initial commit

This commit is contained in:
sreedev
2022-12-24 18:45:16 -05:00
commit 3b06c0851f
9 changed files with 838 additions and 0 deletions

1
.gitignore vendored Normal file
View File

@@ -0,0 +1 @@
/target

653
Cargo.lock generated Normal file
View File

@@ -0,0 +1,653 @@
# This file is automatically @generated by Cargo.
# It is not intended for manual editing.
version = 3
[[package]]
name = "anyhow"
version = "1.0.68"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "2cb2f989d18dd141ab8ae82f64d1a8cdd37e0840f73a406896cf5e99502fab61"
[[package]]
name = "autocfg"
version = "1.1.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d468802bab17cbc0cc575e9b053f41e72aa36bfa6b7f55e3529ffa43161b97fa"
[[package]]
name = "bitflags"
version = "1.3.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "bef38d45163c2f1dde094a7dfd33ccf595c92905c8f8f4fdc18d06fb1037718a"
[[package]]
name = "block-buffer"
version = "0.9.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "4152116fd6e9dadb291ae18fc1ec3575ed6d84c29642d97890f4b4a3417297e4"
dependencies = [
"generic-array",
]
[[package]]
name = "bytes"
version = "1.3.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "dfb24e866b15a1af2a1b663f10c6b6b8f397a84aadb828f12e5b289ec23a3a3c"
[[package]]
name = "cc"
version = "1.0.78"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "a20104e2335ce8a659d6dd92a51a767a0c062599c73b343fd152cb401e828c3d"
[[package]]
name = "cfg-if"
version = "1.0.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "baf1de4339761588bc0619e3cbc0120ee582ebb74b53b4efbf79117bd2da40fd"
[[package]]
name = "clap"
version = "4.0.32"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "a7db700bc935f9e43e88d00b0850dae18a63773cfbec6d8e070fccf7fef89a39"
dependencies = [
"bitflags",
"clap_derive",
"clap_lex",
"is-terminal",
"once_cell",
"strsim",
"termcolor",
]
[[package]]
name = "clap_derive"
version = "4.0.21"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "0177313f9f02afc995627906bbd8967e2be069f5261954222dac78290c2b9014"
dependencies = [
"heck",
"proc-macro-error",
"proc-macro2",
"quote",
"syn",
]
[[package]]
name = "clap_lex"
version = "0.3.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "0d4198f73e42b4936b35b5bb248d81d2b595ecb170da0bac7655c54eedfa8da8"
dependencies = [
"os_str_bytes",
]
[[package]]
name = "cpufeatures"
version = "0.2.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "28d997bd5e24a5928dd43e46dc529867e207907fe0b239c3477d924f7f2ca320"
dependencies = [
"libc",
]
[[package]]
name = "deduplicator"
version = "0.0.1"
dependencies = [
"anyhow",
"clap",
"glob",
"md5",
"sha256",
"sqlite",
"thiserror",
"tokio",
]
[[package]]
name = "digest"
version = "0.9.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d3dd60d1080a57a05ab032377049e0591415d2b31afd7028356dbf3cc6dcb066"
dependencies = [
"generic-array",
]
[[package]]
name = "errno"
version = "0.2.8"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "f639046355ee4f37944e44f60642c6f3a7efa3cf6b78c78a0d989a8ce6c396a1"
dependencies = [
"errno-dragonfly",
"libc",
"winapi",
]
[[package]]
name = "errno-dragonfly"
version = "0.1.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "aa68f1b12764fab894d2755d2518754e71b4fd80ecfb822714a1206c2aab39bf"
dependencies = [
"cc",
"libc",
]
[[package]]
name = "generic-array"
version = "0.14.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "bff49e947297f3312447abdca79f45f4738097cc82b06e72054d2223f601f1b9"
dependencies = [
"typenum",
"version_check",
]
[[package]]
name = "glob"
version = "0.3.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9b919933a397b79c37e33b77bb2aa3dc8eb6e165ad809e58ff75bc7db2e34574"
[[package]]
name = "heck"
version = "0.4.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "2540771e65fc8cb83cd6e8a237f70c319bd5c29f78ed1084ba5d50eeac86f7f9"
[[package]]
