Merge pull request #49 from sreedevk/development

Version 0.1.6

.github/workflows/release.yml

@@ -1,41 +1,136 @@
+# CI that:
+#
+# * checks for a Git Tag that looks like a release ("v1.2.0")
+# * creates a Github Release™️
+# * builds binaries/packages with cargo-dist
+# * uploads those packages to the Github Release™️
+#
+# Note that the Github Release™️ will be created before the packages,
+# so there will be a few minutes where the release has no packages
+# and then they will slowly trickle in, possibly failing. To make
+# this more pleasant we mark the release as a "draft" until all
+# artifacts have been successfully uploaded. This allows you to
+# choose what to do with partial successes and avoids spamming
+# anyone with notifications before the release is actually ready.
 name: Release
 
-env:
+permissions:
-  PROJECT_NAME: deduplicator
+  contents: write
-  PROJECT_DESC: "Filter, Sort & Delete Duplicate Files Recursively"
-  PROJECT_AUTH: "sreedevk"
 
+# This task will run whenever you push a git tag that looks like
+# a version number. We just look for `v` followed by at least one number
+# and then whatever. so `v1`, `v1.0.0`, and `v1.0.0-prerelease` all work.
+#
+# If there's a prerelease-style suffix to the version then the Github Release™️
+# will be marked as a prerelease (handled by taiki-e/create-gh-release-action).
+#
+# Note that when generating links to uploaded artifacts, cargo-dist will currently
+# assume that your git tag is always v{VERSION} where VERSION is the version in
+# the published package's Cargo.toml (this is the default behaviour of cargo-release).
+# In the future this may be made more robust/configurable.
 on:
   push:
     tags:
-      - "[0-9]+.*"
+      - v[0-9]+.*
+
+env:
+  ALL_CARGO_DIST_TARGET_ARGS: --target=x86_64-unknown-linux-gnu --target=x86_64-apple-darwin --target=x86_64-pc-windows-msvc 
+  ALL_CARGO_DIST_INSTALLER_ARGS: 
 
 jobs:
+  # Create the Github Release™️ so the packages have something to be uploaded to
   create-release:
     runs-on: ubuntu-latest
+    outputs:
+      tag: ${{ steps.create-gh-release.outputs.computed-prefix }}${{ steps.create-gh-release.outputs.version }}
     steps:
       - uses: actions/checkout@v3
-      - uses: taiki-e/create-gh-release-action@v1.6.2
+      - id: create-gh-release
+        uses: taiki-e/create-gh-release-action@v1
         with:
-          changelog: CHANGELOG.md
+          draft: true
+          # (required) GitHub token for creating GitHub Releases.
           token: ${{ secrets.GITHUB_TOKEN }}
-          branch: main
 
-  upload-assets:
+
+  # Build and packages all the things
+  upload-artifacts:
+    needs: create-release
     strategy:
       matrix:
-        os:
+        # For these target platforms
-          - ubuntu-latest
+        include:
-          - macos-latest
+        - target: x86_64-unknown-linux-gnu
-          - windows-latest
+          os: ubuntu-20.04
+          install-dist: curl --proto '=https' --tlsv1.2 -L -sSf https://github.com/axodotdev/cargo-dist/releases/download/v0.0.2/installer.sh | sh
+        - target: x86_64-apple-darwin
+          os: macos-11
+          install-dist: curl --proto '=https' --tlsv1.2 -L -sSf https://github.com/axodotdev/cargo-dist/releases/download/v0.0.2/installer.sh | sh
+        - target: x86_64-pc-windows-msvc
+          os: windows-2019
+          install-dist: irm 'https://github.com/axodotdev/cargo-dist/releases/download/v0.0.2/installer.ps1' | iex
     runs-on: ${{ matrix.os }}
+    env:
+      GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
     steps:
       - uses: actions/checkout@v3
-      - uses: taiki-e/upload-rust-binary-action@v1
+      - name: Install Rust
-        with:
+        run: rustup update stable && rustup default stable
-          bin: deduplicator
+      - name: Install cargo-dist
-          tar: unix
+        run: ${{ matrix.install-dist }}
-          zip: windows
+      - name: Run cargo-dist
-          token: ${{ secrets.GITHUB_TOKEN }}
+        # This logic is a bit janky because it's trying to be a polyglot between
-        env:
+        # powershell and bash since this will run on windows, macos, and linux!
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        # The two platforms don't agree on how to talk about env vars but they
+        # do agree on 'cat' and '$()' so we use that to marshal values between commmands.
+        run: |
+          # Actually do builds and make zips and whatnot
+          cargo dist --target=${{ matrix.target }} --output-format=json > dist-manifest.json
+          echo "dist ran successfully"
+          cat dist-manifest.json
+          # Parse out what we just built and upload it to the Github Release™️
+          cat dist-manifest.json | jq --raw-output ".releases[].artifacts[].path" > uploads.txt
+          echo "uploading..."
+          cat uploads.txt
+          gh release upload ${{ needs.create-release.outputs.tag }} $(cat uploads.txt)
+          echo "uploaded!"
+
+  # Compute and upload the manifest for everything
+  upload-manifest:
+    needs: create-release
+    runs-on: ubuntu-latest
+    env:
+      GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+    steps:
+      - uses: actions/checkout@v3
+      - name: Install Rust
+        run: rustup update stable && rustup default stable
+      - name: Install cargo-dist
+        run: curl --proto '=https' --tlsv1.2 -L -sSf https://github.com/axodotdev/cargo-dist/releases/download/v0.0.2/installer.sh | sh
+      - name: Run cargo-dist manifest
+        run: |
+          # Generate a manifest describing everything
+          cargo dist manifest --no-local-paths --output-format=json $ALL_CARGO_DIST_TARGET_ARGS $ALL_CARGO_DIST_INSTALLER_ARGS > dist-manifest.json
+          echo "dist manifest ran successfully"
+          cat dist-manifest.json
+          # Upload the manifest to the Github Release™️
+          gh release upload ${{ needs.create-release.outputs.tag }} dist-manifest.json
+          echo "uploaded manifest!"
+          # Edit the Github Release™️ title/body to match what cargo-dist thinks it should be
+          CHANGELOG_TITLE=$(cat dist-manifest.json | jq --raw-output ".releases[].changelog_title")
+          cat dist-manifest.json | jq --raw-output ".releases[].changelog_body" > new_dist_changelog.md
+          gh release edit ${{ needs.create-release.outputs.tag }} --title="$CHANGELOG_TITLE" --notes-file=new_dist_changelog.md
+          echo "updated release notes!"
+
+  # Mark the Github Release™️ as a non-draft now that everything has succeeded!
+  publish-release:
+    needs: [create-release, upload-artifacts, upload-manifest]
+    runs-on: ubuntu-latest
+    env:
+      GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+    steps:
+      - uses: actions/checkout@v3
+      - name: mark release as non-draft
+        run: |
+          gh release edit ${{ needs.create-release.outputs.tag }} --draft=false
+

