mirror of
https://github.com/sreedevk/deduplicator.git
synced 2026-08-26 10:05:32 +00:00
Compare commits
56 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
163e8d85c0 | ||
|
|
b1c508e9e7 | ||
|
|
4125b18d67 | ||
|
|
10329015f7 | ||
|
|
de6d2e325e | ||
|
|
850c274adc | ||
|
|
31d35aae51 | ||
|
|
087f36ac52 | ||
|
|
6f8b1d55df | ||
|
|
c6318a310b | ||
|
|
76c69ef8a0 | ||
|
|
fd4e882aa8 | ||
|
|
fd1d214d62 | ||
|
|
1a573fbf3f | ||
|
|
b12b662ba1 | ||
|
|
96337b6b48 | ||
|
|
02f70aa55f | ||
|
|
4a18b3fd91 | ||
|
|
876fdc69ac | ||
|
|
8acc3f8c8f | ||
|
|
38f6c48452 | ||
|
|
3e1e9c0e2e | ||
|
|
0674ab55bf | ||
|
|
ccff95dfc5 | ||
|
|
53d28abb62 | ||
|
|
ea6cf94952 | ||
|
|
7b275d40d0 | ||
|
|
30398c3ca9 | ||
|
|
c0042fc9f7 | ||
|
|
5aea0eb6f4 | ||
|
|
f0ff1ec325 | ||
|
|
b267fcdedf | ||
|
|
84b194efca | ||
|
|
d162ca98ef | ||
|
|
dfb73ceb5c | ||
|
|
72ca7c7a44 | ||
|
|
2f3cfd3162 | ||
|
|
9b1f591c20 | ||
|
|
e24603c645 | ||
|
|
0e624b042d | ||
|
|
e61d1f1475 | ||
|
|
8c76c6a3c8 | ||
|
|
df3bea3d4f | ||
|
|
7ace0bde63 | ||
|
|
70de402eab | ||
|
|
01dd93a0ea | ||
|
|
8ac78fb856 | ||
|
|
37a4c4d52d | ||
|
|
1ea5705474 | ||
|
|
ea748c60d8 | ||
|
|
51f5f8e61a | ||
|
|
175c7579c4 | ||
|
|
81c96ce3b8 | ||
|
|
0031891b8b | ||
|
|
ae87e4e830 | ||
|
|
284e168453 |
31
.github/workflows/release.yml
vendored
Normal file
31
.github/workflows/release.yml
vendored
Normal file
@@ -0,0 +1,31 @@
|
||||
name: Release
|
||||
|
||||
env:
|
||||
PROJECT_NAME: deduplicator
|
||||
PROJECT_DESC: "Filter, Sort & Delete Duplicate Files Recursively"
|
||||
PROJECT_AUTH: "sreedevk"
|
||||
|
||||
on:
|
||||
release:
|
||||
types:
|
||||
- created
|
||||
|
||||
jobs:
|
||||
upload-assets:
|
||||
strategy:
|
||||
matrix:
|
||||
os:
|
||||
- ubuntu-latest
|
||||
- macos-latest
|
||||
- windows-latest
|
||||
runs-on: ${{ matrix.os }}
|
||||
steps:
|
||||
- uses: actions/checkout@v3
|
||||
- uses: taiki-e/upload-rust-binary-action@v1
|
||||
with:
|
||||
bin: deduplicator
|
||||
tar: unix
|
||||
zip: windows
|
||||
token: ${{ secrets.GITHUB_TOKEN }}
|
||||
env:
|
||||
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
|
||||
1
.gitignore
vendored
1
.gitignore
vendored
@@ -1,2 +1,3 @@
|
||||
/target
|
||||
/test_data
|
||||
.envrc
|
||||
|
||||
@@ -12,6 +12,7 @@
|
||||
* Assign the Issue to yourself (if unassigned) before you start working in order to avoid any conficts.
|
||||
* Open a new GitHub pull request with the patch.
|
||||
* Ensure the PR description clearly describes the problem and solution. Include the relevant issue number.
|
||||
* Make sure that the PR points to the development branch.
|
||||
|
||||
#### **Did you fix whitespace, format code, or make a purely cosmetic patch?**
|
||||
|
||||
|
||||
274
Cargo.lock
generated
274
Cargo.lock
generated
@@ -2,6 +2,15 @@
|
||||
# It is not intended for manual editing.
|
||||
version = 3
|
||||
|
||||
[[package]]
|
||||
name = "aho-corasick"
|
||||
version = "0.7.20"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "cc936419f96fa211c1b9166887b38e5e40b19958e5b895be7c1f93adec7071ac"
|
||||
dependencies = [
|
||||
"memchr",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "android_system_properties"
|
||||
version = "0.1.5"
|
||||
@@ -52,6 +61,16 @@ dependencies = [
|
||||
"serde",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "bstr"
|
||||
version = "1.1.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "b45ea9b00a7b3f2988e9a65ad3917e62123c38dba709b666506207be96d1790b"
|
||||
dependencies = [
|
||||
"memchr",
|
||||
"serde",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "bumpalo"
|
||||
version = "3.11.1"
|
||||
@@ -71,10 +90,10 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "dfb24e866b15a1af2a1b663f10c6b6b8f397a84aadb828f12e5b289ec23a3a3c"
|
||||
|
||||
[[package]]
|
||||
name = "cassowary"
|
||||
version = "0.3.0"
|
||||
name = "bytesize"
|
||||
version = "1.1.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "df8670b8c7b9dae1793364eafadf7239c40d669904660c5960d74cfd80b46a53"
|
||||
checksum = "6c58ec36aac5066d5ca17df51b3e70279f5670a72102f5752cb7e7c856adfc70"
|
||||
|
||||
[[package]]
|
||||
name = "cc"
|
||||
@@ -223,38 +242,13 @@ dependencies = [
|
||||
"cfg-if",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "crossterm"
|
||||
version = "0.25.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "e64e6c0fbe2c17357405f7c758c1ef960fce08bdfb2c03d88d2a18d7e09c4b67"
|
||||
dependencies = [
|
||||
"bitflags",
|
||||
"crossterm_winapi",
|
||||
"libc",
|
||||
"mio",
|
||||
"parking_lot",
|
||||
"signal-hook",
|
||||
"signal-hook-mio",
|
||||
"winapi",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "crossterm_winapi"
|
||||
version = "0.9.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "2ae1b35a484aa10e07fe0638d02301c5ad24de82d310ccbd2f3693da5f09bf1c"
|
||||
dependencies = [
|
||||
"winapi",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "csv"
|
||||
version = "1.1.6"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "22813a6dc45b335f9bade10bf7271dc477e81113e89eb251a0bc2a8a81c536e1"
|
||||
dependencies = [
|
||||
"bstr",
|
||||
"bstr 0.2.17",
|
||||
"csv-core",
|
||||
"itoa",
|
||||
"ryu",
|
||||
@@ -314,26 +308,39 @@ dependencies = [
|
||||
"syn",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "dashmap"
|
||||
version = "5.4.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "907076dfda823b0b36d2a1bb5f90c96660a5bbcd7729e10727f07858f22c4edc"
|
||||
dependencies = [
|
||||
"cfg-if",
|
||||
"hashbrown",
|
||||
"lock_api",
|
||||
"once_cell",
|
||||
"parking_lot_core",
|
||||
"rayon",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "deduplicator"
|
||||
version = "0.0.9"
|
||||
version = "0.1.4"
|
||||
dependencies = [
|
||||
"anyhow",
|
||||
"bytesize",
|
||||
"chrono",
|
||||
"clap",
|
||||
"colored",
|
||||
"crossterm",
|
||||
"dashmap",
|
||||
"fxhash",
|
||||
"glob",
|
||||
"humansize",
|
||||
"globwalk",
|
||||
"indicatif",
|
||||
"itertools",
|
||||
"memmap2",
|
||||
"prettytable-rs",
|
||||
"rayon",
|
||||
"sqlite",
|
||||
"thiserror",
|
||||
"tokio",
|
||||
"tui",
|
||||
"unicode-segmentation",
|
||||
]
|
||||
|
||||
@@ -397,6 +404,12 @@ dependencies = [
|
||||
"libc",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "fnv"
|
||||
version = "1.0.7"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "3f9eec918d3f24069decb9af1554cad7c880e2da24a9afd88aca000531ab82c1"
|
||||
|
||||
[[package]]
|
||||
name = "fxhash"
|
||||
version = "0.2.1"
|
||||
@@ -418,10 +431,34 @@ dependencies = [
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "glob"
