80 Commits
0.0.3 ... 0.1.2

Author SHA1 Message Date
sreedev
c0042fc9f7 version 0.1.2 release changes 2023-01-19 09:40:58 -05:00
Sreedev Kodichath
5aea0eb6f4 Merge pull request #28 from sreedevk/development
Version 0.1.2
2023-01-19 09:39:59 -05:00
Sreedev Kodichath
f0ff1ec325 Merge pull request #27 from beeb/sorted_by_size
Sort table results by ascending file size
2023-01-18 10:36:11 -05:00
Sreedev Kodichath
b267fcdedf Merge pull request #29 from beeb/cli_value_hint
feat(cli): add value hint for --dir argument
2023-01-18 10:28:15 -05:00
Valentin Bersier
84b194efca feat(cli): add value hint for --dir argument 2023-01-18 15:40:10 +01:00
Valentin Bersier
d162ca98ef docs: comment 2023-01-18 15:34:58 +01:00
Valentin Bersier
dfb73ceb5c feat: sort interactive results by descending size 2023-01-18 15:33:23 +01:00
Valentin Bersier
72ca7c7a44 Merge branch 'development' into sorted_by_size 2023-01-18 15:24:47 +01:00
Sreedev Kodichath
2f3cfd3162 Merge pull request #26 from sreedevk/feature/min-filesize
Min Size Filter Feature
2023-01-18 02:40:17 -05:00
sreedev
9b1f591c20 adds minsize option to README.md 2023-01-18 02:39:29 -05:00
sreedev
e24603c645 output enhancements 2023-01-18 02:34:08 -05:00
sreedev
0e624b042d added minsize filter 2023-01-18 02:30:48 -05:00
Valentin Bersier
e61d1f1475 perf: unwrap the size once 2023-01-18 08:07:51 +01:00
Valentin Bersier
8c76c6a3c8 refactor: simplify iterator to get size 2023-01-18 08:00:53 +01:00
Valentin Bersier
df3bea3d4f feat: display results in ascending size order 2023-01-18 07:59:51 +01:00
sreedev
7ace0bde63 scanner optimizations 2023-01-18 01:33:51 -05:00
sreedev
70de402eab performance updates in README.md 2023-01-18 00:45:24 -05:00
Sreedev Kodichath
01dd93a0ea Merge pull request #22 from sreedevk/development
Version 0.1.1
2023-01-18 00:35:51 -05:00
sreedev
8ac78fb856 version 0.1.1 2023-01-18 00:32:53 -05:00
Sreedev Kodichath
37a4c4d52d Merge pull request #23 from sreedevk/performance/incremental-hashing
Performance Improvements
2023-01-18 00:31:27 -05:00
sreedev
1ea5705474 fix confusing delete confirmation 2023-01-18 00:30:39 -05:00
sreedev
ea748c60d8 performance tweaks 2023-01-18 00:24:50 -05:00
sreedev
51f5f8e61a incremental hashing + remove sqlite + mmap file reads 2023-01-17 23:40:57 -05:00
Sreedev Kodichath
175c7579c4 Merge pull request #21 from sreedevk/code-opts
Code Optimizations
2023-01-13 21:03:58 -05:00
sreedev
81c96ce3b8 code optimizations 2023-01-13 20:54:09 -05:00
sreedev
0031891b8b remove unused code 2023-01-13 20:47:51 -05:00
Sreedev Kodichath
ae87e4e830 Create rust.yml 2023-01-13 07:32:28 -05:00
Sreedev Kodichath
284e168453 Update CONTRIBUTING.md 2023-01-13 01:09:31 -05:00
Sreedev Kodichath
a6511f2cf3 Merge pull request #20 from sreedevk/development
Version 0.0.9
2023-01-13 00:55:25 -05:00
sreedev
64d0106765 version changes 2023-01-13 00:53:46 -05:00
Sreedev Kodichath
c75b2eb1c9 Merge pull request #17 from ghfghfg23/main
Fix of "thread 'main' panicked at 'range start index 130 out of range…
2023-01-13 00:49:13 -05:00
Andrey Ryabov
b736853dfe Take 32 grapheme clusters instead of characters 2023-01-12 21:43:31 +02:00
Sreedev Kodichath
92290480a8 Update README.md 2023-01-11 19:41:23 -05:00
Sreedev Kodichath
b7f775e04c Update README.md 2023-01-11 19:39:02 -05:00
sreedev
12295d7847 version 0.0.8 2023-01-11 19:28:34 -05:00
Sreedev Kodichath
d81f499db3 Create CONTRIBUTING.md 2023-01-11 19:14:39 -05:00
Sreedev Kodichath
9e1360aeb4 Merge pull request #18 from sreedevk/progress-bar
[Feature] Add Progress Bar When Indexing Files
2023-01-11 18:56:40 -05:00
Sreedev Kodichath
38ea37711f Update README.md 2023-01-11 18:37:10 -05:00
Andrey Ryabov