.gitignore

@@ -1,2 +1,3 @@
 /target
 /test_data
+.envrc

Cargo.lock

@@ -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"
@@ -53,10 +62,20 @@ dependencies = [
 ]
 
 [[package]]
-name = "bumpalo"
+name = "bstr"
-version = "3.11.1"
+version = "1.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "572f695136211188308f16ad2ca5c851a712c464060ae6974944458eb83880ba"
+checksum = "b45ea9b00a7b3f2988e9a65ad3917e62123c38dba709b666506207be96d1790b"
+dependencies = [
+ "memchr",
+ "serde",
+]
+
+[[package]]
+name = "bumpalo"
+version = "3.12.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0d261e256854913907f67ed06efbc3338dfe6179796deefc1ff763fc1aee5535"
 
 [[package]]
 name = "byteorder"
@@ -64,12 +83,6 @@ version = "1.4.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "14c189c53d098945499cdfa7ecc63567cf3886b3332b312a5b4585d8d3a6a610"
 
-[[package]]
-name = "bytes"
-version = "1.3.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "dfb24e866b15a1af2a1b663f10c6b6b8f397a84aadb828f12e5b289ec23a3a3c"
-
 [[package]]
 name = "bytesize"
 version = "1.1.0"
@@ -105,9 +118,9 @@ dependencies = [
 
 [[package]]
 name = "clap"
-version = "4.0.32"
+version = "4.1.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a7db700bc935f9e43e88d00b0850dae18a63773cfbec6d8e070fccf7fef89a39"
+checksum = "f13b9c79b5d1dd500d20ef541215a6423c75829ef43117e1b4d17fd8af0b5d76"
 dependencies = [
  "bitflags",
  "clap_derive",
@@ -120,9 +133,9 @@ dependencies = [
 
 [[package]]
 name = "clap_derive"
-version = "4.0.21"
+version = "4.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0177313f9f02afc995627906bbd8967e2be069f5261954222dac78290c2b9014"
+checksum = "684a277d672e91966334af371f1a7b5833f9aa00b07c84e92fbce95e00208ce8"
 dependencies = [
  "heck",
  "proc-macro-error",
@@ -133,9 +146,9 @@ dependencies = [
 
 [[package]]
 name = "clap_lex"
-version = "0.3.0"
+version = "0.3.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0d4198f73e42b4936b35b5bb248d81d2b595ecb170da0bac7655c54eedfa8da8"
+checksum = "783fe232adfca04f90f56201b26d79682d4cd2625e0bc7290b95123afe558ade"
 dependencies = [
  "os_str_bytes",
 ]
@@ -163,9 +176,9 @@ dependencies = [
 
 [[package]]
 name = "console"
-version = "0.15.4"
+version = "0.15.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c9b6515d269224923b26b5febea2ed42b2d5f2ce37284a4dd670fedd6cb8347a"
+checksum = "c3d79fbe8970a77e3e34151cc13d3b3e248aa0faaecb9f6091fa07ebefe5ad60"
 dependencies = [
  "encode_unicode 0.3.6",
  "lazy_static",
@@ -229,7 +242,7 @@ 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",
@@ -247,9 +260,9 @@ dependencies = [
 
 [[package]]
 name = "cxx"
-version = "1.0.85"
+version = "1.0.87"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "5add3fc1717409d029b20c5b6903fc0c0b02fa6741d820054f4a2efa5e5816fd"
+checksum = "b61a7545f753a88bcbe0a70de1fcc0221e10bfc752f576754fa91e663db1622e"
 dependencies = [
  "cc",
  "cxxbridge-flags",
@@ -259,9 +272,9 @@ dependencies = [
 