|
||||
version = "0.3.0"
|
||||
name = "globset"
|
||||
version = "0.4.10"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "9b919933a397b79c37e33b77bb2aa3dc8eb6e165ad809e58ff75bc7db2e34574"
|
||||
checksum = "029d74589adefde59de1a0c4f4732695c32805624aec7b68d91503d4dba79afc"
|
||||
dependencies = [
|
||||
"aho-corasick",
|
||||
"bstr 1.1.0",
|
||||
"fnv",
|
||||
"log",
|
||||
"regex",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "globwalk"
|
||||
version = "0.8.1"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "93e3af942408868f6934a7b85134a3230832b9977cf66125df2f9edcfce4ddcc"
|
||||
dependencies = [
|
||||
"bitflags",
|
||||
"ignore",
|
||||
"walkdir",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "hashbrown"
|
||||
version = "0.12.3"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "8a9ee70c43aaf417c914396645a0fa852624801b24ebb7ae78fe8272889ac888"
|
||||
|
||||
[[package]]
|
||||
name = "heck"
|
||||
@@ -447,15 +484,6 @@ dependencies = [
|
||||
"libc",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "humansize"
|
||||
version = "2.1.2"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "4e682e2bd70ecbcce5209f11a992a4ba001fea8e60acf7860ce007629e6d2756"
|
||||
dependencies = [
|
||||
"libm",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "iana-time-zone"
|
||||
version = "0.1.53"
|
||||
@@ -480,6 +508,23 @@ dependencies = [
|
||||
"cxx-build",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "ignore"
|
||||
version = "0.4.20"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "dbe7873dab538a9a44ad79ede1faf5f30d49f9a5c883ddbab48bce81b64b7492"
|
||||
dependencies = [
|
||||
"globset",
|
||||
"lazy_static",
|
||||
"log",
|
||||
"memchr",
|
||||
"regex",
|
||||
"same-file",
|
||||
"thread_local",
|
||||
"walkdir",
|
||||
"winapi-util",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "indicatif"
|
||||
version = "0.17.2"
|
||||
@@ -552,12 +597,6 @@ version = "0.2.139"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "201de327520df007757c1f0adce6e827fe8562fbc28bfd9c15571c66ca1f5f79"
|
||||
|
||||
[[package]]
|
||||
name = "libm"
|
||||
version = "0.2.6"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "348108ab3fba42ec82ff6e9564fc4ca0247bdccdc68dd8af9764bbc79c3c8ffb"
|
||||
|
||||
[[package]]
|
||||
name = "link-cplusplus"
|
||||
version = "1.0.8"
|
||||
@@ -598,6 +637,15 @@ version = "2.5.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "2dffe52ecf27772e601905b7522cb4ef790d2cc203488bbd0e2fe85fcb74566d"
|
||||
|
||||
[[package]]
|
||||
name = "memmap2"
|
||||
version = "0.5.8"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "4b182332558b18d807c4ce1ca8ca983b34c3ee32765e47b3f0f69b90355cc1dc"
|
||||
dependencies = [
|
||||
"libc",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "memoffset"
|
||||
version = "0.7.1"
|
||||
@@ -695,12 +743,6 @@ 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 = "portable-atomic"
|
||||
version = "0.3.19"
|
||||
@@ -805,12 +847,29 @@ dependencies = [
|
||||
"thiserror",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "regex"
|
||||
version = "1.7.1"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "48aaa5748ba571fb95cd2c85c09f629215d3a6ece942baa100950af03a34f733"
|
||||
dependencies = [
|
||||
"aho-corasick",
|
||||
"memchr",
|
||||
"regex-syntax",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "regex-automata"
|
||||
version = "0.1.10"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "6c230d73fb8d8c1b9c0b3135c5142a8acee3a0558fb8db5cf1cb65f8d7862132"
|
||||
|
||||
[[package]]
|
||||
name = "regex-syntax"
|
||||
version = "0.6.28"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "456c603be3e8d448b072f410900c09faf164fbce2d480456f50eea6e25f9c848"
|
||||
|
||||
[[package]]
|
||||
name = "rustix"
|
||||
version = "0.36.5"
|
||||
@@ -837,6 +896,15 @@ version = "1.0.12"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "7b4b9743ed687d4b4bcedf9ff5eaa7398495ae14e61cba0a295704edbc7decde"
|
||||
|
||||
[[package]]
|
||||
name = "same-file"
|
||||
version = "1.0.6"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "93fc1dc3aaa9bfed95e02e6eadabb4baf7e3078b0bd1b4d7b6b0b68378900502"
|
||||
dependencies = [
|
||||
"winapi-util",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "scopeguard"
|
||||
version = "1.1.0"
|
||||
@@ -855,27 +923,6 @@ version = "1.0.152"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "bb7d1f0d3021d347a83e556fc4683dea2ea09d87bccdf88ff5c12545d89d5efb"
|
||||
|
||||
[[package]]
|
||||
name = "signal-hook"
|
||||
version = "0.3.14"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "a253b5e89e2698464fc26b545c9edceb338e18a89effeeecfea192c3025be29d"
|
||||
dependencies = [
|
||||
"libc",
|
||||
"signal-hook-registry",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "signal-hook-mio"
|
||||
version = "0.2.3"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "29ad2e15f37ec9a6cc544097b78a1ec90001e9f71b81338ca39f430adaca99af"
|
||||
dependencies = [
|
||||
"libc",
|
||||
"mio",
|
||||
"signal-hook",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "signal-hook-registry"
|
||||
version = "1.4.0"
|
||||
@@ -901,36 +948,6 @@ dependencies = [
|
||||
"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"
|
||||
@@ -988,6 +1005,15 @@ dependencies = [
|
||||
"syn",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "thread_local"
|
||||
version = "1.1.4"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "5516c27b78311c50bf42c071425c560ac799b11c30b31f87e3081965fe5e0180"
|
||||
dependencies = [
|
||||
"once_cell",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "time"
|
||||
version = "0.1.45"
|
||||
@@ -1001,9 +1027,9 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "tokio"
|
||||
version = "1.23.0"
|
||||
version = "1.23.1"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "eab6d665857cc6ca78d6e80303a02cea7a7851e85dfbd77cbdc09bd129f1ef46"
|
||||
checksum = "38a54aca0c15d014013256222ba0ebed095673f89345dd79119d912eb561b7a8"
|
||||
dependencies = [
|
||||
"autocfg",
|
||||
"bytes",
|
||||
@@ -1030,19 +1056,6 @@ dependencies = [
|
||||
"syn",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "tui"
|
||||
version = "0.19.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "ccdd26cbd674007e649a272da4475fb666d3aa0ad0531da7136db6fab0e5bad1"
|
||||
dependencies = [
|
||||
"bitflags",
|
||||
"cassowary",
|
||||
"crossterm",
|
||||
"unicode-segmentation",
|
||||
"unicode-width",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "unicode-ident"
|
||||
