @@
|
|||
use crate::{bail, Result};
|
||||
use csv::ReaderBuilder;
|
||||
use std::path::PathBuf;
|
||||
use typed_builder::TypedBuilder;
|
||||
|
||||
/// Returns a slice of rows from the CSV data.
|
||||
///
|
||||
/// See [`czv::slice::Slice`](crate::slice::Slice) for a builder version (recommended) of this function.
|
||||
///
|
||||
/// ## Example
|
||||
///
|
||||
/// We have a file `fruits.csv` at the path `tests/resources/fruits.csv`:
|
||||
///
|
||||
/// ```csv
|
||||
/// fruit,price
|
||||
/// apple,2.50
|
||||
/// banana,3.00
|
||||
/// strawberry,1.50
|
||||
/// ```
|
||||
///
|
||||
/// Let's print the first two non-header rows in the CSV file:
|
||||
///
|
||||
/// ```rust
|
||||
/// use czv::{
|
||||
/// Result,
|
||||
/// slice::Slice
|
||||
/// };
|
||||
///
|
||||
/// fn main() -> Result<()> {
|
||||
/// let file_path = "tests/resources/fruits.csv";
|
||||
///
|
||||
/// let output: String = Slice::new()
|
||||
/// .file_path(file_path)
|
||||
/// .start(0)
|
||||
/// .end(2) // exclusive
|
||||
/// .include_header_row(false)
|
||||
/// .execute()?;
|
||||
///
|
||||
/// println!("{output}");
|
||||
///
|
||||
/// Ok(())
|
||||
/// }
|
||||
/// ```
|
||||
///
|
||||
/// Printed to the terminal we get:
|
||||
///
|
||||
/// ```console
|
||||
/// apple,2.50
|
||||
/// banana,3.00
|
||||
/// ```
|
||||
///
|
||||
/// ## Notes
|
||||
///
|
||||
/// - You may not use `file_path` and `file_data` together, only one may be specified.
|
||||
/// - You may not use `end` and `length` together, only one may be specified.
|
||||
/// - You may not use `index` with any of `start`, `end`, or `length`.
|
||||
///
|
||||
/// ## Arguments
|
||||
///
|
||||
/// * `file_path` - CSV file path (alternative to `file_data`).
|
||||
/// * `file_data` - CSV file data (alternative to `file_path`).
|
||||
/// * `start` - The index of the record to slice from (0-indexed).
|
||||
/// If negative, starts from the last record.
|
||||
/// * `end` - The index of the record to slice to.
|
||||
/// * `length` - The length of the slice (alternative to `end`).
|
||||
/// * `index` - Slice a single record. If negative, starts from the last record.
|
||||
/// * `include_header_row` - Specify whether to include the header row (first row) in the records.
|
||||
pub fn slice(
|
||||
file_path: Option<PathBuf>,
|
||||
file_data: Option<String>,
|
||||
start: Option<i32>,
|
||||
end: Option<i32>,
|
||||
length: Option<i32>,
|
||||
index: Option<i32>,
|
||||
include_header_row: bool,
|
||||
) -> Result<String> {
|
||||
match (file_path, file_data) {
|
||||
(Some(_), Some(_)) => bail!("Cannot have both file_path and file_data, specify one only."),
|
||||
(None, None) => bail!("Must provide either file_path or file_data."),
|
||||
(Some(file_path), None) => {
|
||||
let mut rdr = ReaderBuilder::new()
|
||||
.has_headers(include_header_row)
|
||||
.from_path(file_path)?;
|
||||
if !include_header_row {
|
||||
rdr.byte_headers()?;
|
||||
}
|
||||
let original_pos = rdr.position().to_owned();
|
||||
let records_count = rdr.records().count();
|
||||
|
||||
if index.is_some() && (start.is_some() || end.is_some() || length.is_some()) {
|
||||
bail!("Cannot use index with start, end, or length.")