 [[package]]
 name = "cxx-build"
-version = "1.0.85"
+version = "1.0.87"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b4c87959ba14bc6fbc61df77c3fcfe180fc32b93538c4f1031dd802ccb5f2ff0"
+checksum = "f464457d494b5ed6905c63b0c4704842aba319084a0a3561cdc1359536b53200"
 dependencies = [
  "cc",
  "codespan-reporting",
@@ -274,15 +287,15 @@ dependencies = [
 
 [[package]]
 name = "cxxbridge-flags"
-version = "1.0.85"
+version = "1.0.87"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "69a3e162fde4e594ed2b07d0f83c6c67b745e7f28ce58c6df5e6b6bef99dfb59"
+checksum = "43c7119ce3a3701ed81aca8410b9acf6fc399d2629d057b87e2efa4e63a3aaea"
 
 [[package]]
 name = "cxxbridge-macro"
-version = "1.0.85"
+version = "1.0.87"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "3e7e2adeb6a0d4a282e581096b06e1791532b7d576dcde5ccd9382acf55db8e6"
+checksum = "65e07508b90551e610910fa648a1878991d367064997a596135b86df30daf07e"
 dependencies = [
  "proc-macro2",
  "quote",
@@ -305,7 +318,7 @@ dependencies = [
 
 [[package]]
 name = "deduplicator"
-version = "0.1.3"
+version = "0.1.6"
 dependencies = [
  "anyhow",
  "bytesize",
@@ -314,14 +327,12 @@ dependencies = [
  "colored",
  "dashmap",
  "fxhash",
- "glob",
+ "globwalk",
  "indicatif",
  "itertools",
  "memmap2",
  "prettytable-rs",
  "rayon",
- "thiserror",
- "tokio",
  "unicode-segmentation",
 ]
 
@@ -385,6 +396,12 @@ 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"
@@ -406,10 +423,28 @@ dependencies = [
 ]
 
 [[package]]
-name = "glob"
+name = "globset"
-version = "0.3.0"
+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"
@@ -466,24 +501,40 @@ dependencies = [
 ]
 
 [[package]]
-name = "indicatif"
+name = "ignore"
-version = "0.17.2"
+version = "0.4.20"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "4295cbb7573c16d310e99e713cf9e75101eb190ab31fccd35f2d2691b4352b19"
+checksum = "dbe7873dab538a9a44ad79ede1faf5f30d49f9a5c883ddbab48bce81b64b7492"
+dependencies = [
+ "globset",
+ "lazy_static",
+ "log",
+ "memchr",
+ "regex",
+ "same-file",
+ "thread_local",
+ "walkdir",
+ "winapi-util",
+]
+
+[[package]]
+name = "indicatif"
+version = "0.17.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "cef509aa9bc73864d6756f0d34d35504af3cf0844373afe9b8669a5b8005a729"
 dependencies = [
  "console",
  "number_prefix",
  "portable-atomic",
  "rayon",
- "tokio",
  "unicode-width",
 ]
 
 [[package]]
 name = "io-lifetimes"
-version = "1.0.3"
+version = "1.0.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "46112a93252b123d31a119a8d1a1ac19deac4fac6e0e8b0df58f0d4e5870e63c"
+checksum = "e7d6c6f8c91b4b9ed43484ad1a938e393caf35960fce7f82a040497207bd8e9e"
 dependencies = [
  "libc",
  "windows-sys",
@@ -595,18 +646,6 @@ dependencies = [
  "autocfg",
 ]
 
-[[package]]
-name = "mio"
-version = "0.8.5"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e5d732bc30207a6423068df043e3d02e0735b155ad7ce1a6f76fe2baa5b158de"
-dependencies = [
- "libc",
- "log",
- "wasi 0.11.0+wasi-snapshot-preview1",
- "windows-sys",
-]
-
 [[package]]
 name = "num-integer"
 version = "0.1.45"
@@ -644,9 +683,9 @@ checksum = "830b246a0e5f20af87141b25c173cd1b609bd7779a4617d6ec582abaf90870f3"
 
 [[package]]
 name = "once_cell"
-version = "1.16.0"
+version = "1.17.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "86f0b0d4bf799edbc74508c1e8bf170ff5f41238e5f8225603ca7caaae2b7860"
+checksum = "6f61fba1741ea2b3d6a1e3178721804bb716a68a6aeba1149b5d52e3d464ea66"
 
 [[package]]
 name = "os_str_bytes"
@@ -654,21 +693,11 @@ version = "6.4.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "9b7820b9daea5457c9f21c69448905d723fbd21136ccf521748f23fd49e723ee"
 
-[[package]]
-name = "parking_lot"
-version = "0.12.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "3742b2c103b9f06bc9fff0a37ff4912935851bee6d36f3c02bcc755bcfec228f"
-dependencies = [
- "lock_api",
- "parking_lot_core",
-]
-
 [[package]]
 name = "parking_lot_core"
-version = "0.9.5"
+version = "0.9.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7ff9f3fef3968a3ec5945535ed654cb38ff72d7495a25619e2247fb15a2ed9ba"
+checksum = "ba1ef8814b5c993410bb3adfad7a5ed269563e4a2f90c41f5d85be7fb47133bf"
 dependencies = [
  "cfg-if",
  "libc",
@@ -677,12 +706,6 @@ dependencies = [
  "windows-sys",
 ]
 