2294471b50 Fix of "thread 'main' panicked at 'range start index 130 out of range for slice of length 104', src/output.rs:21:9" 2023-01-11 23:01:10 +02:00
sreedev
dbf504fc17 added progress bar 2023-01-11 15:55:31 -05:00
Sreedev Kodichath
06efb2ed6f Update issue templates 2023-01-11 07:45:51 -05:00
sreedev
95af6c4a70 updated docs to show interactive mode 2023-01-10 20:28:53 -05:00
Sreedev Kodichath
dd4b051378 Merge pull request #16 from sreedevk/interactive-mode
Interactive mode
2023-01-10 20:26:38 -05:00
sreedev
533f81f724 version 0.0.7 2023-01-10 20:26:03 -05:00
sreedev
471e60fa6c added delete options 2023-01-10 20:23:53 -05:00
sreedev
3fd4869869 UI setup complete 2023-01-10 20:13:45 -05:00
sreedev
99b87cf7fa Merge branch 'main' into interactive-mode 2023-01-09 22:55:14 -05:00
Sreedev Kodichath
b826dbe118 Update README.md 2023-01-09 22:54:19 -05:00
Sreedev Kodichath
2c75a017ce Merge pull request #14 from sreedevk/improved-ui
* Improved Duplicates Table Printing
* Added Prettytable-rs crate
* Versioning for 0.0.6
2023-01-09 22:48:59 -05:00
sreedev
b5bb58b3ed version changes 2023-01-09 22:47:54 -05:00
sreedev
6e412fc59c table display improvements 2023-01-09 22:40:37 -05:00
sreedev
a0083cb571 table printing added 2023-01-09 22:15:44 -05:00
sreedev
0f33b4d6b5 added interactive param 2023-01-09 11:13:29 -05:00
sreedev
96fe667d3f version 0.0.5 2023-01-09 11:08:20 -05:00
sreedev
c32e64450f bug fix: connection result issue 2023-01-09 11:04:29 -05:00
Sreedev Kodichath
85acbded46 Merge pull request #13 from beeb/panics
Fix some more unhandled errors
2023-01-09 11:03:12 -05:00
Sreedev Kodichath
f12cecc9ee Merge branch 'main' into panics 2023-01-09 11:02:56 -05:00
sreedev
05f513735e tempdir fixes 2023-01-09 11:01:52 -05:00
Valentin Bersier
552f6c73f2 Merge branch 'main' into panics 2023-01-09 16:59:42 +01:00
Valentin Bersier
138b66038f refactor: various clippy fixes 2023-01-09 16:57:43 +01:00
Sreedev Kodichath
d8e1de169d Merge pull request #12 from dhruvasagar/fix/temp_file_path
Fix Temporary File Path #6
2023-01-09 10:48:28 -05:00
Valentin Bersier
bc170f139e style: remove trailing spaces 2023-01-09 16:46:12 +01:00
Valentin Bersier
c76ad81a55 refactor: do no unwrap in database.rs 2023-01-09 16:41:55 +01:00
Valentin Bersier
254e61cabe fix: clippy warnings 2023-01-09 16:27:52 +01:00
Valentin Bersier
a76163f24f style: format 2023-01-09 16:21:13 +01:00
Valentin Bersier
27fef21be0 fix: no unwrap in params.rs 2023-01-09 16:17:50 +01:00
Dhruva Sagar
8b00faf075 Fix Temporary File Path #6
Better cross platform support
2023-01-09 10:53:20 +05:30
sreedev
e158a8267a added authors & updated version 2023-01-08 17:16:46 -05:00
Sreedev Kodichath
e6f93ce3d6 Merge pull request #9 from beeb/scanner
Refactor scanner
2023-01-08 17:11:36 -05:00
Sreedev Kodichath
011da05c59 Merge pull request #10 from beeb/output
Refactor output.rs
2023-01-08 17:11:04 -05:00
beeb
6087abe960 refactor: no need for into_iter 2023-01-08 13:24:08 +01:00
beeb
5eba7cdc30 fix: still print items even if file size or modified time cannot be retrieved 2023-01-08 13:21:47 +01:00
beeb
5a65550e58 refactor: output.rs 2023-01-08 13:20:15 +01:00
beeb
0b5effd06e refactor: no need to consume pathbuf iterator 2023-01-08 13:09:43 +01:00
beeb
cc243f413a refactor: no need to consume iterator items 2023-01-08 13:08:27 +01:00
beeb
ad467d70a8 style: combine use statements for std 2023-01-08 12:20:27 +01:00
beeb
4490ea4c69 style: combine use statements for database 2023-01-08 12:19:56 +01:00
beeb
8ed0b13ff0 style: order imports 2023-01-08 12:19:25 +01:00
beeb
be7e8d38ae refactor: avoid unwraps 2023-01-08 11:48:49 +01:00
beeb
c9694dea09 fix: clippy warnings 2023-01-08 11:22:43 +01:00
20 changed files with 701 additions and 487 deletions