version = "1.0.6"
|
||||
@@ -1067,6 +1080,17 @@ version = "0.9.4"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "49874b5167b65d7193b8aba1567f5c7d93d001cafc34600cee003eda787e483f"
|
||||
|
||||
[[package]]
|
||||
name = "walkdir"
|
||||
version = "2.3.2"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "808cf2735cd4b6866113f648b791c6adc5714537bc222d9347bb203386ffda56"
|
||||
dependencies = [
|
||||
"same-file",
|
||||
"winapi",
|
||||
"winapi-util",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "wasi"
|
||||
version = "0.10.0+wasi-snapshot-preview1"
|
||||
|
||||
19
Cargo.toml
19
Cargo.toml
@@ -1,28 +1,31 @@
|
||||
[package]
|
||||
name = "deduplicator"
|
||||
version = "0.0.9"
|
||||
version = "0.1.4"
|
||||
edition = "2021"
|
||||
description = "find,filter,delete Duplicates"
|
||||
license = "MIT"
|
||||
authors = ["Sreedev Kodichath <sreedevpadmakumar@gmail.com>", "Valentin Bersier <vbersier@gmail.com>", "Dhruva Sagar <dhruva.sagar@gmail.com>"]
|
||||
authors = [
|
||||
"Sreedev Kodichath <sreedevpadmakumar@gmail.com>",
|
||||
"Valentin Bersier <vbersier@gmail.com>",
|
||||
"Dhruva Sagar <dhruva.sagar@gmail.com>",
|
||||
]
|
||||
|
||||
# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
|
||||
|
||||
[dependencies]
|
||||
anyhow = "1.0.68"
|
||||
bytesize = "1.1.0"
|
||||
chrono = "0.4.23"
|
||||
clap = { version = "4.0.32", features = ["derive"] }
|
||||
colored = "2.0.0"
|
||||
crossterm = "0.25.0"
|
||||
dashmap = { version = "5.4.0", features = ["rayon"] }
|
||||
fxhash = "0.2.1"
|
||||
glob = "0.3.0"
|
||||
humansize = "2.1.2"
|
||||
globwalk = "0.8.1"
|
||||
indicatif = { version = "0.17.2", features = ["rayon", "tokio"] }
|
||||
itertools = "0.10.5"
|
||||
memmap2 = "0.5.8"
|
||||
prettytable-rs = "0.10.0"
|
||||
rayon = "1.6.1"
|
||||
sqlite = "0.30.3"
|
||||
thiserror = "1.0.38"
|
||||
tokio = { version = "1.23.0", features = ["full"] }
|
||||
tui = "0.19.0"
|
||||
tokio = { version = "1.23.1", features = ["full"] }
|
||||
unicode-segmentation = "1.10.0"
|
||||
|
||||
112
README.md
112
README.md
@@ -4,47 +4,97 @@
|
||||
Find, Sort, Filter & Delete duplicate files
|
||||
</p>
|
||||
|
||||
<p align="center">
|
||||
NOTE: This project is still being developed. At the moment, as shown in the screenshot below, deduplicator is able to scan through and list duplicates with and without caching. Contributions are welcome.
|
||||
</p>
|
||||
|
||||
<h2 align="center">Usage</h2>
|
||||
## Usage
|
||||
|
||||
```bash
|
||||
Usage: deduplicator [OPTIONS]
|
||||
|
||||
Options:
|
||||
-t, --types <TYPES> Filetypes to deduplicate (default = all)
|
||||
--dir <DIR> Run Deduplicator on dir different from pwd
|
||||
-n, --nocache Don't use cache for indexing files (default = false)
|
||||
-i, --interactive Delete files interactively
|
||||
-h, --help Print help information
|
||||
-V, --version Print version information
|
||||
-t, --types <TYPES> Filetypes to deduplicate (default = all)
|
||||
--dir <DIR> Run Deduplicator on dir different from pwd
|
||||
-i, --interactive Delete files interactively
|
||||
-m, --minsize <MINSIZE> Minimum filesize of duplicates to scan (e.g., 100B/1K/2M/3G/4T). [default = 0]
|
||||
-h, --help Print help information
|
||||
-V, --version Print version information
|
||||
```
|
||||
|
||||
<h2 align="center">Installation</h2>
|
||||
## Installation
|
||||
|
||||
<p align="center">Currently, deduplicator is only installable via rust's cargo package manager</p>
|
||||
### Cargo Install
|
||||
|
||||
#### Stable
|
||||
|
||||
```bash
|
||||
$ cargo install deduplicator
|
||||
```
|
||||
|
||||
#### Nightly
|
||||
|
||||
if you'd like to install with nightly features, you can use
|
||||
|
||||
```bash
|
||||
$ cargo install --git https://github.com/sreedevk/deduplicator
|
||||
```
|
||||
Please note that if you use a version manager to install rust (like asdf), you need to reshim (`asdf reshim rust`).
|
||||
|
||||
### Linux (Pre-built Binary)
|
||||
|
||||
you can download the pre-built binary from the [Releases](https://github.com/sreedevk/deduplicator/releases) page.
|
||||
download the `deduplicator-x86_64-unknown-linux-gnu.tar.gz` for linux. Once you have the tarball file with the executable,
|
||||
you can follow these steps to install:
|
||||
|
||||
```bash
|
||||
$ tar -zxvf deduplicator-x86_64-unknown-linux-gnu.tar.gz
|
||||
$ sudo mv deduplicator /usr/bin/
|
||||
```
|
||||
|
||||
### Mac OS (Pre-built Binary)
|
||||
|
||||
you can download the pre-build binary from the [Releases](https://github.com/sreedevk/deduplicator/releases) page.
|
||||
download the `deduplicator-x86_64-apple-darwin.tar.gz` tarball for mac os. Once you have the tarball file with the executable, you can follow these steps to install:
|
||||
|
||||
```bash
|
||||
$ tar -zxvf deduplicator-x86_64-unknown-linux-gnu.tar.gz
|
||||
$ sudo mv deduplicator /usr/bin/
|
||||
```
|
||||
|
||||
### Windows (Pre-built Binary)
|
||||
|
||||
you can download the pre-build binary from the [Releases](https://github.com/sreedevk/deduplicator/releases) page.
|
||||
download the `deduplicator-x86_64-pc-windows-msvc.zip` zip file for windows. unzip the `zip` file & move the `deduplicator.exe` to a location in the PATH system environment variable.
|
||||
|
||||
Note: If you Run into an msvc error, please install MSCV from [here](https://learn.microsoft.com/en-us/cpp/windows/latest-supported-vc-redist?view=msvc-170)
|
||||
|
||||
## Performance
|
||||
|
||||
Deduplicator uses size comparison and fxhash (a non non-cryptographic hashing algo) to quickly scan through large number of files to find duplicates. its also highly parallel (uses rayon and dashmap). I was able to scan through 120GB of files (Videos, PDFs, Images) in ~300ms. checkout the benchmarks
|
||||
|
||||
## benchmarks
|
||||
|
||||
| Command | Dirsize | Mean [ms] | Min [ms] | Max [ms] | Relative |
|
||||
|:---|:---|---:|---:|---:|---:|
|
||||
| `deduplicator --dir ~/Data/tmp` | (~120G) | 27.5 ± 1.0 | 26.0 | 32.1 | 1.70 ± 0.09 |
|
||||
| `deduplicator --dir ~/Data/books` | (~8.6G) | 21.8 ± 0.7 | 20.5 | 24.4 | 1.35 ± 0.07 |
|
||||
| `deduplicator --dir ~/Data/books --minsize 10M` | (~8.6G) | 16.1 ± 0.6 | 14.9 | 18.8 | 1.00 |
|
||||
| `deduplicator --dir ~/Data/ --types pdf,jpg,png,jpeg` | (~290G) | 1857.4 ± 24.5 | 1817.0 | 1895.5 | 115.07 ± 4.64 |
|
||||
|
||||
* The last entry is lower because of the number of files deduplicator had to go through (~660895 Files). The average size of the files rarely affect the performance of deduplicator.