-[[package]]
-name = "pin-project-lite"
-version = "0.2.9"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e0a7ae3ac2f1173085d398531c705756c94a4c56843785df85a60c1a0afac116"
-
 [[package]]
 name = "portable-atomic"
 version = "0.3.19"
@@ -729,9 +752,9 @@ dependencies = [
 
 [[package]]
 name = "proc-macro2"
-version = "1.0.49"
+version = "1.0.50"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "57a8eca9f9c4ffde41714334dee777596264c7825420f521abc92b5b5deb63a5"
+checksum = "6ef7d57beacfaf2d8aee5937dab7b7f28de3cb8b1828479bb5de2a7106f2bae2"
 dependencies = [
  "unicode-ident",
 ]
@@ -757,9 +780,9 @@ dependencies = [
 
 [[package]]
 name = "rayon-core"
-version = "1.10.1"
+version = "1.10.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "cac410af5d00ab6884528b4ab69d1e8e146e8d471201800fa1b4524126de6ad3"
+checksum = "356a0625f1954f730c0201cdab48611198dc6ce21f4acff55089b5a78e6e835b"
 dependencies = [
  "crossbeam-channel",
  "crossbeam-deque",
@@ -787,6 +810,17 @@ 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"
@@ -794,10 +828,16 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "6c230d73fb8d8c1b9c0b3135c5142a8acee3a0558fb8db5cf1cb65f8d7862132"
 
 [[package]]
-name = "rustix"
+name = "regex-syntax"
-version = "0.36.5"
+version = "0.6.28"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a3807b5d10909833d3e9acd1eb5fb988f79376ff10fce42937de71a449c4c588"
+checksum = "456c603be3e8d448b072f410900c09faf164fbce2d480456f50eea6e25f9c848"
+
+[[package]]
+name = "rustix"
+version = "0.36.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d4fdebc4b395b7fbb9ab11e462e20ed9051e7b16e42d24042c776eca0ac81b03"
 dependencies = [
  "bitflags",
  "errno",
@@ -819,6 +859,15 @@ 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"
@@ -837,31 +886,12 @@ version = "1.0.152"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "bb7d1f0d3021d347a83e556fc4683dea2ea09d87bccdf88ff5c12545d89d5efb"
 
-[[package]]
-name = "signal-hook-registry"
-version = "1.4.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e51e73328dc4ac0c7ccbda3a494dfa03df1de2f46018127f60c693f2648455b0"
-dependencies = [
- "libc",
-]
-
 [[package]]
 name = "smallvec"
 version = "1.10.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "a507befe795404456341dfab10cef66ead4c041f62b8b11bbb92bffe5d0953e0"
 
-[[package]]
-name = "socket2"
-version = "0.4.7"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "02e2d2db9033d13a1567121ddd7a095ee144db4e1ca1b1bda3419bc0da294ebd"
-dependencies = [
- "libc",
- "winapi",
-]
-
 [[package]]
 name = "strsim"
 version = "0.10.0"
@@ -892,9 +922,9 @@ dependencies = [
 
 [[package]]
 name = "termcolor"
-version = "1.1.3"
+version = "1.2.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "bab24d30b911b2376f3a13cc2cd443142f0c81dda04c118693e35b3835757755"
+checksum = "be55cf8942feac5c765c2c993422806843c9a9a45d4d5c407ad6dd2ea95eb9b6"
 dependencies = [
  "winapi-util",
 ]
@@ -919,6 +949,15 @@ 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"
@@ -930,37 +969,6 @@ dependencies = [
  "winapi",
 ]
 
-[[package]]
-name = "tokio"
-version = "1.23.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "38a54aca0c15d014013256222ba0ebed095673f89345dd79119d912eb561b7a8"
-dependencies = [
- "autocfg",
- "bytes",
- "libc",
- "memchr",
- "mio",
- "num_cpus",
- "parking_lot",
- "pin-project-lite",
- "signal-hook-registry",
- "socket2",
- "tokio-macros",
- "windows-sys",
-]
-
-[[package]]
-name = "tokio-macros"
-version = "1.8.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d266c00fde287f55d3f1c3e96c500c362a2b8c695076ec180f27918820bc6df8"
-dependencies = [
- "proc-macro2",
- "quote",
- "syn",
-]
-
 [[package]]
 name = "unicode-ident"
 version = "1.0.6"
@@ -985,6 +993,17 @@ 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"
@@ -1099,42 +1118,42 @@ dependencies = [
 
 [[package]]
 name = "windows_aarch64_gnullvm"
-version = "0.42.0"
+version = "0.42.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "41d2aa71f6f0cbe00ae5167d90ef3cfe66527d6f613ca78ac8024c3ccab9a19e"
+checksum = "8c9864e83243fdec7fc9c5444389dcbbfd258f745e7853198f365e3c4968a608"
 
 [[package]]
 name = "windows_aarch64_msvc"
-version = "0.42.0"
+version = "0.42.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "dd0f252f5a35cac83d6311b2e795981f5ee6e67eb1f9a7f64eb4500fbc4dcdb4"
+checksum = "4c8b1b673ffc16c47a9ff48570a9d85e25d265735c503681332589af6253c6c7"
 
 [[package]]
 name = "windows_i686_gnu"
-version = "0.42.0"
+version = "0.42.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "fbeae19f6716841636c28d695375df17562ca208b2b7d0dc47635a50ae6c5de7"
+checksum = "de3887528ad530ba7bdbb1faa8275ec7a1155a45ffa57c37993960277145d640"
 