name = "hermit-abi"
version = "0.2.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ee512640fe35acbfb4bb779db6f0d80704c2cacfa2e39b601ef3e3f47d1ae4c7"
dependencies = [
"libc",
]
[[package]]
name = "hex"
version = "0.4.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7f24254aa9a54b5c858eaee2f5bccdb46aaf0e486a595ed5fd8f86ba55232a70"
[[package]]
name = "io-lifetimes"
version = "1.0.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "46112a93252b123d31a119a8d1a1ac19deac4fac6e0e8b0df58f0d4e5870e63c"
dependencies = [
"libc",
"windows-sys",
]
[[package]]
name = "is-terminal"
version = "0.4.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "28dfb6c8100ccc63462345b67d1bbc3679177c75ee4bf59bf29c8b1d110b8189"
dependencies = [
"hermit-abi",
"io-lifetimes",
"rustix",
"windows-sys",
]
[[package]]
name = "libc"
version = "0.2.139"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "201de327520df007757c1f0adce6e827fe8562fbc28bfd9c15571c66ca1f5f79"
[[package]]
name = "linux-raw-sys"
version = "0.1.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "f051f77a7c8e6957c0696eac88f26b0117e54f52d3fc682ab19397a8812846a4"
[[package]]
name = "lock_api"
version = "0.4.9"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "435011366fe56583b16cf956f9df0095b405b82d76425bc8981c0e22e60ec4df"
dependencies = [
"autocfg",
"scopeguard",
]
[[package]]
name = "log"
version = "0.4.17"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "abb12e687cfb44aa40f41fc3978ef76448f9b6038cad6aef4259d3c095a2382e"
dependencies = [
"cfg-if",
]
[[package]]
name = "md5"
version = "0.7.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "490cc448043f947bae3cbee9c203358d62dbee0db12107a74be5c30ccfd09771"
[[package]]
name = "memchr"
version = "2.5.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "2dffe52ecf27772e601905b7522cb4ef790d2cc203488bbd0e2fe85fcb74566d"
[[package]]
name = "mio"
version = "0.8.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e5d732bc30207a6423068df043e3d02e0735b155ad7ce1a6f76fe2baa5b158de"
dependencies = [
"libc",
"log",
"wasi",
"windows-sys",
]
[[package]]
name = "num_cpus"
version = "1.15.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "0fac9e2da13b5eb447a6ce3d392f23a29d8694bff781bf03a16cd9ac8697593b"
dependencies = [
"hermit-abi",
"libc",
]
[[package]]
name = "once_cell"
version = "1.16.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "86f0b0d4bf799edbc74508c1e8bf170ff5f41238e5f8225603ca7caaae2b7860"
[[package]]
name = "opaque-debug"
version = "0.3.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "624a8340c38c1b80fd549087862da4ba43e08858af025b236e509b6649fc13d5"
[[package]]
name = "os_str_bytes"
version = "6.4.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9b7820b9daea5457c9f21c69448905d723fbd21136ccf521748f23fd49e723ee"
[[package]]
name = "parking_lot"
version = "0.12.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "3742b2c103b9f06bc9fff0a37ff4912935851bee6d36f3c02bcc755bcfec228f"
dependencies = [
"lock_api",
"parking_lot_core",
]
[[package]]
name = "parking_lot_core"
version = "0.9.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7ff9f3fef3968a3ec5945535ed654cb38ff72d7495a25619e2247fb15a2ed9ba"
dependencies = [
"cfg-if",
"libc",
"redox_syscall",
"smallvec",
"windows-sys",
]
[[package]]
name = "pin-project-lite"
version = "0.2.9"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e0a7ae3ac2f1173085d398531c705756c94a4c56843785df85a60c1a0afac116"
[[package]]
name = "pkg-config"
version = "0.3.26"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "6ac9a59f73473f1b8d852421e59e64809f025994837ef743615c6d0c5b305160"
[[package]]
name = "proc-macro-error"
version = "1.0.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "da25490ff9892aab3fcf7c36f08cfb902dd3e71ca0f9f9517bea02a73a5ce38c"
dependencies = [
"proc-macro-error-attr",