30
.github/ISSUE_TEMPLATE/bug_report.md vendored Normal file
View File

@@ -0,0 +1,30 @@
---
name: Bug report
about: Create a report to help us improve
title: "[Bug] Title"
labels: ''
assignees: ''
---
**Describe the bug**
A clear and concise description of what the bug is.
** Runtime Info **
App Arguments: [e.g. `-i --nocache`]
Install Type: [e.g. `cargo install`]
App Version: [e.g. v0.0.7]
**Expected behavior**
A clear and concise description of what you expected to happen.
**Screenshots**
If applicable, add screenshots to help explain your problem.
**Platform Details (please complete the following information):**
- OS: [e.g. Arch Linux]
- Terminal Emulator: [e.g Alacritty]
- Shell [e.g. Zshell]
**Additional context**
Add any other context about the problem here.

View File

@@ -0,0 +1,20 @@
---
name: Feature request
about: Suggest an idea for this project
title: "[Feature] Title"
labels: ''
assignees: ''
---
**Is your feature request related to a problem? Please describe.**
A clear and concise description of what the problem is. Ex. I'm always frustrated when [...]
**Describe the solution you'd like**
A clear and concise description of what you want to happen.
**Describe alternatives you've considered**
A clear and concise description of any alternative solutions or features you've considered.
**Additional context**
Add any other context or screenshots about the feature request here.

20
.github/workflows/rust.yml vendored Normal file
View File

@@ -0,0 +1,20 @@
name: Rust
on:
push:
branches: [ "main" ]
pull_request:
branches: [ "main" ]
env:
CARGO_TERM_COLOR: always
jobs:
build:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v3
- name: Build
run: cargo build --verbose
- name: Run tests
run: cargo test --verbose

28
CONTRIBUTING.md Normal file
View File

@@ -0,0 +1,28 @@
## How to contribute to Deduplicator
#### **Did you find a bug?**
* **Ensure the bug was not already reported** by searching on GitHub under [Issues](https://github.com/sreedevk/deduplicator/issues).
* If you're unable to find an open issue addressing the problem, [open a new one](https://github.com/sreedevk/deduplicator/issues/new). Be sure to include a **title and clear description**, as much relevant information as possible, and a **code sample** or an **executable test case** demonstrating the expected behavior that is not occurring.
* If possible, use the [bug report template](https://github.com/sreedevk/deduplicator/blob/main/.github/ISSUE_TEMPLATE/bug_report.md) to create the issue.
#### **Would you like to write a fix for the bug?**
* 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?**
Changes that are cosmetic in nature and do not add anything substantial to the stability, functionality, or testability of Deduplicator will generally not be accepted/
#### **Do you intend to add a new feature or change an existing one?**
* First open an issue with the sugggestion using the [feature request template](https://github.com/sreedevk/deduplicator/blob/main/.github/ISSUE_TEMPLATE/feature-request.md)
* Do not create a PR before one of the core contributors has conveyed acceptance for a feature request.
#### **Do you have questions about the source code?**
* If you have a question, raise an issue in the repository with a "question" label.