|
||||
}
|
||||
if end.is_some() && length.is_some() {
|
||||
bail!("Cannot use end with length.")
|
||||
}
|
||||
|
||||
let start_line = match start {
|
||||
Some(x) => {
|
||||
if x > records_count as i32 {
|
||||
bail!("start value {x} cannot be greater than the number of records.")
|
||||
} else if x >= 0 {
|
||||
Some(x as usize)
|
||||
} else {
|
||||
Some((records_count as i32 + x) as usize)
|
||||
}
|
||||
}
|
||||
None => None,
|
||||
};
|
||||
let end_line = match end {
|
||||
Some(x) => {
|
||||
if x >= records_count as i32 {
|
||||
bail!("end value {x} cannot be greater than or equal to the number of records.")
|
||||
} else if x >= 0 {
|
||||
Some(x as usize)
|
||||
} else {
|
||||
Some((records_count as i32 + x) as usize)
|
||||
}
|
||||
}
|
||||
None => None,
|
||||
};
|
||||
|
||||
rdr.seek(original_pos)?;
|
||||
let mut res_vec: Vec<String> = vec![];
|
||||
|
||||
if let Some(idx) = index {
|
||||
return Ok(rdr
|
||||
.records()
|
||||
.skip(idx as usize)
|
||||
.next()
|
||||
.unwrap()?
|
||||
.iter()
|
||||
.map(|x| x.to_string())
|
||||
.collect::<Vec<_>>()
|
||||
.join(","));
|
||||
}
|
||||
|
||||
for r in rdr
|
||||
.records()
|
||||
.skip(start_line.unwrap())
|
||||
.take(end_line.unwrap() - start_line.unwrap())
|
||||
{
|
||||
let record = r?;
|
||||
res_vec.push(
|
||||
record
|
||||
.iter()
|
||||
.map(|x| x.to_string())
|
||||
.collect::<Vec<_>>()
|
||||
.join(","),
|
||||
);
|
||||
}
|
||||
Ok(res_vec
|
||||
.iter()
|
||||
.map(|x| x.to_string())
|
||||
.collect::<Vec<_>>()
|
||||
.join("\n"))
|
||||
}
|
||||
(None, Some(file_data)) => {
|
||||
let mut rdr = ReaderBuilder::new()
|
||||
.has_headers(include_header_row)
|
||||
.from_reader(std::io::Cursor::new(file_data.as_str()));
|
||||
if !include_header_row {
|
||||
rdr.byte_headers()?;
|
||||
}
|
||||
let original_pos = rdr.position().to_owned();
|
||||
let records_count = rdr.records().count();
|
||||
|
||||
if index.is_some() && (start.is_some() || end.is_some() || length.is_some()) {
|
||||
bail!("Cannot use index with start, end, or length.")
|
||||
}
|
||||
if end.is_some() && length.is_some() {
|
||||
bail!("Cannot use end with length.")
|
||||
}
|
||||
|
||||
let start_line = match start {
|
||||
Some(x) => {
|
||||
if x > records_count as i32 {
|
||||
bail!("start value {x} cannot be greater than the number of records.")
|
||||
} else if x >= 0 {
|
||||
Some(x as usize)
|
||||
} else {
|
||||
Some((records_count as i32 + x) as usize)
|
||||
}
|
||||
}
|
||||
None => None,
|
||||
};
|
||||
let end_line = match end {
|
||||
Some(x) => {
|
||||
if x >= records_count as i32 {
|
||||
bail!("end value {x} cannot be greater than or equal to the number of records.")