|
||||
|
||||
These benchmarks were run using [hyperfine](https://github.com/sharkdp/hyperfine). Here are the specs of the machine used to benchmark deduplicator:
|
||||
|
||||
```
|
||||
cargo install deduplicator
|
||||
OS: Arch Linux x86_64
|
||||
Host: Precision 5540
|
||||
Kernel: 5.15.89-1-lts
|
||||
Uptime: 4 hours, 44 mins
|
||||
Shell: zsh 5.9
|
||||
Terminal: kitty
|
||||
CPU: Intel i9-9880H (16) @ 4.800GHz
|
||||
GPU: NVIDIA Quadro T2000 Mobile / Max-Q
|
||||
GPU: Intel CoffeeLake-H GT2 [UHD Graphics 630]
|
||||
Memory: 31731MiB (~32GiB)
|
||||
```
|
||||
<p align="center">
|
||||
note that if you use a version manager to install rust (like asdf), you need to reshim (`asdf reshim rust`).
|
||||
</p>
|
||||
|
||||
<h2 align="center">Performance</h2>
|
||||
|
||||
<p align="center">
|
||||
Deduplicator uses fxhash (a non-cryptographic hashing algorithm) which is extremely fast. As a result, deduplicator is able to process huge amounts of data in a couple of seconds.</p>
|
||||
|
||||
<p align="center">
|
||||
While testing, Deduplicator was able to go through 8.6GB of pdf files and detect duplicates in 2.9 seconds
|
||||
</p>
|
||||
|
||||
<h2 align="center">Screenshots</h2>
|
||||
|
||||
|
||||
<img src="https://user-images.githubusercontent.com/36154121/211948081-63c12b94-6251-487b-a49f-ac5418169d5a.gif" />
|
||||
<img src="https://user-images.githubusercontent.com/36154121/211458077-90092aa3-496c-492f-a061-618059890d5f.png" />
|
||||
## Screenshots
|
||||
|
||||
|
||||
|
||||
18
src/app.rs
Normal file
18
src/app.rs
Normal file
@@ -0,0 +1,18 @@
|
||||
use crate::output;
|
||||
use crate::params::Params;
|
||||
use crate::scanner;
|
||||
use anyhow::Result;
|
||||
|
||||
pub struct App;
|
||||
|
||||
impl App {
|
||||
pub fn init(app_args: &Params) -> Result<()> {
|
||||
let duplicates = scanner::duplicates(app_args)?;
|
||||
match app_args.interactive {
|
||||
true => output::interactive(duplicates, app_args),
|
||||
false => output::print(duplicates, app_args),
|
||||
}
|
||||
|
||||
Ok(())
|
||||
}
|
||||
}
|
||||
@@ -1,28 +0,0 @@
|
||||
use std::time::Duration;
|
||||
|
||||
use anyhow::Result;
|
||||
use crossterm::event::{self, KeyCode, KeyEvent};
|
||||
|
||||
use super::events;
|
||||
|
||||
pub struct EventHandler;
|
||||
|
||||
impl EventHandler {
|
||||
pub fn init() -> Result<events::Event> {
|
||||
if crossterm::event::poll(Duration::from_millis(10))? {
|
||||
match event::read()? {
|
||||
event::Event::Key(keycode) => Self::handle_keypress(keycode),
|
||||
_ => Ok(events::Event::Noop),
|
||||
}
|
||||
} else {
|
||||
Ok(events::Event::Noop)
|
||||
}
|
||||
}
|
||||
|
||||
fn handle_keypress(keyevent: KeyEvent) -> Result<events::Event> {
|
||||
match keyevent.code {
|
||||
KeyCode::Char('q') => Ok(events::Event::Exit),
|
||||
_ => Ok(events::Event::Noop),
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -1,4 +0,0 @@
|
||||
pub enum Event {
|
||||
Exit,
|
||||
Noop,
|
||||
}
|
||||
@@ -1,89 +0,0 @@
|
||||
#![allow(unused)]
|
||||
|
||||
mod event_handler;
|
||||
mod events;
|
||||
mod formatter;
|
||||
mod ui;
|
||||
pub mod file_manager;
|
||||
|
||||
use std::{io, thread, time::Duration};
|
||||
|
||||
use anyhow::{anyhow, Result};
|
||||
use crossterm::{event, execute, terminal};
|
||||
use event_handler::EventHandler;
|
||||
use tui::{
|
||||
backend::CrosstermBackend,
|
||||
widgets::{Block, Borders, Widget},
|
||||
Terminal,
|
||||
};
|
||||
use ui::Ui;
|
||||
|
||||
use crate::database;
|
||||
use crate::output;
|
||||
use crate::params::Params;
|
||||
use crate::scanner;
|
||||
|
||||
pub struct App;
|
||||
|
||||
impl App {
|
||||
pub fn init(app_args: &Params) -> Result<()> {
|
||||
// let mut term = Self::init_terminal()?;
|
||||
|
||||
let connection = database::get_connection(app_args)?;
|
||||
let duplicates = scanner::duplicates(app_args, &connection)?;
|
||||
|
||||
// Self::init_render_loop(&mut term)?;
|
||||
// Self::cleanup(&mut term)?;
|
||||
|
||||
match app_args.interactive {
|
||||
true => output::interactive(duplicates, app_args),
|
||||
false => output::print(duplicates, app_args) /* TODO: APP TUI INIT FUNCTION */
|
||||
}
|
||||
|
||||
Ok(())
|
||||
}
|
||||
|
||||
fn cleanup(term: &mut Terminal<CrosstermBackend<io::Stdout>>) -> Result<()> {
|
||||
terminal::disable_raw_mode()?;
|
||||
execute!(
|
||||
term.backend_mut(),
|
||||
terminal::LeaveAlternateScreen,
|
||||
event::DisableMouseCapture
|
||||
)?;
|
||||
|
||||
term.show_cursor()?;
|
||||
Ok(())
|
||||
}
|
||||
|
||||
fn render_cycle(term: &mut Terminal<CrosstermBackend<io::Stdout>>) -> Result<()> {
|
||||
match EventHandler::init()? {
|
||||
events::Event::Noop => Ui::render_frame(term),
|
||||
events::Event::Exit => Err(anyhow!("Exit")),
|
||||
}
|
||||
}
|
||||
|
||||
fn init_render_loop(term: &mut Terminal<CrosstermBackend<io::Stdout>>) -> Result<()> {
|
||||
// this could be simplified with a `while Self::render_cycle(term).is_ok() {}` in the current state, but maybe
|
||||
// it's good to keep it to handle errors in the future
|
||||
loop {
|
||||
match Self::render_cycle(term) {
|
||||
Ok(_) => continue,
|
||||
Err(_) => break,
|
||||
}
|
||||
}
|
||||
|
||||
Ok(())
|
||||
}
|
||||
|
||||
fn init_terminal() -> Result<Terminal<CrosstermBackend<io::Stdout>>> {
|
||||
terminal::enable_raw_mode()?;
|
||||
let mut stdout = io::stdout();
|
||||
execute!(
|
||||
stdout,
|
||||
terminal::EnterAlternateScreen,
|
||||
event::EnableMouseCapture
|
||||
)?;
|
||||
let backend = CrosstermBackend::new(stdout);
|
||||
Ok(Terminal::new(backend)?)