308
Cargo.lock generated
View File

@@ -40,6 +40,18 @@ version = "1.3.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "bef38d45163c2f1dde094a7dfd33ccf595c92905c8f8f4fdc18d06fb1037718a"
[[package]]
name = "bstr"
version = "0.2.17"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ba3569f383e8f1598449f1a423e72e99569137b47740b1da11ef19af3d5c3223"
dependencies = [
"lazy_static",
"memchr",
"regex-automata",
"serde",
]
[[package]]
name = "bumpalo"
version = "3.11.1"
@@ -59,10 +71,10 @@ 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"
@@ -149,6 +161,19 @@ dependencies = [
"winapi",
]
[[package]]
name = "console"
version = "0.15.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c9b6515d269224923b26b5febea2ed42b2d5f2ce37284a4dd670fedd6cb8347a"
dependencies = [
"encode_unicode 0.3.6",
"lazy_static",
"libc",
"unicode-width",
"windows-sys",
]
[[package]]
name = "core-foundation-sys"
version = "0.8.3"
@@ -199,28 +224,25 @@ dependencies = [
]
[[package]]
name = "crossterm"
version = "0.25.0"
name = "csv"
version = "1.1.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e64e6c0fbe2c17357405f7c758c1ef960fce08bdfb2c03d88d2a18d7e09c4b67"
checksum = "22813a6dc45b335f9bade10bf7271dc477e81113e89eb251a0bc2a8a81c536e1"
dependencies = [
"bitflags",
"crossterm_winapi",
"libc",
"mio",
"parking_lot",
"signal-hook",
"signal-hook-mio",
"winapi",
"bstr",
"csv-core",
"itoa",
"ryu",
"serde",
]
[[package]]
name = "crossterm_winapi"
version = "0.9.0"
name = "csv-core"
version = "0.1.10"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "2ae1b35a484aa10e07fe0638d02301c5ad24de82d310ccbd2f3693da5f09bf1c"
checksum = "2b2466559f260f48ad25fe6317b3c8dac77b5bdb5763ac7d9d6103530663bc90"
dependencies = [
"winapi",
"memchr",
]
[[package]]
@@ -267,24 +289,61 @@ 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 = "0.0.3"
version = "0.1.2"
dependencies = [
"anyhow",
"bytesize",
"chrono",
"clap",
"colored",
"crossterm",
"dashmap",
"fxhash",
"glob",
"humansize",
"indicatif",
"itertools",
"memmap2",
"prettytable-rs",
"rayon",
"sqlite",
"thiserror",
"tokio",
"tui",
"unicode-segmentation",
]
[[package]]
name = "dirs-next"
version = "2.0.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b98cf8ebf19c3d1b223e151f99a4f9f0690dca41414773390fc824184ac833e1"
dependencies = [
"cfg-if",
"dirs-sys-next",
]
[[package]]
name = "dirs-sys-next"
version = "0.1.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "4ebda144c4fe02d1f7ea1a7d9641b6fc6b580adcfa024ae48797ecdeb6825b4d"
dependencies = [
"libc",
"redox_users",
"winapi",
]
[[package]]
@@ -293,6 +352,18 @@ version = "1.8.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "90e5c1c8368803113bf0c9584fc495a58b86dc8a29edbf8fe877d21d9507e797"
[[package]]
name = "encode_unicode"
version = "0.3.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "a357d28ed41a50f9c765dbfe56cbc04a64e53e5fc58ba79fbc34c10ef3df831f"
[[package]]
name = "encode_unicode"
version = "1.0.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "34aa73646ffb006b8f5147f3dc182bd4bcb190227ce861fc4a4844bf8e3cb2c0"
[[package]]
name = "errno"
version = "0.2.8"
@@ -323,12 +394,29 @@ dependencies = [
"byteorder",
]
[[package]]
name = "getrandom"
version = "0.2.8"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c05aeb6a22b8f62540c194aac980f2115af067bfe15a0734d7277a768d396b31"
dependencies = [
"cfg-if",
"libc",
"wasi 0.11.0+wasi-snapshot-preview1",
]
[[package]]
name = "glob"
version = "0.3.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9b919933a397b79c37e33b77bb2aa3dc8eb6e165ad809e58ff75bc7db2e34574"
[[package]]
name = "hashbrown"
version = "0.12.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "8a9ee70c43aaf417c914396645a0fa852624801b24ebb7ae78fe8272889ac888"
[[package]]