|
||||
} else if x >= 0 {
|
||||
Some(x as usize)
|
||||
} else {
|
||||
Some((records_count as i32 + x) as usize)
|
||||
}
|
||||
}
|
||||
None => None,
|
||||
};
|
||||
|
||||
rdr.seek(original_pos)?;
|
||||
let mut res_vec: Vec<String> = vec![];
|
||||
for r in rdr
|
||||
.records()
|
||||
.skip(start_line.unwrap())
|
||||
.take(end_line.unwrap() - start_line.unwrap())
|
||||
{
|
||||
let record = r?;
|
||||
res_vec.push(
|
||||
record
|
||||
.iter()
|
||||
.map(|x| x.to_string())
|
||||
.collect::<Vec<_>>()
|
||||
.join(","),
|
||||
);
|
||||
}
|
||||
Ok(res_vec
|
||||
.iter()
|
||||
.map(|x| x.to_string())
|
||||
.collect::<Vec<_>>()
|
||||
.join("\n"))
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
#[derive(TypedBuilder)]
|
||||
#[builder(builder_method(name=new), build_method(vis="", name=__build))]
|
||||
pub struct Slice {
|
||||
#[builder(default, setter(strip_option, into))]
|
||||
file_path: Option<PathBuf>,
|
||||
|
||||
#[builder(default, setter(strip_option, into))]
|
||||
file_data: Option<String>,
|
||||
|
||||
#[builder(default, setter(strip_option))]
|
||||
start: Option<i32>,
|
||||
|
||||
#[builder(default, setter(strip_option))]
|
||||
end: Option<i32>,
|
||||
|
||||
#[builder(default, setter(strip_option))]
|
||||
length: Option<i32>,
|
||||
|
||||
#[builder(default, setter(strip_option))]
|
||||
index: Option<i32>,
|
||||
|
||||
#[builder(default = false)]
|
||||
include_header_row: bool,
|
||||
}
|
||||
|
||||
#[allow(non_camel_case_types)]
|
||||
impl<
|
||||
__include_header_row: typed_builder::Optional<bool>,
|
||||
__index: typed_builder::Optional<Option<i32>>,
|
||||
__length: typed_builder::Optional<Option<i32>>,
|
||||
__end: typed_builder::Optional<Option<i32>>,
|
||||
__start: typed_builder::Optional<Option<i32>>,
|
||||
__file_data: typed_builder::Optional<Option<String>>,
|
||||
__file_path: typed_builder::Optional<Option<PathBuf>>,
|
||||
>
|
||||
SliceBuilder<(
|
||||
__file_path,
|
||||
__file_data,
|
||||
__start,
|
||||
__end,
|
||||
__length,
|
||||
__index,
|
||||
__include_header_row,
|
||||
)>
|
||||
{
|
||||
pub fn execute(self) -> Result<String> {
|
||||
let builder = self.__build();
|
||||
slice(
|
||||
builder.file_path,
|
||||
builder.file_data,
|
||||
builder.start,
|
||||
builder.end,
|
||||
builder.length,
|
||||
builder.index,
|
||||
builder.include_header_row,
|
||||
)
|
||||
}
|
||||
}
|
||||
33972
czv/tests/resources/constituents_altnames.csv
Normal file
33972
czv/tests/resources/constituents_altnames.csv
Normal file
File diff suppressed because it is too large
Load diff
4
czv/tests/resources/fruits.csv
Normal file
4
czv/tests/resources/fruits.csv
Normal file
|
|
@ -0,0 +1,4 @@
|
|||
fruit,price
|
||||
apple,2.50
|
||||
banana,3.00
|
||||
strawberry,1.50
|
||||
|
56
czv/tests/test_count.rs
Normal file
56
czv/tests/test_count.rs
Normal file
|
|
@ -0,0 +1,56 @@
|
|||
use czv;
|
||||
use czv::Result;
|
||||
|
||||
#[test]
|
||||
fn test_row_count() -> Result<()> {
|
||||
let cases = vec![
|
||||
("tests/resources/fruits.csv", 3),
|
||||
("tests/resources/constituents_altnames.csv", 33971),
|
||||
];
|
||||
for (file_name, expected) in cases {
|
||||
let got = czv::count::row_count(Some(file_name.into()), None, false)?;