"proc-macro2",
"quote",
"syn",
"version_check",
]
[[package]]
name = "proc-macro-error-attr"
version = "1.0.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "a1be40180e52ecc98ad80b184934baf3d0d29f979574e439af5a55274b35f869"
dependencies = [
"proc-macro2",
"quote",
"version_check",
]
[[package]]
name = "proc-macro2"
version = "1.0.49"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "57a8eca9f9c4ffde41714334dee777596264c7825420f521abc92b5b5deb63a5"
dependencies = [
"unicode-ident",
]
[[package]]
name = "quote"
version = "1.0.23"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "8856d8364d252a14d474036ea1358d63c9e6965c8e5c1885c18f73d70bff9c7b"
dependencies = [
"proc-macro2",
]
[[package]]
name = "redox_syscall"
version = "0.2.16"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "fb5a58c1855b4b6819d59012155603f0b22ad30cad752600aadfcb695265519a"
dependencies = [
"bitflags",
]
[[package]]
name = "rustix"
version = "0.36.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "a3807b5d10909833d3e9acd1eb5fb988f79376ff10fce42937de71a449c4c588"
dependencies = [
"bitflags",
"errno",
"io-lifetimes",
"libc",
"linux-raw-sys",
"windows-sys",
]
[[package]]
name = "scopeguard"
version = "1.1.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d29ab0c6d3fc0ee92fe66e2d99f700eab17a8d57d1c1d3b748380fb20baa78cd"
[[package]]
name = "sha2"
version = "0.9.9"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "4d58a1e1bf39749807d89cf2d98ac2dfa0ff1cb3faa38fbb64dd88ac8013d800"
dependencies = [
"block-buffer",
"cfg-if",
"cpufeatures",
"digest",
"opaque-debug",
]
[[package]]
name = "sha256"
version = "1.1.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e334db67871c14c18fc066ad14af13f9fdf5f9a91c61af432d1e3a39c8c6a141"
dependencies = [
"hex",
"sha2",
]
[[package]]
name = "signal-hook-registry"
version = "1.4.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e51e73328dc4ac0c7ccbda3a494dfa03df1de2f46018127f60c693f2648455b0"
dependencies = [
"libc",
]
[[package]]
name = "smallvec"
version = "1.10.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "a507befe795404456341dfab10cef66ead4c041f62b8b11bbb92bffe5d0953e0"
[[package]]
name = "socket2"
version = "0.4.7"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "02e2d2db9033d13a1567121ddd7a095ee144db4e1ca1b1bda3419bc0da294ebd"
dependencies = [
"libc",
"winapi",
]
[[package]]
name = "sqlite"
version = "0.30.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "12e072cb5fb89b3fe5e9c9584676348feb503f9fb3ae829d9868171bc5372d48"
dependencies = [
"libc",
"sqlite3-sys",
]
[[package]]
name = "sqlite3-src"
version = "0.4.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d1815a7a02c996eb8e5c64f61fcb6fd9b12e593ce265c512c5853b2513635691"
dependencies = [
"cc",
"pkg-config",
]
[[package]]
name = "sqlite3-sys"
version = "0.14.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d47c99824fc55360ba00caf28de0b8a0458369b832e016a64c13af0ad9fbb9ee"
dependencies = [
"libc",
"sqlite3-src",
]
[[package]]
name = "strsim"
version = "0.10.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "73473c0e59e6d5812c5dfe2a064a6444949f089e20eec9a2e5506596494e4623"
[[package]]
name = "syn"
version = "1.0.107"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "1f4064b5b16e03ae50984a5a8ed5d4f8803e6bc1fd170a3cda91a1be4b18e3f5"
dependencies = [
"proc-macro2",
"quote",
"unicode-ident",
]
[[package]]
name = "termcolor"
version = "1.1.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "bab24d30b911b2376f3a13cc2cd443142f0c81dda04c118693e35b3835757755"
dependencies = [
"winapi-util",
]
[[package]]
name = "thiserror"
version = "1.0.38"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "6a9cd18aa97d5c45c6603caea1da6628790b37f7a34b6ca89522331c5180fed0"
dependencies = [
"thiserror-impl",
]
[[package]]
name = "thiserror-impl"