name = "heck"
version = "0.4.0"
@@ -353,15 +441,6 @@ 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"
@@ -386,6 +465,20 @@ dependencies = [
"cxx-build",
]
[[package]]
name = "indicatif"
version = "0.17.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "4295cbb7573c16d310e99e713cf9e75101eb190ab31fccd35f2d2691b4352b19"
dependencies = [
"console",
"number_prefix",
"portable-atomic",
"rayon",
"tokio",
"unicode-width",
]
[[package]]
name = "io-lifetimes"
version = "1.0.3"
@@ -417,6 +510,12 @@ dependencies = [
"either",
]
[[package]]
name = "itoa"
version = "0.4.8"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b71991ff56294aa922b450139ee08b3bfc70982c6b2c7562771375cf73542dd4"
[[package]]
name = "js-sys"
version = "0.3.60"
@@ -438,12 +537,6 @@ 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"
@@ -484,6 +577,15 @@ 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"
@@ -534,6 +636,12 @@ dependencies = [
"libc",
]
[[package]]
name = "number_prefix"
version = "0.4.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "830b246a0e5f20af87141b25c173cd1b609bd7779a4617d6ec582abaf90870f3"
[[package]]
name = "once_cell"
version = "1.16.0"
@@ -576,10 +684,24 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e0a7ae3ac2f1173085d398531c705756c94a4c56843785df85a60c1a0afac116"
[[package]]
name = "pkg-config"
version = "0.3.26"
name = "portable-atomic"
version = "0.3.19"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "6ac9a59f73473f1b8d852421e59e64809f025994837ef743615c6d0c5b305160"
checksum = "26f6a7b87c2e435a3241addceeeff740ff8b7e76b74c13bf9acb17fa454ea00b"
[[package]]
name = "prettytable-rs"
version = "0.10.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "eea25e07510aa6ab6547308ebe3c036016d162b8da920dbb079e3ba8acf3d95a"
dependencies = [
"csv",
"encode_unicode 1.0.0",
"is-terminal",
"lazy_static",
"term",
"unicode-width",
]
[[package]]
name = "proc-macro-error"
@@ -654,6 +776,23 @@ dependencies = [
"bitflags",
]
[[package]]
name = "redox_users"
version = "0.4.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b033d837a7cf162d7993aded9304e30a83213c648b6e389db233191f891e5c2b"
dependencies = [
"getrandom",
"redox_syscall",
"thiserror",
]
[[package]]
name = "regex-automata"
version = "0.1.10"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "6c230d73fb8d8c1b9c0b3135c5142a8acee3a0558fb8db5cf1cb65f8d7862132"
[[package]]
name = "rustix"
version = "0.36.5"
@@ -668,6 +807,18 @@ dependencies = [
"windows-sys",
]
[[package]]
name = "rustversion"
version = "1.0.11"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "5583e89e108996506031660fe09baa5011b9dd0341b89029313006d1fb508d70"
[[package]]
name = "ryu"
version = "1.0.12"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7b4b9743ed687d4b4bcedf9ff5eaa7398495ae14e61cba0a295704edbc7decde"
[[package]]
name = "scopeguard"
version = "1.1.0"
@@ -681,25 +832,10 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ddccb15bcce173023b3fedd9436f882a0739b8dfb45e4f6b6002bee5929f61b2"
[[package]]
name = "signal-hook"
version = "0.3.14"
name = "serde"
version = "1.0.152"
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",
]
checksum = "bb7d1f0d3021d347a83e556fc4683dea2ea09d87bccdf88ff5c12545d89d5efb"
[[package]]
name = "signal-hook-registry"
@@ -726,36 +862,6 @@ 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"
@@ -773,6 +879,17 @@ dependencies = [
"unicode-ident",
]
[[package]]
name = "term"
version = "0.7.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c59df8ac95d96ff9bede18eb7300b0fda5e5d8d90960e76f8e14ae765eedbf1f"
dependencies = [
"dirs-next",
"rustversion",
"winapi",
]
[[package]]
name = "termcolor"
version = "1.1.3"
@@ -844,19 +961,6 @@ 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"