|
||||
}
|
||||
}
|
||||
@@ -1,54 +0,0 @@
|
||||
use std::io;
|
||||
|
||||
use anyhow::Result;
|
||||
use tui::{
|
||||
backend::{Backend, CrosstermBackend},
|
||||
layout::{Constraint, Direction, Layout, Rect},
|
||||
style::{Modifier, Style},
|
||||
text::{Span, Spans},
|
||||
widgets::{Block, Borders, List, ListItem, Widget},
|
||||
Frame, Terminal,
|
||||
};
|
||||
|
||||
pub struct Ui;
|
||||
|
||||
impl Ui {
|
||||
fn generate_file_list() -> impl Widget {
|
||||
let tasks: Vec<ListItem> = vec!["Sreedev"; 100]
|
||||
.into_iter()
|
||||
.map(|item| ListItem::new(vec![Spans::from(Span::raw(item))]))
|
||||
.collect();
|
||||
|
||||
List::new(tasks)
|
||||
.block(Block::default().borders(Borders::ALL).title("List"))
|
||||
.highlight_style(Style::default().add_modifier(Modifier::BOLD))
|
||||
.highlight_symbol("> ")
|
||||
}
|
||||
|
||||
fn generate_info_bar() -> impl Widget {
|
||||
Block::default().title("Description").borders(Borders::ALL)
|
||||
}
|
||||
|
||||
fn generate_file_desc() -> impl Widget {
|
||||
Block::default().title("Description").borders(Borders::ALL)
|
||||
}
|
||||
|
||||
pub fn render_frame(term: &mut Terminal<CrosstermBackend<io::Stdout>>) -> Result<()> {
|
||||
term.draw(|f| {
|
||||
let windows = Layout::default()
|
||||
.direction(Direction::Vertical)
|
||||
.constraints([Constraint::Ratio(2, 16), Constraint::Ratio(14, 16)].as_ref())
|
||||
.split(f.size());
|
||||
|
||||
let subwindows = Layout::default()
|
||||
.direction(Direction::Horizontal)
|
||||
.constraints([Constraint::Ratio(1, 4), Constraint::Ratio(3, 4)].as_ref())
|
||||
.split(windows[1]);
|
||||
|
||||
f.render_widget(Self::generate_info_bar(), windows[0]);
|
||||
f.render_widget(Self::generate_file_list(), subwindows[0]);
|
||||
f.render_widget(Self::generate_file_desc(), subwindows[1]);
|
||||
})?;
|
||||
Ok(())
|
||||
}
|
||||
}
|
||||
@@ -1,89 +0,0 @@
|
||||
use std::env::temp_dir;
|
||||
|
||||
use anyhow::Result;
|
||||
|
||||
use crate::params::Params;
|
||||
|
||||
#[derive(Debug, Clone)]
|
||||
pub struct File {
|
||||
pub path: String,
|
||||
pub hash: String,
|
||||
}
|
||||
|
||||
fn db_connection_url(args: &Params) -> String {
|
||||
match args.nocache {
|
||||
true => String::from(":memory:"),
|
||||
false => {
|
||||
let temp_dir_path = temp_dir();
|
||||
format!("{}/deduplicator.db", temp_dir_path.display())
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
pub fn get_connection(args: &Params) -> Result<sqlite::Connection, sqlite::Error> {
|
||||
sqlite::open(db_connection_url(args)).and_then(|conn| {
|
||||
setup(&conn).ok();
|
||||
Ok(conn)
|
||||
})
|
||||
}
|
||||
|
||||
pub fn setup(connection: &sqlite::Connection) -> Result<()> {
|
||||
let query = "CREATE TABLE files (file_identifier STRING, hash STRING)";
|
||||
connection.execute(query).ok();
|
||||
Ok(())
|
||||
}
|
||||
|
||||
pub fn put(file: &File, connection: &sqlite::Connection) -> Result<()> {
|
||||
let query = format!(
|
||||
"INSERT INTO files (file_identifier, hash) VALUES (\"{}\", \"{}\")",
|
||||
file.path, file.hash
|
||||
);
|
||||
connection.execute(query)?;
|
||||
Ok(())
|
||||
}
|
||||
|
||||
pub fn indexed_paths(connection: &sqlite::Connection) -> Result<Vec<File>> {
|
||||
let query = "SELECT * FROM files";
|
||||
|
||||
let result: Vec<File> = connection
|
||||
.prepare(query)?
|
||||
.into_iter()
|
||||
.filter_map(|row_result| row_result.ok())
|
||||
.map(|row| {
|
||||
let path = row.read::<&str, _>("file_identifier").to_string();
|
||||
let hash = row.read::<i64, _>("hash").to_string();
|
||||
File { path, hash }
|
||||
})
|
||||
.collect();
|
||||
|
||||
Ok(result)
|
||||
}
|
||||
|
||||
pub fn duplicate_hashes(connection: &sqlite::Connection, path: &str) -> Result<Vec<File>> {
|
||||
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.hash = b.hash
|
||||
WHERE a.file_identifier LIKE \"{}%\"
|
||||
ORDER BY a.file_identifier
|
||||
",
|
||||
path
|
||||
);
|
||||
|
||||
let result: Vec<File> = connection
|
||||
.prepare(query)?
|
||||
.into_iter()
|
||||
.filter_map(|row_result| row_result.ok())
|
||||
.map(|row| {
|
||||
let path = row.read::<&str, _>("file_identifier").to_string();
|
||||
let hash = row.read::<i64, _>("hash").to_string();
|
||||
File { path, hash }
|
||||
})
|
||||
.collect();
|
||||
|
||||
Ok(result)
|
||||
}
|
||||
@@ -1,12 +1,18 @@
|
||||
use crate::database::File;
|
||||
use anyhow::Result;
|
||||
use colored::Colorize;
|
||||
|
||||
#[derive(Debug, Clone)]
|
||||
pub struct File {
|
||||
pub path: String,
|
||||
pub size: Option<u64>,
|
||||
pub hash: Option<String>,
|
||||
}
|
||||
|
||||
pub fn delete_files(files: Vec<File>) -> Result<()> {
|
||||
files.into_iter().for_each(|file| {
|
||||
match std::fs::remove_file(file.path.clone()) {
|
||||
Ok(_) => println!("{}: {}", "DELETED".green(), file.path),
|
||||
Err(e) => println!("{}: {}", "FAILED".red(), file.path)
|
||||
Err(_) => println!("{}: {}", "FAILED".red(), file.path)
|
||||
}
|
||||
});
|
||||
|
||||
12
src/filters.rs
Normal file
12
src/filters.rs
Normal file
@@ -0,0 +1,12 @@
|
||||
use crate::file_manager::File;
|
||||
use crate::params::Params;
|
||||
|
||||
pub fn is_file_gt_minsize(app_opts: &Params, file: &File) -> bool {
|
||||
match app_opts.get_minsize() {
|
||||
Some(msize) => match file.size {
|
||||
Some(fsize) => fsize >= msize,
|
||||
None => true,
|
||||
},
|
||||
None => true,
|
||||
}
|
||||
}
|
||||
@@ -1,9 +1,9 @@
|
||||
#![allow(unused)] // TODO: remove this once TUI is implemented
|
||||
mod app;
|
||||
mod database;
|
||||
mod file_manager;
|
||||
mod output;
|
||||
mod params;
|
||||
mod scanner;
|
||||
mod filters;
|
||||
|
||||
use anyhow::Result;
|
||||
use app::App;
|
||||
|
||||
157
src/output.rs
157
src/output.rs
@@ -1,22 +1,19 @@
|
||||
use std::{collections::HashMap, fs, io};
|
||||
use std::io::Write;
|
||||
|
||||
use crate::file_manager::{self, File};
|
||||
use crate::params::Params;
|
||||
use anyhow::Result;
|
||||
use chrono::offset::Utc;
|
||||