 [[package]]
 name = "windows_i686_msvc"
-version = "0.42.0"
+version = "0.42.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "84c12f65daa39dd2babe6e442988fc329d6243fdce47d7d2d155b8d874862246"
+checksum = "bf4d1122317eddd6ff351aa852118a2418ad4214e6613a50e0191f7004372605"
 
 [[package]]
 name = "windows_x86_64_gnu"
-version = "0.42.0"
+version = "0.42.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "bf7b1b21b5362cbc318f686150e5bcea75ecedc74dd157d874d754a2ca44b0ed"
+checksum = "c1040f221285e17ebccbc2591ffdc2d44ee1f9186324dd3e84e99ac68d699c45"
 
 [[package]]
 name = "windows_x86_64_gnullvm"
-version = "0.42.0"
+version = "0.42.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "09d525d2ba30eeb3297665bd434a54297e4170c7f1a44cad4ef58095b4cd2028"
+checksum = "628bfdf232daa22b0d64fdb62b09fcc36bb01f05a3939e20ab73aaf9470d0463"
 
 [[package]]
 name = "windows_x86_64_msvc"
-version = "0.42.0"
+version = "0.42.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f40009d85759725a34da6d89a94e63d7bdc50a862acf0dbc7c8e488f1edcb6f5"
+checksum = "447660ad36a13288b1db4d4248e857b510e8c3a225c822ba4fb748c0aafecffd"

Cargo.toml

@@ -1,10 +1,14 @@
 [package]
 name = "deduplicator"
-version = "0.1.3"
+version = "0.1.6"
 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
 
@@ -16,12 +20,17 @@ clap = { version = "4.0.32", features = ["derive"] }
 colored = "2.0.0"
 dashmap = { version = "5.4.0", features = ["rayon"] }
 fxhash = "0.2.1"
-glob = "0.3.0"
+globwalk = "0.8.1"
-indicatif = { version = "0.17.2", features = ["rayon", "tokio"] }
+indicatif = { version = "0.17.2", features = ["rayon"] }
 itertools = "0.10.5"
 memmap2 = "0.5.8"
 prettytable-rs = "0.10.0"
 rayon = "1.6.1"
-thiserror = "1.0.38"
-tokio = { version = "1.23.1", features = ["full"] }
 unicode-segmentation = "1.10.0"
+
+# generated by 'cargo dist init'
+[profile.dist]
+inherits = "release"
+debug = true
+split-debuginfo = "packed"
+

README.md

@@ -4,45 +4,120 @@
   Find, Sort, Filter & Delete duplicate files 
 </p>
 
-<p align="center">
+## Usage
-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>
 
 ```bash
-Usage: deduplicator [OPTIONS]
+Usage: deduplicator [OPTIONS] [scan_dir_path]
+
+Arguments:
+  [scan_dir_path]  Run Deduplicator on dir different from pwd (e.g., ~/Pictures )
 
 Options:
-  -t, --types <TYPES>      Filetypes to deduplicate (default = all)
+  -t, --types <TYPES>          Filetypes to deduplicate [default = all]
-      --dir <DIR>          Run Deduplicator on dir different from pwd
+  -i, --interactive            Delete files interactively
-  -i, --interactive        Delete files interactively
+  -s, --min-size <MIN_SIZE>    Minimum filesize of duplicates to scan (e.g., 100B/1K/2M/3G/4T) [default: 1b]
-  -m, --minsize <MINSIZE>  Minimum filesize of duplicates to scan (e.g., 100B/1K/2M/3G/4T). [default = 0]
+  -d, --max-depth <MAX_DEPTH>  Max Depth to scan while looking for duplicates
-  -h, --help               Print help information
+      --min-depth <MIN_DEPTH>  Min Depth to scan while looking for duplicates
-  -V, --version            Print version information
+  -f, --follow-links           Follow links while scanning directories
+  -h, --help                   Print help information
+  -V, --version                Print version information
+```
+### Examples
+
+```bash
+# Scan for duplicates recursively from the current dir, only look for png, jpg & pdf file types & interactively delete files
+deduplicator -t pdf,jpg,png -i
+
+# Scan for duplicates recursively from the ~/Pictures dir, only look for png, jpeg, jpg & pdf file types & interactively delete files
+deduplicator ~/Pictures/ -t png,jpeg,jpg,pdf -i
+
+# Scan for duplicates in the ~/Pictures without recursing into subdirectories
+deduplicator ~/Pictures --max-depth 0
+
+# look for duplicates in the ~/.config directory while also recursing into symbolic link paths
+deduplicator ~/.config --follow-links
+
+# scan for duplicates that are greater than 100mb in the ~/Media directory
+deduplicator ~/Media --min-size 100mb
 ```
 
-<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 | Filecount | Mean [ms] | Min [ms] | Max [ms] | Relative |
+|:---|:---|---:|---:|---:|---:|---:|
+| `deduplicator ~/Data/tmp` | (~120G) | 721 files | 33.5 ± 28.6 | 25.3 | 151.5 | 1.87 ± 1.60 |
+| `deduplicator ~/Data/books` | (~8.6G) | 1419 files | 24.5 ± 1.0 | 22.9 | 28.1 | 1.37 ± 0.08 |
+| `deduplicator ~/Data/books --min-size 10M` | (~8.6G) | 1419 files | 17.9 ± 0.7 | 16.8 | 20.0 | 1.00 |
+| `deduplicator ~/Data/ --types pdf,jpg,png,jpeg` | (~290G) | 104222 files | 1207.2 ± 37.0 | 1172.2 | 1287.7 | 67.27 ± 3.33 |
+
+* 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>
+## Screenshots
 