View File

@@ -1,24 +1,27 @@
[package]
name = "deduplicator"
version = "0.0.3"
version = "0.1.2"
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>"]
# 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"
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"
unicode-segmentation = "1.10.0"

View File

@@ -14,11 +14,12 @@ NOTE: This project is still being developed. At the moment, as shown in the scre
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 = true)
-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>
@@ -35,11 +36,16 @@ cargo install deduplicator
<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>
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 <del>couple of seconds.</del> few milliseconds.</p>
<p align="center">
<del>While testing, Deduplicator was able to go through 8.6GB of pdf files and detect duplicates in 2.9 seconds</del>
As of version 0.1.1, on testing locally, deduplicator was able to process and find duplicates in 120GB of files (Videos, PDFs, Images) in ~300ms
</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>
![_039](https://user-images.githubusercontent.com/36154121/210031222-d8b79143-5a1e-47ca-926e-8855d5bbab60.png)
<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" />

18
src/app.rs Normal file
View 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(())
}
}

View File

@@ -1,28 +0,0 @@
use std::time::Duration;
use crossterm::event::{self, KeyCode, KeyEvent};
use anyhow::Result;
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)
}
}
}

View File

@@ -1,4 +0,0 @@
pub enum Event {
Exit,
Noop
}

View File

View File

@@ -1,80 +0,0 @@
mod event_handler;
mod events;
mod ui;
mod formatter;
use crate::database;
use crate::output;
use crate::params::Params;
use crate::scanner;
use anyhow::{anyhow, Result};
use crossterm::{event, execute, terminal};
use event_handler::EventHandler;
use std::io;
use std::thread;
use std::time::Duration;
use tui::{
backend::CrosstermBackend,
widgets::{Block, Borders, Widget},
Terminal,
};
use ui::Ui;
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)?;
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<()> {
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)?)
}
}

View File

@@ -1,53 +0,0 @@
use anyhow::Result;
use std::io;
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(())
}
}

View File

@@ -1,83 +0,0 @@
use anyhow::Result;
use crate::params::Params;
#[derive(Debug, Clone)]
pub struct File {
pub path: String,
pub hash: String,
}
pub fn get_connection(args: &Params) -> Result<sqlite::Connection, sqlite::Error> {
let connection_url = match args.nocache {
false => "/tmp/deduplicator.db",
true => ":memory:"
};
sqlite::open(connection_url).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
);
let result = connection.execute(query)?;
Ok(result)
}
pub fn indexed_paths(connection: &sqlite::Connection) -> Result<Vec<File>> {
let query = format!(
"SELECT * FROM files"
);
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::<i64, _>("hash").to_string();
File { path, hash }
})
.collect();
Ok(result)
}
pub fn duplicate_hashes(connection: &sqlite::Connection, path: &String) -> 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()
.map(|row_result| row_result.unwrap())
.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)
}

20
src/file_manager.rs Normal file
View File

@@ -0,0 +1,20 @@
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(_) => println!("{}: {}", "FAILED".red(), file.path)
}
});
Ok(())
}

12
src/filters.rs Normal file
View 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,
}
}

View File

@@ -1,12 +1,13 @@
mod params;
mod database;
mod output;
mod scanner;
mod app;
mod file_manager;
mod output;
mod params;
mod scanner;
mod filters;
use anyhow::Result;
use clap::Parser;
use app::App;
use clap::Parser;
#[tokio::main]
async fn main() -> Result<()> {