use chrono::DateTime;
|
||||
use colored::Colorize;
|
||||
use humansize::{format_size, DECIMAL};
|
||||
use dashmap::DashMap;
|
||||
use indicatif::{ProgressBar, ProgressIterator, ProgressStyle};
|
||||
use itertools::Itertools;
|
||||
|
||||
use crate::app::file_manager;
|
||||
use crate::database::File;
|
||||
use crate::params::Params;
|
||||
use prettytable::{format, row, Cell, Row, Table};
|
||||
use prettytable::{format, row, Table};
|
||||
use std::io::Write;
|
||||
use std::{fs, io};
|
||||
use unicode_segmentation::UnicodeSegmentation;
|
||||
|
||||
fn format_path(path: &str, opts: &Params) -> Result<String> {
|
||||
let display_path = path.replace(&opts.get_directory()?, "");
|
||||
|
||||
let display_path = path.replace(opts.get_directory()?.to_string_lossy().as_ref(), "");
|
||||
let display_range = if display_path.chars().count() > 32 {
|
||||
display_path
|
||||
.graphemes(true)
|
||||
@@ -30,13 +27,11 @@ fn format_path(path: &str, opts: &Params) -> Result<String> {
|
||||
display_path
|
||||
};
|
||||
|
||||
Ok(format!("...{:<32}", display_range))
|
||||
Ok(format!("...{display_range:<32}"))
|
||||
}
|
||||
|
||||
fn file_size(path: &String) -> Result<String> {
|
||||
let mdata = fs::metadata(path)?;
|
||||
let formatted_size = format!("{:>12}", format_size(mdata.len(), DECIMAL));
|
||||
Ok(formatted_size)
|
||||
fn file_size(file: &File) -> Result<String> {
|
||||
Ok(format!("{:>12}", bytesize::ByteSize::b(file.size.unwrap())))
|
||||
}
|
||||
|
||||
fn modified_time(path: &String) -> Result<String> {
|
||||
@@ -46,22 +41,6 @@ fn modified_time(path: &String) -> Result<String> {
|
||||
Ok(modified_time.format("%Y-%m-%d %H:%M:%S").to_string())
|
||||
}
|
||||
|
||||
fn group_duplicates(duplicates: Vec<File>) -> HashMap<String, Vec<File>> {
|
||||
let mut duplicate_mapper: HashMap<String, Vec<File>> = HashMap::new();
|
||||
duplicates.into_iter().for_each(|file| {
|
||||
duplicate_mapper
|
||||
.entry(file.hash.clone())
|
||||
.and_modify(|value| value.push(file.clone()))
|
||||
.or_insert_with(|| vec![file]);
|
||||
});
|
||||
|
||||
duplicate_mapper
|
||||
}
|
||||
|
||||
fn print_meta_info(duplicates: &Vec<File>, opts: &Params) {
|
||||
println!("Deduplicator v{}", std::env!("CARGO_PKG_VERSION"));
|
||||
}
|
||||
|
||||
fn scan_group_instruction() -> Result<String> {
|
||||
println!("\nEnter the indices of the files you want to delete.");
|
||||
println!("You can enter multiple files using commas to seperate file indices.");
|
||||
@@ -75,14 +54,14 @@ fn scan_group_instruction() -> Result<String> {
|
||||
}
|
||||
|
||||
fn scan_group_confirmation() -> Result<bool> {
|
||||
print!("\nconfirm? [Y/n]: ");
|
||||
print!("\nconfirm? [y/N]: ");
|
||||
std::io::stdout().flush()?;
|
||||
let mut user_input = String::new();
|
||||
io::stdin().read_line(&mut user_input)?;
|
||||
|
||||
match user_input.trim() {
|
||||
"Y" | "y" => Ok(true),
|
||||
_ => Ok(false)
|
||||
_ => Ok(false),
|
||||
}
|
||||
}
|
||||
|
||||
@@ -108,63 +87,97 @@ fn process_group_action(duplicates: &Vec<File>, dup_index: usize, dup_size: usiz
|
||||
|
||||
print!("{esc}[2J{esc}[1;1H", esc = 27 as char);
|
||||
|
||||
if parsed_file_indices.is_empty() { return }
|
||||
if parsed_file_indices.is_empty() {
|
||||
return;
|
||||
}
|
||||
|
||||
let files_to_delete = parsed_file_indices
|
||||
.into_iter()
|
||||
.map(|index| duplicates[index].clone());
|
||||
|
||||
println!("\n{}", "The following files will be deleted:".red());
|
||||
files_to_delete.clone().enumerate().for_each(|(index, file)| {
|
||||
println!("{}: {}", index.to_string().blue(), file.path);
|
||||
});
|
||||
|
||||
files_to_delete
|
||||
.clone()
|
||||
.enumerate()
|
||||
.for_each(|(index, file)| {
|
||||
println!("{}: {}", index.to_string().blue(), file.path);
|
||||
});
|
||||
|
||||
match scan_group_confirmation().unwrap() {
|
||||
true => { file_manager::delete_files(files_to_delete.collect_vec()); },
|
||||
false => println!("{}", "\nCancelled Delete Operation.".red())
|
||||
true => {
|
||||
file_manager::delete_files(files_to_delete.collect_vec()).ok();
|
||||
}
|
||||
false => println!("{}", "\nCancelled Delete Operation.".red()),
|
||||
}
|
||||
}
|
||||
|
||||
pub fn interactive(duplicates: Vec<File>, opts: &Params) {
|
||||
print_meta_info(&duplicates, opts);
|
||||
let grouped_duplicates = group_duplicates(duplicates);
|
||||
pub fn interactive(duplicates: DashMap<String, Vec<File>>, opts: &Params) {
|
||||
if duplicates.is_empty() {
|
||||
println!(
|
||||
"\n{}",
|
||||
"No duplicates found matching your search criteria.".green()
|
||||
);
|
||||
return;
|
||||
}
|
||||
|
||||
grouped_duplicates.iter().enumerate().for_each(|(gindex, (hash, group))| {
|
||||
let mut itable = Table::new();
|
||||
itable.set_format(*format::consts::FORMAT_NO_BORDER_LINE_SEPARATOR);
|
||||
itable.set_titles(row!["index", "filename", "size", "updated_at"]);
|
||||
group.iter().enumerate().for_each(|(index, file)| {
|
||||
itable.add_row(row![
|
||||
index,
|
||||
format_path(&file.path, opts).unwrap_or_default().blue(),
|
||||
file_size(&file.path).unwrap_or_default().red(),
|
||||
modified_time(&file.path).unwrap_or_default().yellow()
|
||||
]);
|
||||
duplicates
|
||||
.clone()
|
||||
.into_iter()
|
||||
.sorted_unstable_by_key(|(_, f)| {
|
||||
-(f.first().and_then(|ff| ff.size).unwrap_or_default() as i64)
|
||||
}) // sort by descending file size in interactive mode
|
||||
.enumerate()
|
||||
.for_each(|(gindex, (_, group))| {
|
||||
let mut itable = Table::new();
|
||||
itable.set_format(*format::consts::FORMAT_NO_BORDER_LINE_SEPARATOR);
|
||||
itable.set_titles(row!["index", "filename", "size", "updated_at"]);
|
||||
group.iter().enumerate().for_each(|(index, file)| {
|
||||
itable.add_row(row![
|
||||
index,
|
||||
format_path(&file.path, opts).unwrap_or_default().blue(),
|
||||
file_size(file).unwrap_or_default().red(),
|
||||
modified_time(&file.path).unwrap_or_default().yellow()
|
||||
]);
|
||||
});
|
||||
|
||||