-<p align="center">
+![](https://user-images.githubusercontent.com/36154121/213618143-e5182e39-731e-4817-87dd-1a6a0f38a449.gif)
-  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>
-
-<h2 align="center">Screenshots</h2>
-
-<img src="https://user-images.githubusercontent.com/36154121/213618143-e5182e39-731e-4817-87dd-1a6a0f38a449.gif" />

src/file_manager.rs

@@ -1,9 +1,10 @@
 use anyhow::Result;
 use colored::Colorize;
+use std::path::PathBuf;
 
 #[derive(Debug, Clone)]
 pub struct File {
-    pub path: String,
+    pub path: PathBuf,
     pub size: Option<u64>,
     pub hash: Option<String>,
 }
@@ -11,8 +12,8 @@ pub struct File {
 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),
+            Ok(_) => println!("{}: {}", "DELETED".green(), file.path.display()),
-            Err(_) => println!("{}: {}", "FAILED".red(), file.path)
+            Err(_) => println!("{}: {}", "FAILED".red(), file.path.display())
         }
     });
 

src/filters.rs

@@ -1,8 +1,8 @@
 use crate::file_manager::File;
 use crate::params::Params;
 
-pub fn is_file_gt_minsize(app_opts: &Params, file: &File) -> bool {
+pub fn is_file_gt_min_size(app_opts: &Params, file: &File) -> bool {
-    match app_opts.get_minsize() {
+    match app_opts.get_min_size() {
         Some(msize) => match file.size {
             Some(fsize) => fsize >= msize,
             None => true,

src/main.rs

@@ -9,7 +9,6 @@ use anyhow::Result;
 use app::App;
 use clap::Parser;
 
-#[tokio::main]
+fn main() -> Result<()> {
-async fn main() -> Result<()> {
     App::init(&params::Params::parse())
 }

src/output.rs

@@ -5,14 +5,19 @@ use chrono::offset::Utc;
 use chrono::DateTime;
 use colored::Colorize;
 use dashmap::DashMap;
+use indicatif::{ProgressBar, ProgressIterator, ProgressStyle};
 use itertools::Itertools;
 use prettytable::{format, row, Table};
 use std::io::Write;
+use std::path::Path;
+use std::time::Duration;
 use std::{fs, io};
 use unicode_segmentation::UnicodeSegmentation;
 
-fn format_path(path: &str, opts: &Params) -> Result<String> {
+fn format_path(path: &Path, opts: &Params) -> Result<String> {
-    let display_path = path.replace(&opts.get_directory()?, "");
+    let display_path = path
+        .to_string_lossy()
+        .replace(opts.get_directory()?.to_string_lossy().as_ref(), "");
     let display_range = if display_path.chars().count() > 32 {
         display_path
             .graphemes(true)
@@ -26,14 +31,14 @@ fn format_path(path: &str, opts: &Params) -> Result<String> {
         display_path
     };
 
-    Ok(format!("...{:<32}", display_range))
+    Ok(format!("...{display_range:<32}"))
 }
 
 fn file_size(file: &File) -> Result<String> {
     Ok(format!("{:>12}", bytesize::ByteSize::b(file.size.unwrap())))
 }
 
-fn modified_time(path: &String) -> Result<String> {
+fn modified_time(path: &Path) -> Result<String> {
     let mdata = fs::metadata(path)?;
     let modified_time: DateTime<Utc> = mdata.modified()?.into();
 
@@ -73,7 +78,7 @@ fn process_group_action(duplicates: &Vec<File>, dup_index: usize, dup_size: usiz
         .split(',')
         .filter(|element| !element.is_empty())
         .map(|index| index.parse::<usize>().unwrap_or_default())
-        .collect_vec();
+        .collect::<Vec<usize>>();
 
     if parsed_file_indices
         .clone()
@@ -99,12 +104,12 @@ fn process_group_action(duplicates: &Vec<File>, dup_index: usize, dup_size: usiz
         .clone()
         .enumerate()
         .for_each(|(index, file)| {
-            println!("{}: {}", index.to_string().blue(), file.path);
+            println!("{}: {}", index.to_string().blue(), file.path.display());
         });
 
     match scan_group_confirmation().unwrap() {
         true => {
-            file_manager::delete_files(files_to_delete.collect_vec()).ok();
+            file_manager::delete_files(files_to_delete.collect::<Vec<File>>()).ok();
         }
         false => println!("{}", "\nCancelled Delete Operation.".red()),
     }
@@ -153,10 +158,19 @@ pub fn print(duplicates: DashMap<String, Vec<File>>, opts: &Params) {
     }
 
     let mut output_table = Table::new();
+    let progress_bar = ProgressBar::new(duplicates.len() as u64);
+    progress_bar.enable_steady_tick(Duration::from_millis(50));
+    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"]);
+
     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);
@@ -172,3 +186,32 @@ pub fn print(duplicates: DashMap<String, Vec<File>>, opts: &Params) {
 