View File

@@ -1,68 +1,182 @@
use crate::database::File;
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 std::{collections::HashMap, fs};
use crate::params::Params;
use dashmap::DashMap;
use itertools::Itertools;
use prettytable::{format, row, Table};
use std::io::Write;
use std::{fs, io};
use unicode_segmentation::UnicodeSegmentation;
fn format_path(path: &String, opts: &Params) -> String {
let display_path = path.replace(&opts.get_directory().unwrap(), "");
let text_vec = display_path.chars().collect::<Vec<_>>();
let display_range = if text_vec.len() > 32 {
text_vec[(display_path.len() - 32)..].into_iter().collect::<String>()
fn format_path(path: &str, opts: &Params) -> Result<String> {
let display_path = path.replace(&opts.get_directory()?, "");
let display_range = if display_path.chars().count() > 32 {
display_path
.graphemes(true)
.collect::<Vec<&str>>()
.into_iter()
.rev()
.take(32)
.rev()
.collect()
} else {
display_path
};
format!("...{}", display_range)
Ok(format!("...{:<32}", display_range))
}
fn file_size(path: &String) -> String {
let mdata = fs::metadata(path).unwrap();
let formatted_size = format_size(mdata.len(), DECIMAL);
format!("{}", formatted_size)
fn file_size(file: &File) -> Result<String> {
Ok(format!("{:>12}", bytesize::ByteSize::b(file.size.unwrap())))
}
fn modified_time(path: &String) -> String {
let mdata = fs::metadata(path).unwrap();
let modified_time: DateTime<Utc> = mdata.modified().unwrap().into();
fn modified_time(path: &String) -> Result<String> {
let mdata = fs::metadata(path)?;
let modified_time: DateTime<Utc> = mdata.modified()?.into();
modified_time.format("%Y-%m-%d %H:%M:%S").to_string()
Ok(modified_time.format("%Y-%m-%d %H:%M:%S").to_string())
}
fn print_divider() {
println!("-------------------+-------------------------------------+------------------+----------------------------------+");
fn print_meta_info() {
println!("Deduplicator v{}", std::env!("CARGO_PKG_VERSION"));
}
pub fn print(duplicates: Vec<File>, opts: &Params) {
print_divider();
println!(
"| {0: <16} | {1: <35} | {2: <16} | {3: <32} |",
"hash", "filename", "size", "updated_at"
);
print_divider();
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.");
println!("example: 1,2");
print!("\n> ");
std::io::stdout().flush()?;
let mut user_input = String::new();
io::stdin().read_line(&mut user_input)?;
let mut dup_index: HashMap<String, Vec<File>> = HashMap::new();
Ok(user_input)
}
duplicates.into_iter().for_each(|file| {
dup_index
.entry(file.hash.clone())
.and_modify(|value| value.push(file.clone()))
.or_insert(vec![file]);
});
fn scan_group_confirmation() -> Result<bool> {
print!("\nconfirm? [y/N]: ");
std::io::stdout().flush()?;
let mut user_input = String::new();
io::stdin().read_line(&mut user_input)?;
dup_index.into_iter().for_each(|(_, group)| {
group.into_iter().for_each(|file| {
println!(
"| {0: <16} | {1: <35} | {2: <16} | {3: <32} |",
file.hash.red(),
format_path(&file.path, opts).yellow(),
file_size(&file.path).blue(),
modified_time(&file.path).blue()
);
match user_input.trim() {
"Y" | "y" => Ok(true),
_ => Ok(false),
}
}
fn process_group_action(duplicates: &Vec<File>, dup_index: usize, dup_size: usize, table: Table) {
println!("\nDuplicate Set {} of {}\n", dup_index + 1, dup_size);
table.printstd();
let files_to_delete = scan_group_instruction().unwrap_or_default();
let parsed_file_indices = files_to_delete
.trim()
.split(',')
.filter(|element| !element.is_empty())
.map(|index| index.parse::<usize>().unwrap_or_default())
.collect_vec();
if parsed_file_indices
.clone()
.into_iter()
.any(|index| index > (duplicates.len() - 1))
{
println!("{}", "Err: File Index Out of Bounds!".red());
return process_group_action(duplicates, dup_index, dup_size, table);
}
print!("{esc}[2J{esc}[1;1H", esc = 27 as char);
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);
});
print_divider();
});
match scan_group_confirmation().unwrap() {
true => {
file_manager::delete_files(files_to_delete.collect_vec()).ok();
}
false => println!("{}", "\nCancelled Delete Operation.".red()),
}
}
pub fn interactive(duplicates: DashMap<String, Vec<File>>, opts: &Params) {
print_meta_info();
if duplicates.is_empty() {
println!(
"\n{}",
"No duplicates found matching your search criteria.".green()
);
return;
}
duplicates
.clone()
.into_iter()
.sorted_unstable_by_key(|f| {
-(f.1.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);
});
}
pub fn print(duplicates: DashMap<String, Vec<File>>, opts: &Params) {
print_meta_info();
if duplicates.is_empty() {
println!(
"\n{}",
"No duplicates found matching your search criteria.".green()
);
return;
}
let mut output_table = Table::new();
output_table.set_titles(row!["hash", "duplicates"]);
duplicates
.into_iter()
.sorted_unstable_by_key(|f| f.1.first().and_then(|ff| ff.size).unwrap_or_default()) // sort by ascending size
.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.printstd();
}