|
||||
assert_eq!(expected, got);
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_row_count_builder() -> Result<()> {
|
||||
let cases = vec![
|
||||
("tests/resources/fruits.csv", 3),
|
||||
("tests/resources/constituents_altnames.csv", 33971),
|
||||
];
|
||||
for (file_name, expected) in cases {
|
||||
let got = czv::count::RowCount::new().file_path(file_name).execute()?;
|
||||
assert_eq!(expected, got);
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_column_count() -> Result<()> {
|
||||
let cases = vec![
|
||||
("tests/resources/fruits.csv", 2),
|
||||
("tests/resources/constituents_altnames.csv", 6),
|
||||
];
|
||||
for (file_name, expected) in cases {
|
||||
let got = czv::count::column_count(Some(file_name.into()), None)?;
|
||||
assert_eq!(expected, got);
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_column_count_builder() -> Result<()> {
|
||||
let cases = vec![
|
||||
("tests/resources/fruits.csv", 2),
|
||||
("tests/resources/constituents_altnames.csv", 6),
|
||||
];
|
||||
for (file_name, expected) in cases {
|
||||
let got = czv::count::ColumnCount::new()
|
||||
.file_path(file_name)
|
||||
.execute()?;
|
||||
assert_eq!(expected, got);
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
75
czv/tests/test_slice.rs
Normal file
75
czv/tests/test_slice.rs
Normal file
|
|
@ -0,0 +1,75 @@
|
|||
use czv;
|
||||
use czv::Result;
|
||||
|
||||
#[test]
|
||||
fn test_slice_start_end() -> Result<()> {
|
||||
let cases = vec![(
|
||||
"tests/resources/fruits.csv",
|
||||
1,
|
||||
3,
|
||||
"banana,3.00\nstrawberry,1.50".to_string(),
|
||||
)];
|
||||
for (file_name, start, end, expected) in cases {
|
||||
let got = czv::slice::slice(
|
||||
Some(file_name.into()),
|
||||
None,
|
||||
Some(start),
|
||||
Some(end),
|
||||
None,
|
||||
None,
|
||||
false,
|
||||
)?;
|
||||
assert_eq!(expected, got);
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_slice_start_end_data() -> Result<()> {
|
||||
let cases = vec![(
|
||||
"fruit,price\napple,2.50\nbanana,3.00\nstrawberry,1.50".to_string(),
|
||||
1,
|
||||
3,
|
||||
"banana,3.00\nstrawberry,1.50".to_string(),
|
||||
)];
|
||||
for (file_data, start, end, expected) in cases {
|
||||
let got = czv::slice::slice(
|
||||
None,
|
||||
Some(file_data),
|
||||
Some(start),
|
||||
Some(end),
|
||||
None,
|
||||
None,
|
||||
false,
|
||||
)?;
|
||||
assert_eq!(expected, got);
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_slice_start_0_end_3() -> Result<()> {
|
||||
let expected = "apple,2.50\nbanana,3.00".to_string();
|
||||
let got: String = czv::slice::Slice::new()
|
||||
.file_path("tests/resources/fruits.csv")
|
||||
.start(0)
|
||||
.end(2) // exclusive
|
||||
.include_header_row(false)
|
||||
.execute()?;
|
||||
|
||||
assert_eq!(expected, got);
|
||||
Ok(())
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_slice_index_2() -> Result<()> {
|
||||
let expected = "strawberry,1.50".to_string();
|
||||
let got: String = czv::slice::Slice::new()
|
||||
.file_path("tests/resources/fruits.csv")
|
||||
.index(2)
|
||||
.include_header_row(false)
|
||||
.execute()?;
|
||||
|
||||
assert_eq!(expected, got);
|
||||
Ok(())
|
||||
}
|
||||
Loading…
Add table
Add a link
Reference in a new issue