     output_table.printstd();
 }
+
+#[allow(unused)]
+pub fn raw(duplicates: DashMap<String, Vec<File>>, opts: &Params) -> Result<()> {
+    if duplicates.is_empty() {
+        println!(
+            "\n{}",
+            "No duplicates found matching your search criteria.".green()
+        );
+        return Ok(());
+    }
+
+    duplicates
+        .into_iter()
+        .sorted_unstable_by_key(|(_, f)| f.first().and_then(|ff| ff.size).unwrap_or_default())
+        .for_each(|(_hash, group)| {
+            group.iter().for_each(|file| {
+                println!(
+                    "{}\t{}\t{}",
+                    format_path(&file.path, opts).unwrap_or_default().blue(),
+                    file_size(file).unwrap_or_default().red(),
+                    modified_time(&file.path).unwrap_or_default().yellow()
+                )
+            });
+
+            println!("---");
+        });
+
+    Ok(())
+}

src/params.rs

@@ -1,27 +1,38 @@
+use std::{fs, path::PathBuf};
+
 use anyhow::{anyhow, Result};
 use clap::{Parser, ValueHint};
-use std::{fs, path::PathBuf};
+use globwalk::{GlobWalker, GlobWalkerBuilder};
 
 #[derive(Parser, Debug)]
 #[command(author, version, about, long_about = None)]
 pub struct Params {
-    /// Filetypes to deduplicate (default = all)
+    /// Filetypes to deduplicate [default = all]
     #[arg(short, long)]
     pub types: Option<String>,
-    /// Run Deduplicator on dir different from pwd
+    /// Run Deduplicator on dir different from pwd (e.g., ~/Pictures )
-    #[arg(long, value_hint = ValueHint::DirPath)]
+    #[arg(value_hint = ValueHint::DirPath, value_name = "scan_dir_path")]
     pub dir: Option<PathBuf>,
     /// Delete files interactively
     #[arg(long, short)]
     pub interactive: bool,
-    /// Minimum filesize of duplicates to scan (e.g., 100B/1K/2M/3G/4T). [default = 0]
+    /// Minimum filesize of duplicates to scan (e.g., 100B/1K/2M/3G/4T).
+    #[arg(long, short = 's', default_value = "1b")]
+    pub min_size: Option<String>,
+    /// Max Depth to scan while looking for duplicates
+    #[arg(long, short = 'd')]
+    pub max_depth: Option<usize>,
+    /// Min Depth to scan while looking for duplicates
+    #[arg(long)]
+    pub min_depth: Option<usize>,
+    /// Follow links while scanning directories
     #[arg(long, short)]
-    pub minsize: Option<String>,
+    pub follow_links: bool,
 }
 
 impl Params {
-    pub fn get_minsize(&self) -> Option<u64> {
+    pub fn get_min_size(&self) -> Option<u64> {
-        match &self.minsize {
+        match &self.min_size {
             Some(msize) => match msize.parse::<bytesize::ByteSize>() {
                 Ok(units) => Some(units.0),
                 Err(_) => None,
@@ -30,35 +41,48 @@ impl Params {
         }
     }
 
-    pub fn get_directory(&self) -> Result<String> {
+    pub fn get_directory(&self) -> Result<PathBuf> {
-        let dir_pathbuf: PathBuf = self
+        let current_dir = std::env::current_dir()?;
-            .dir
+        let dir_path = self.dir.as_ref().unwrap_or(&current_dir).as_path();
-            .as_ref()
+        let dir = fs::canonicalize(dir_path)?;
-            .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();
-
         Ok(dir)
     }
 
-    pub fn get_glob_patterns(&self) -> PathBuf {
+    fn add_glob_min_depth(&self, builder: GlobWalkerBuilder) -> Result<GlobWalkerBuilder> {
-        match self.types.as_ref() {
+        match self.min_depth {
-            Some(filetypes) => vec![
+            Some(mindepth) => Ok(builder.min_depth(mindepth)),
-                self.get_directory().unwrap(),
+            None => Ok(builder),
-                String::from("**"),
-                format!("{{{}}}", filetypes),
-            ]
-            .iter()
-            .collect::<PathBuf>(),
-            None => vec![self.get_directory().unwrap().as_str(), "**", "*"]
-                .iter()
-                .collect::<PathBuf>(),
         }
     }
+
+    fn add_glob_max_depth(&self, builder: GlobWalkerBuilder) -> Result<GlobWalkerBuilder> {
+        match self.max_depth {
+            Some(maxdepth) => Ok(builder.max_depth(maxdepth)),
+            None => Ok(builder),
+        }
+    }
+
+    fn add_glob_follow_links(&self, builder: GlobWalkerBuilder) -> Result<GlobWalkerBuilder> {
+        match self.follow_links {
+            true => Ok(builder.follow_links(true)),
+            false => Ok(builder.follow_links(false)),
+        }
+    }
+
+    pub fn get_glob_walker(&self) -> Result<GlobWalker> {
+        let pattern: String = match self.types.as_ref() {
+            Some(filetypes) => format!("**/*{{{filetypes}}}"),
+            None => "**/*".to_string(),
+        };
+
+        let glob_walker_builder = self
+            .add_glob_min_depth(GlobWalkerBuilder::from_patterns(
+                self.get_directory()?,
+                &[pattern],
+            ))
+            .and_then(|builder| self.add_glob_max_depth(builder))
+            .and_then(|builder| self.add_glob_follow_links(builder))?;
+
+        glob_walker_builder.build().map_err(|e| anyhow!(e))
+    }
 }