version = "1.0.38"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "1fb327af4685e4d03fa8cbcf1716380da910eeb2bb8be417e7f9fd3fb164f36f"
dependencies = [
"proc-macro2",
"quote",
"syn",
]
[[package]]
name = "tokio"
version = "1.23.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "eab6d665857cc6ca78d6e80303a02cea7a7851e85dfbd77cbdc09bd129f1ef46"
dependencies = [
"autocfg",
"bytes",
"libc",
"memchr",
"mio",
"num_cpus",
"parking_lot",
"pin-project-lite",
"signal-hook-registry",
"socket2",
"tokio-macros",
"windows-sys",
]
[[package]]
name = "tokio-macros"
version = "1.8.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d266c00fde287f55d3f1c3e96c500c362a2b8c695076ec180f27918820bc6df8"
dependencies = [
"proc-macro2",
"quote",
"syn",
]
[[package]]
name = "typenum"
version = "1.16.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "497961ef93d974e23eb6f433eb5fe1b7930b659f06d12dec6fc44a8f554c0bba"
[[package]]
name = "unicode-ident"
version = "1.0.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "84a22b9f218b40614adcb3f4ff08b703773ad44fa9423e4e0d346d5db86e4ebc"
[[package]]
name = "version_check"
version = "0.9.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "49874b5167b65d7193b8aba1567f5c7d93d001cafc34600cee003eda787e483f"
[[package]]
name = "wasi"
version = "0.11.0+wasi-snapshot-preview1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9c8d87e72b64a3b4db28d11ce29237c246188f4f51057d65a7eab63b7987e423"
[[package]]
name = "winapi"
version = "0.3.9"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "5c839a674fcd7a98952e593242ea400abe93992746761e38641405d28b00f419"
dependencies = [
"winapi-i686-pc-windows-gnu",
"winapi-x86_64-pc-windows-gnu",
]
[[package]]
name = "winapi-i686-pc-windows-gnu"
version = "0.4.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ac3b87c63620426dd9b991e5ce0329eff545bccbbb34f3be09ff6fb6ab51b7b6"
[[package]]
name = "winapi-util"
version = "0.1.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "70ec6ce85bb158151cae5e5c87f95a8e97d2c0c4b001223f33a334e3ce5de178"
dependencies = [
"winapi",
]
[[package]]
name = "winapi-x86_64-pc-windows-gnu"
version = "0.4.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "712e227841d057c1ee1cd2fb22fa7e5a5461ae8e48fa2ca79ec42cfc1931183f"
[[package]]
name = "windows-sys"
version = "0.42.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "5a3e1820f08b8513f676f7ab6c1f99ff312fb97b553d30ff4dd86f9f15728aa7"
dependencies = [
"windows_aarch64_gnullvm",
"windows_aarch64_msvc",
"windows_i686_gnu",
"windows_i686_msvc",
"windows_x86_64_gnu",
"windows_x86_64_gnullvm",
"windows_x86_64_msvc",
]
[[package]]
name = "windows_aarch64_gnullvm"
version = "0.42.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "41d2aa71f6f0cbe00ae5167d90ef3cfe66527d6f613ca78ac8024c3ccab9a19e"
[[package]]
name = "windows_aarch64_msvc"
version = "0.42.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "dd0f252f5a35cac83d6311b2e795981f5ee6e67eb1f9a7f64eb4500fbc4dcdb4"
[[package]]
name = "windows_i686_gnu"
version = "0.42.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "fbeae19f6716841636c28d695375df17562ca208b2b7d0dc47635a50ae6c5de7"
[[package]]
name = "windows_i686_msvc"
version = "0.42.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "84c12f65daa39dd2babe6e442988fc329d6243fdce47d7d2d155b8d874862246"
[[package]]
name = "windows_x86_64_gnu"
version = "0.42.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "bf7b1b21b5362cbc318f686150e5bcea75ecedc74dd157d874d754a2ca44b0ed"
[[package]]
name = "windows_x86_64_gnullvm"
version = "0.42.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "09d525d2ba30eeb3297665bd434a54297e4170c7f1a44cad4ef58095b4cd2028"
[[package]]
name = "windows_x86_64_msvc"
version = "0.42.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "f40009d85759725a34da6d89a94e63d7bdc50a862acf0dbc7c8e488f1edcb6f5"