process_group_action(&group, gindex, duplicates.len(), itable);
|
||||
});
|
||||
|
||||
process_group_action(group, gindex, grouped_duplicates.len(), itable);
|
||||
});
|
||||
}
|
||||
|
||||
pub fn print(duplicates: Vec<File>, opts: &Params) {
|
||||
print_meta_info(&duplicates, opts);
|
||||
pub fn print(duplicates: DashMap<String, Vec<File>>, opts: &Params) {
|
||||
if duplicates.is_empty() {
|
||||
println!(
|
||||
"\n{}",
|
||||
"No duplicates found matching your search criteria.".green()
|
||||
);
|
||||
return;
|
||||
}
|
||||
|
||||
let mut output_table = Table::new();
|
||||
let grouped_duplicates: HashMap<String, Vec<File>> = group_duplicates(duplicates);
|
||||
let progress_bar = ProgressBar::new(duplicates.len() as u64);
|
||||
let progress_style = ProgressStyle::default_bar()
|
||||
.template("{spinner:.green} [generating output] [{wide_bar:.cyan/blue}] {pos}/{len} files")
|
||||
.unwrap();
|
||||
|
||||
progress_bar.set_style(progress_style);
|
||||
output_table.set_titles(row!["hash", "duplicates"]);
|
||||
grouped_duplicates.iter().for_each(|(hash, group)| {
|
||||
let mut inner_table = Table::new();
|
||||
inner_table.set_format(*format::consts::FORMAT_NO_BORDER_LINE_SEPARATOR);
|
||||
group.iter().for_each(|file| {
|
||||
inner_table.add_row(row![
|
||||
format_path(&file.path, opts).unwrap_or_default().blue(),
|
||||
file_size(&file.path).unwrap_or_default().red(),
|
||||
modified_time(&file.path).unwrap_or_default().yellow()
|
||||
]);
|
||||
|
||||
duplicates
|
||||
.into_iter()
|
||||
.sorted_unstable_by_key(|(_, f)| f.first().and_then(|ff| ff.size).unwrap_or_default())
|
||||
.progress_with(progress_bar)
|
||||
.for_each(|(hash, group)| {
|
||||
let mut inner_table = Table::new();
|
||||
inner_table.set_format(*format::consts::FORMAT_NO_BORDER_LINE_SEPARATOR);
|
||||
group.iter().for_each(|file| {
|
||||
inner_table.add_row(row![
|
||||
format_path(&file.path, opts).unwrap_or_default().blue(),
|
||||
file_size(file).unwrap_or_default().red(),
|
||||
modified_time(&file.path).unwrap_or_default().yellow()
|
||||
]);
|
||||
});
|
||||
output_table.add_row(row![hash.green(), inner_table]);
|
||||
});
|
||||
output_table.add_row(row![hash.green(), inner_table]);
|
||||
});
|
||||
|
||||
output_table.printstd();
|
||||
}
|
||||
|
||||
@@ -1,7 +1,8 @@
|
||||
use std::{fs, path::PathBuf};
|
||||
|
||||
use anyhow::{anyhow, Result};
|
||||
use clap::Parser;
|
||||
use clap::{Parser, ValueHint};
|
||||
use globwalk::{GlobWalker, GlobWalkerBuilder};
|
||||
|
||||
#[derive(Parser, Debug)]
|
||||
#[command(author, version, about, long_about = None)]
|
||||
@@ -10,31 +11,42 @@ pub struct Params {
|
||||
#[arg(short, long)]
|
||||
pub types: Option<String>,
|
||||
/// Run Deduplicator on dir different from pwd
|
||||
#[arg(long)]
|
||||
#[arg(long, value_hint = ValueHint::DirPath)]
|
||||
pub dir: Option<PathBuf>,
|
||||
/// Don't use cache for indexing files (default = false)
|
||||
#[arg(long, short)]
|
||||
pub nocache: bool,
|
||||
/// Delete files interactively
|
||||
#[arg(long, short)]
|
||||
pub interactive: bool
|
||||
pub interactive: bool,
|
||||
/// Minimum filesize of duplicates to scan (e.g., 100B/1K/2M/3G/4T). [default = 0]
|
||||
#[arg(long, short)]
|
||||
pub minsize: Option<String>,
|
||||
}
|
||||
|
||||
impl Params {
|
||||
pub fn get_directory(&self) -> Result<String> {
|
||||
let dir_pathbuf: PathBuf = self
|
||||
.dir
|
||||
.clone()
|
||||
.unwrap_or(std::env::current_dir()?)
|
||||
.as_os_str()
|
||||
.into();
|
||||
|
||||
let dir = fs::canonicalize(dir_pathbuf)?
|
||||
.as_os_str()
|
||||
.to_str()
|
||||
.ok_or_else(|| anyhow!("Invalid directory"))?
|
||||
.to_string();
|
||||
pub fn get_minsize(&self) -> Option<u64> {
|
||||
match &self.minsize {
|
||||
Some(msize) => match msize.parse::<bytesize::ByteSize>() {
|
||||
Ok(units) => Some(units.0),
|
||||
Err(_) => None,
|
||||
},
|
||||
None => None,
|
||||
}
|
||||
}
|
||||
|
||||
pub fn get_directory(&self) -> Result<PathBuf> {
|
||||
let current_dir = std::env::current_dir()?;
|
||||
let dir_path = self.dir.as_ref().unwrap_or(¤t_dir).as_path();
|
||||
let dir = fs::canonicalize(dir_path)?;
|
||||
Ok(dir)
|
||||
}
|
||||
|
||||
pub fn get_glob_walker(&self) -> Result<GlobWalker> {
|
||||
let pattern: String = match self.types.as_ref() {
|
||||
Some(filetypes) => format!("**/*{{{filetypes}}}"),
|
||||
None => "**/*".to_string(),
|
||||
};
|
||||
// TODO: add params for maximum depth and following symlinks, then pass them to this builder
|
||||
GlobWalkerBuilder::from_patterns(self.get_directory()?, &[pattern])
|
||||
.build()
|
||||
.map_err(|e| anyhow!(e))
|
||||
}
|
||||
}
|
||||
|
||||
186
src/scanner.rs
186
src/scanner.rs
@@ -1,87 +1,133 @@
|
||||
use std::{fs, path::PathBuf};
|
||||
use indicatif::{HumanDuration, MultiProgress, ProgressBar, ProgressStyle, ParallelProgressIterator};
|
||||
use crate::{file_manager::File, filters, params::Params};
|
||||
use anyhow::Result;
|
||||
use fxhash::hash32 as hasher;
|
||||
use glob::glob;
|
||||
use itertools::Itertools;
|
||||
use dashmap::DashMap;
|
||||
use fxhash::hash64 as hasher;
|
||||
use indicatif::{ParallelProgressIterator, ProgressBar, ProgressIterator, ProgressStyle};
|
||||
use memmap2::Mmap;
|
||||
use rayon::prelude::*;
|
||||
use std::hash::Hasher;
|
||||
use std::time::Duration;
|
||||
use std::{fs, path::PathBuf};
|
||||
|
||||
use crate::{
|
||||
database::{self, File},
|
||||
params::Params,
|
||||
};
|
||||
|
||||
pub fn duplicates(app_opts: &Params, connection: &sqlite::Connection) -> Result<Vec<File>> {
|
||||
let scan_results = scan(app_opts, connection)?;
|
||||
let base_path = app_opts.get_directory()?;
|
||||
|
||||
index_files(scan_results, connection)?;
|
||||
database::duplicate_hashes(connection, &base_path)
|
||||
#[derive(Clone, Copy)]
|
||||
enum IndexCritera {
|
||||
Size,
|
||||
Hash,
|
||||
}
|
||||
|
||||
fn get_glob_patterns(opts: &Params, directory: &str) -> Vec<PathBuf> {
|
||||
opts.types
|
||||
.clone()
|
||||