src/scanner.rs

@@ -2,12 +2,15 @@ use crate::{file_manager::File, filters, params::Params};
 use anyhow::Result;
 use dashmap::DashMap;
 use fxhash::hash64 as hasher;
-use glob::glob;
+use indicatif::{ParallelProgressIterator, ProgressBar, ProgressIterator, ProgressStyle};
-use indicatif::{ParallelProgressIterator, ProgressStyle};
 use memmap2::Mmap;
 use rayon::prelude::*;
 use std::hash::Hasher;
-use std::{fs, path::PathBuf};
+use std::time::Duration;
+use std::{
+    fs,
+    path::{Path, PathBuf},
+};
 
 #[derive(Clone, Copy)]
 enum IndexCritera {
@@ -40,27 +43,43 @@ pub fn duplicates(app_opts: &Params) -> Result<DashMap<String, Vec<File>>> {
 }
 
 fn scan(app_opts: &Params) -> Result<Vec<File>> {
-    let glob_patterns = app_opts.get_glob_patterns().display().to_string();
+    let walker = app_opts.get_glob_walker()?;
-    let glob_iter = glob(&glob_patterns)?;
+    let progress = ProgressBar::new_spinner();
-    let files = glob_iter
+    let progress_style =
-        .filter(Result::is_ok)
+        ProgressStyle::with_template("{spinner:.green} [mapping paths] {pos} paths")?;
-        .map(|file| file.unwrap())
+    progress.set_style(progress_style);
+    progress.enable_steady_tick(Duration::from_millis(50));
+
+    let files = walker
+        .progress_with(progress)
+        .filter_map(Result::ok)
+        .map(|file| file.into_path())
         .filter(|fpath| fpath.is_file())
-        .collect::<Vec<PathBuf>>()
+        .collect::<Vec<PathBuf>>();
+
+    let scan_progress = ProgressBar::new(files.len() as u64);
+    let scan_progress_style = ProgressStyle::with_template(
+        "{spinner:.green} [processing mapped paths] [{wide_bar:.cyan/blue}] {pos}/{len} files",
+    )?;
+    scan_progress.set_style(scan_progress_style);
+    scan_progress.enable_steady_tick(Duration::from_millis(50));
+
+    let scan_results = files
         .into_par_iter()
-        .progress_with_style(ProgressStyle::with_template(
+        .progress_with(scan_progress)
-            "{spinner:.green} [processing scan results] [{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()),
+            size: Some(
+                fs::metadata(fpath)
+                    .map(|metadata| metadata.len())
+                    .unwrap_or_default(),
+            ),
         })
-        .filter(|file| filters::is_file_gt_minsize(app_opts, file))
+        .filter(|file| filters::is_file_gt_min_size(app_opts, file))
         .collect();
 
-    Ok(files)
+    Ok(scan_results)
 }
 
 fn process_file_index(
@@ -78,7 +97,7 @@ fn process_file_index(
         IndexCritera::Hash => {
             file.hash = Some(hash_file(&file.path).unwrap_or_default());
             store
-                .entry(file.clone().hash.unwrap())
+                .entry(file.clone().hash.unwrap_or_default())
                 .and_modify(|fileset| fileset.push(file.clone()))
                 .or_insert_with(|| vec![file]);
         }
@@ -90,17 +109,22 @@ fn index_files(
     index_criteria: IndexCritera,
 ) -> Result<DashMap<String, Vec<File>>> {
     let store: DashMap<String, Vec<File>> = DashMap::new();
+    let index_progress = ProgressBar::new(files.len() as u64);
+    let index_progress_style = ProgressStyle::with_template(
+        "{spinner:.green} [indexing files] [{wide_bar:.cyan/blue}] {pos}/{len} files",
+    )?;
+    index_progress.set_style(index_progress_style);
+    index_progress.enable_steady_tick(Duration::from_millis(50));
+
     files
         .into_par_iter()
-        .progress_with_style(ProgressStyle::with_template(
+        .progress_with(index_progress)
-            "{spinner:.green} [indexing files] [{wide_bar:.cyan/blue}] {pos}/{len} files",
-        )?)
         .for_each(|file| process_file_index(file, &store, index_criteria));
 
     Ok(store)
 }
 
-fn incremental_hashing(filepath: &str) -> Result<String> {
+fn incremental_hashing(filepath: &Path) -> Result<String> {
     let file = fs::File::open(filepath)?;
     let fmap = unsafe { Mmap::map(&file)? };
     let mut inchasher = fxhash::FxHasher::default();
@@ -111,12 +135,12 @@ fn incremental_hashing(filepath: &str) -> Result<String> {
     Ok(format!("{}", inchasher.finish()))
 }
 
-fn standard_hashing(filepath: &str) -> Result<String> {
+fn standard_hashing(filepath: &Path) -> Result<String> {
     let file = fs::read(filepath)?;
     Ok(hasher(&*file).to_string())
 }
 
-fn hash_file(filepath: &str) -> Result<String> {
+fn hash_file(filepath: &Path) -> Result<String> {
     let filemeta = fs::metadata(filepath)?;
 
     // NOTE: USE INCREMENTAL HASHING ONLY FOR FILES > 100MB