View File

@@ -1,7 +1,6 @@
use std::path::PathBuf;
use clap::Parser;
use anyhow::Result;
use std::fs;
use anyhow::{anyhow, Result};
use clap::{Parser, ValueHint};
use std::{fs, path::PathBuf};
#[derive(Parser, Debug)]
#[command(author, version, about, long_about = None)]
@@ -10,31 +9,55 @@ 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 = true)
/// Delete files interactively
#[arg(long, short)]
pub nocache: 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_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<String> {
let dir_string: String = self
let dir_pathbuf: PathBuf = self
.dir
.clone()
.unwrap_or(std::env::current_dir()?)
.as_os_str()
.to_str()
.unwrap()
.to_string();
.into();
let dir_pathbuf = PathBuf::from(&dir_string);
let dir = fs::canonicalize(&dir_pathbuf)?
let dir = fs::canonicalize(dir_pathbuf)?
.as_os_str()
.to_str()
.unwrap()
.ok_or_else(|| anyhow!("Invalid directory"))?
.to_string();
Ok(dir)
}
pub fn get_glob_patterns(&self) -> Vec<PathBuf> {
self.types
.clone()
.unwrap_or_else(|| String::from("*"))
.split(',')
.map(|filetype| format!("*.{}", filetype))
.map(|filetype| {
vec![self.get_directory().unwrap(), String::from("**"), filetype]
.iter()
.collect()
})
.collect()
}
}

View File

@@ -1,79 +1,142 @@
use crate::database;
use crate::{params::Params, database::File};
use crate::{file_manager::File, filters, params::Params};
use anyhow::Result;
use dashmap::DashMap;
use fxhash::hash64 as hasher;
use glob::glob;
use itertools::Itertools;
use indicatif::{ParallelProgressIterator, ProgressStyle};
use memmap2::Mmap;
use rayon::prelude::*;
use std::fs;
use std::path::PathBuf;
use fxhash::hash32 as hasher;
use std::hash::Hasher;
use std::{fs, path::PathBuf};
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: &String) -> Vec<PathBuf> {
opts.types
.clone()
.unwrap_or(String::from("*"))
.split(",")
.map(|filetype| format!("*.{}", filetype))
.map(|filetype| {
vec![directory.clone(), String::from("**"), filetype]
.iter()
.collect()
})
.collect()
}
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)?;
fn is_indexed_file(path: &String, indexed: &Vec<File>) -> bool {
indexed
.into_iter()
.map(|file| file.path.clone())
.contains(path)
}
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
let sizewize_duplicate_files = size_index_store
.into_par_iter()
.map(|glob_pattern| glob(&glob_pattern.as_os_str().to_str().unwrap()))
.map(|glob_result| glob_result.unwrap())
.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 glob_patterns: Vec<PathBuf> = app_opts.get_glob_patterns();
let files: Vec<File> = glob_patterns
.par_iter()
.progress_with_style(ProgressStyle::with_template(
"{spinner:.green} [scanning files] [{wide_bar:.cyan/blue}] {pos}/{len} files",
)?)
.filter_map(|glob_pattern| glob(glob_pattern.as_os_str().to_str()?).ok())
.flat_map(|file_vec| {
file_vec
.map(|x| x.unwrap().as_os_str().to_str().unwrap().to_string())
.filter(|fpath| !is_indexed_file(fpath, &indexed_paths))
.filter(|glob_result| fs::metadata(glob_result).unwrap().is_file())
.filter_map(|x| Some(x.ok()?.as_os_str().to_str()?.to_string()))
.filter(|glob_result| {
fs::metadata(glob_result)
.map(|f| f.is_file())
.unwrap_or(false)
})
.collect::<Vec<String>>()
})
.map(|file_path| File {
path: file_path.clone(),
hash: None,
size: Some(fs::metadata(file_path).unwrap().len()),
})
.filter(|file| filters::is_file_gt_minsize(app_opts, file))
.collect();
Ok(files)
}
fn index_files(files: Vec<String>, connection: &sqlite::Connection) {
let hashed: Vec<File> = files
fn process_file_hash_index(file: &File) -> Result<File> {
Ok(File {
path: file.path.clone(),
size: file.size,
hash: Some(hash_file(&file.path).unwrap_or_default()),
})
}
fn process_file_index(
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 => {
let processed_file = process_file_hash_index(&file).unwrap();
let indexhash = processed_file.clone().hash.unwrap_or_default();
store
.entry(indexhash)
.and_modify(|fileset| fileset.push(processed_file.clone()))
.or_insert_with(|| vec![processed_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()
.map(|file| {
let hash = hash_file(&file).unwrap();
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.into_iter().for_each(|file| {
database::put(&file, connection).unwrap();
});
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),
}
}