.unwrap_or_else(|| String::from("*"))
|
||||
.split(',')
|
||||
.map(|filetype| format!("*.{}", filetype))
|
||||
.map(|filetype| {
|
||||
vec![directory.to_owned(), String::from("**"), filetype]
|
||||
.iter()
|
||||
.collect()
|
||||
})
|
||||
.collect()
|
||||
}
|
||||
|
||||
fn is_indexed_file(path: impl Into<String>, indexed: &[File]) -> bool {
|
||||
indexed
|
||||
.iter()
|
||||
.map(|file| file.path.clone())
|
||||
.contains(&path.into())
|
||||
}
|
||||
|
||||
fn scan(app_opts: &Params, connection: &sqlite::Connection) -> Result<Vec<String>> {
|
||||
let directory = app_opts.get_directory()?;
|
||||
let glob_patterns: Vec<PathBuf> = get_glob_patterns(app_opts, &directory);
|
||||
let indexed_paths = database::indexed_paths(connection)?;
|
||||
let files: Vec<String> = glob_patterns
|
||||
.par_iter()
|
||||
.progress_with_style(ProgressStyle::with_template("{spinner:.green} [scanning files] [{wide_bar:.cyan/blue}] {pos}/{len} files").unwrap())
|
||||
.filter_map(|glob_pattern| glob(glob_pattern.as_os_str().to_str()?).ok())
|
||||
.flat_map(|file_vec| {
|
||||
file_vec
|
||||
.filter_map(|x| Some(x.ok()?.as_os_str().to_str()?.to_string()))
|
||||
.filter(|fpath| !is_indexed_file(fpath, &indexed_paths))
|
||||
.filter(|glob_result| {
|
||||
fs::metadata(glob_result)
|
||||
.map(|f| f.is_file())
|
||||
.unwrap_or(false)
|
||||
})
|
||||
.collect::<Vec<String>>()
|
||||
pub fn duplicates(app_opts: &Params) -> Result<DashMap<String, Vec<File>>> {
|
||||
let scan_results = scan(app_opts)?;
|
||||
let size_index_store = index_files(scan_results, IndexCritera::Size)?;
|
||||
|
||||
let sizewize_duplicate_files = size_index_store
|
||||
.into_par_iter()
|
||||
.filter(|(_, files)| files.len() > 1)
|
||||
.map(|(_, files)| files)
|
||||
.flatten()
|
||||
.collect::<Vec<File>>();
|
||||
|
||||
if sizewize_duplicate_files.len() > 1 {
|
||||
let hash_index_store = index_files(sizewize_duplicate_files, IndexCritera::Hash)?;
|
||||
let duplicate_files = hash_index_store
|
||||
.into_par_iter()
|
||||
.filter(|(_, files)| files.len() > 1)
|
||||
.collect();
|
||||
|
||||
Ok(duplicate_files)
|
||||
} else {
|
||||
Ok(DashMap::new())
|
||||
}
|
||||
}
|
||||
|
||||
fn scan(app_opts: &Params) -> Result<Vec<File>> {
|
||||
let walker = app_opts.get_glob_walker()?;
|
||||
let progress = ProgressBar::new_spinner();
|
||||
let progress_style =
|
||||
ProgressStyle::with_template("{spinner:.green} [mapping paths] {pos} paths")?;
|
||||
progress.set_style(progress_style);
|
||||
progress.enable_steady_tick(Duration::from_millis(100));
|
||||
|
||||
let files = walker
|
||||
.progress_with(progress)
|
||||
.filter_map(Result::ok)
|
||||
.map(|file| file.into_path())
|
||||
.filter(|fpath| fpath.is_file())
|
||||
.collect::<Vec<PathBuf>>()
|
||||
.into_par_iter()
|
||||
.progress_with_style(ProgressStyle::with_template(
|
||||
"{spinner:.green} [processing mapped paths] [{wide_bar:.cyan/blue}] {pos}/{len} files",
|
||||
)?)
|
||||
.map(|fpath| fpath.display().to_string())
|
||||
.map(|fpath| File {
|
||||
path: fpath.clone(),
|
||||
hash: None,
|
||||
size: Some(fs::metadata(fpath).unwrap().len()),
|
||||
})
|
||||
.filter(|file| filters::is_file_gt_minsize(app_opts, file))
|
||||
.collect();
|
||||
|
||||
Ok(files)
|
||||
}
|
||||
|
||||
fn index_files(files: Vec<String>, connection: &sqlite::Connection) -> Result<()> {
|
||||
let hashed: Vec<File> = files
|
||||
fn process_file_index(
|
||||
mut file: File,
|
||||
store: &DashMap<String, Vec<File>>,
|
||||
index_criteria: IndexCritera,
|
||||
) {
|
||||
match index_criteria {
|
||||
IndexCritera::Size => {
|
||||
store
|
||||
.entry(file.size.unwrap_or_default().to_string())
|
||||
.and_modify(|fileset| fileset.push(file.clone()))
|
||||
.or_insert_with(|| vec![file]);
|
||||
}
|
||||
IndexCritera::Hash => {
|
||||
file.hash = Some(hash_file(&file.path).unwrap_or_default());
|
||||
store
|
||||
.entry(file.clone().hash.unwrap())
|
||||
.and_modify(|fileset| fileset.push(file.clone()))
|
||||
.or_insert_with(|| vec![file]);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
fn index_files(
|
||||
files: Vec<File>,
|
||||
index_criteria: IndexCritera,
|
||||
) -> Result<DashMap<String, Vec<File>>> {
|
||||
let store: DashMap<String, Vec<File>> = DashMap::new();
|
||||
files
|
||||
.into_par_iter()
|
||||
.progress_with_style(ProgressStyle::with_template("{spinner:.green} [indexing files] [{wide_bar:.cyan/blue}] {pos}/{len} files").unwrap())
|
||||
.filter_map(|file| {
|
||||
let hash = hash_file(&file).ok()?;
|
||||
Some(database::File { path: file, hash })
|
||||
})
|
||||
.collect();
|
||||
.progress_with_style(ProgressStyle::with_template(
|
||||
"{spinner:.green} [indexing files] [{wide_bar:.cyan/blue}] {pos}/{len} files",
|
||||
)?)
|
||||
.for_each(|file| process_file_index(file, &store, index_criteria));
|
||||
|
||||
hashed
|
||||
.iter()
|
||||
.try_for_each(|file| database::put(file, connection))
|
||||
Ok(store)
|
||||
}
|
||||
|
||||
pub fn hash_file(filepath: &str) -> Result<String> {
|
||||
fn incremental_hashing(filepath: &str) -> Result<String> {
|
||||
let file = fs::File::open(filepath)?;
|
||||
let fmap = unsafe { Mmap::map(&file)? };
|
||||
let mut inchasher = fxhash::FxHasher::default();
|
||||
|
||||
fmap.chunks(1_000_000)
|
||||
.for_each(|mega| inchasher.write(mega));
|
||||
|
||||
Ok(format!("{}", inchasher.finish()))
|
||||
}
|
||||
|
||||
fn standard_hashing(filepath: &str) -> Result<String> {
|
||||
let file = fs::read(filepath)?;
|
||||
let hash = hasher(&*file).to_string();
|
||||
|
||||
Ok(hash)
|
||||
Ok(hasher(&*file).to_string())
|
||||
}
|
||||
|
||||
fn hash_file(filepath: &str) -> Result<String> {
|
||||
let filemeta = fs::metadata(filepath)?;
|
||||
|
||||
// NOTE: USE INCREMENTAL HASHING ONLY FOR FILES > 100MB
|
||||
match filemeta.len() < 100_000_000 {
|
||||
true => standard_hashing(filepath),
|
||||
false => incremental_hashing(filepath),
|
||||
}
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user