16
Cargo.toml Normal file
View File

@@ -0,0 +1,16 @@
[package]
name = "deduplicator"
version = "0.0.1"
edition = "2021"
# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
[dependencies]
anyhow = "1.0.68"
clap = { version = "4.0.32", features = ["derive"] }
glob = "0.3.0"
md5 = "0.7.0"
sha256 = "1.1.1"
sqlite = "0.30.3"
thiserror = "1.0.38"
tokio = { version = "1.23.0", features = ["full"] }

16
src/cli.rs Normal file
View File

@@ -0,0 +1,16 @@
use std::path::PathBuf;
use clap::Parser;
#[derive(Parser, Debug)]
#[command(author, version, about, long_about = None)]
pub struct App {
/// Filetypes to deduplicate (default = all)
#[arg(short, long)]
pub filetypes: Option<String>,
/// List duplcates without deleting (default = true)
#[arg(short, long)]
pub dry: bool,
/// Run Deduplicator on dir different from pwd
#[arg(long)]
pub dir: Option<PathBuf>
}

71
src/database.rs Normal file
View File

@@ -0,0 +1,71 @@
use anyhow::{anyhow, Result};
#[derive(Debug)]
pub struct File {
pub path: String,
pub hash: String,
}
pub fn setup() -> Result<()> {
let connection = sqlite::open(":memory:")?;
let query = "CREATE TABLE files (file_identifier STRING, hash STRING)";
match connection.execute(query) {
Ok(_) => Ok(()),
Err(e) => Err(anyhow!("Database Setup Failed! {}", e)),
}
}
pub fn put(file: File) -> Result<()> {
let connection = sqlite::open(":memory:")?;
let query = format!(
"INSERT INTO files (file_identifier, hash) VALUES ({}, {})",
file.path, file.hash
);
let result = connection.execute(query)?;
Ok(result)
}
pub fn duplicate_hashes() -> Result<Vec<File>> {
let connection = sqlite::open(":memory:")?;
let query = format!(
"
SELECT a.* FROM files a
JOIN (SELECT file_identifier, hash, COUNT(*)
FROM files
GROUP BY hash
HAVING count(*) > 1 ) b
ON a.file_identifier = b.file_identifier
ORDER BY a.file_identifier
"
);
let result: Vec<File> = connection
.prepare(query)?
.into_iter()
.map(|row_result| row_result.unwrap())
.map(|row| {
let path = row.read::<&str, _>("file_identifier").to_string();
let hash = row.read::<&str, _>("hash").to_string();
File { path, hash }
})
.collect();
Ok(result)
}
pub fn lookup(hash: &str) -> Result<Vec<File>> {
let connection = sqlite::open(":memory:")?;
let result_set = connection
.prepare("SELECT * FROM files WHERE hash = ?")?
.into_iter()
.bind((1, hash))?
.map(|row| row.unwrap())
.map(|row| {
let path = row.read::<&str, _>("file_identifier").to_owned();
let hash = row.read::<&str, _>("hash").to_owned();
File { path, hash }
})
.collect::<Vec<File>>();
Ok(result_set)
}

15
src/main.rs Normal file
View File

@@ -0,0 +1,15 @@
mod database;
mod scanner;
mod cli;
use clap::Parser;
use anyhow::Result;
#[tokio::main]
async fn main() -> Result<()> {
database::setup()?;
let duplicates = scanner::duplicates(cli::App::parse())?;
dbg!(duplicates);
Ok(())
}

66
src/scanner.rs Normal file
View File

@@ -0,0 +1,66 @@
use std::path::PathBuf;
use crate::{cli::App, database::File};
use crate::database;
use anyhow::Result;
use glob::glob;
use std::{fs, io};
pub fn duplicates(app_opts: App) -> Result<Vec<File>> {
index_files(scan(app_opts)?);
database::duplicate_hashes()
}
fn scan(app_opts: App) -> Result<Vec<String>> {
let directory: String = app_opts
.dir
.unwrap_or(std::env::current_dir()?)
.as_os_str()
.to_str()
.unwrap()
.to_string();
let glob_patterns: Vec<PathBuf> = app_opts
.filetypes
.unwrap_or(String::from("*"))
.split(",")
.map(|filetype| format!("*.{}", filetype))
.map(|filetype| {
vec![directory.clone(), String::from("**"), filetype]
.iter()
.collect()
})
.collect();
let files: Vec<String> = glob_patterns
.into_iter()
.map(|glob_pattern| glob(&glob_pattern.as_os_str().to_str().unwrap()))
.map(|glob_result| glob_result.unwrap())
.flat_map(|file_vec| {
file_vec
.map(|x| x.unwrap().as_os_str().to_str().unwrap().to_string())
.collect::<Vec<String>>()
})
.collect();
Ok(files)
}
fn index_files(files: Vec<String>) {
files
.into_iter()
.map(|file| {
let hash = hash_file(&file).unwrap();
database::File { path: file, hash }
})
.for_each(|file| {
database::put(file).unwrap();
});
}
pub fn hash_file(filepath: &str) -> Result<String> {
let file = fs::read(filepath)?;
let hash = sha256::digest(&*file);
Ok(hash)
}

Binary file not shown.

After

Width:  |  Height:  |  Size: 63 KiB

BIN
test_data/bidsgbp.png Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 63 KiB