Add license detection

.gitattributes

@@ -1 +1,2 @@
 src/text/** linguist-vendored
+src/detection/cache.bin.zstd filter=lfs diff=lfs merge=lfs -text

.github/workflows/ci.yaml

@@ -12,9 +12,9 @@ name: CI
 jobs:
   lint:
     name: Lint
-    runs-on: ubuntu-22.04
+    runs-on: ubuntu-24.04
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v6
       - uses: dtolnay/rust-toolchain@stable
         with:
           components: "rustfmt,clippy"
@@ -30,16 +30,16 @@ jobs:
 
   deny-check:
     name: cargo-deny check
-    runs-on: ubuntu-22.04
+    runs-on: ubuntu-24.04
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v6
       - uses: EmbarkStudios/cargo-deny-action@v2
 
   msrv-check:
     name: Minimum Stable Rust Version Check
-    runs-on: ubuntu-22.04
+    runs-on: ubuntu-24.04
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v6
       - uses: dtolnay/[email protected]
       - run: cargo fetch
       - name: cargo check
@@ -49,12 +49,21 @@ jobs:
     name: Test
     strategy:
       matrix:
-        os: [ubuntu-22.04]
+        os: [ubuntu-24.04]
     runs-on: ${{ matrix.os }}
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v6
+        with:
+          lfs: true
+      - run: git lfs checkout
       - uses: dtolnay/rust-toolchain@stable
       - run: cargo fetch
       - name: cargo build
         run: cargo build --tests --all-features
       - run: cargo test --all-features
+
+  test_success:
+    runs-on: ubuntu-24.04
+    needs: [lint, test, deny-check, msrv-check]
+    steps:
+      - run: echo "All test jobs passed"

CHANGELOG.md

@@ -8,6 +8,9 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 <!-- next-header -->
 ## [Unreleased] - ReleaseDate
+### Added
+- [PR#84](https://github.com/EmbarkStudios/spdx/pull/84) resolved [#67](https://github.com/EmbarkStudios/spdx/issues/67) by inling the `askalono` crate to allow detection of license texts or headers from arbitrary text data. There are multiple features flags associated with this new feature.
+
 ## [0.12.0] - 2025-08-19
 ### Added
 - [PR#81](https://github.com/EmbarkStudios/spdx/pull/81) resolved [#68](https://github.com/EmbarkStudios/spdx/issues/68) by adding support for the ` WITH [%s"DocumentRef-"(idstring)":"]%s"AdditionRef-"(idstring)` syntax. Thanks [@weihanglo](https://github.com/weihanglo)!

Cargo.toml

@@ -26,10 +26,23 @@ include = [
 [features]
 # Includes the full canonical text of each license
 text = []
+# Allows analysis of text to determine if it might be an SPDX license text
+detection = ["regex", "unicode-normalization"]
+# Allows de/serialization of a spdx::detection::Store for quicker loading
+detection-cache = ["detection", "zstd"]
+# Inlines a cache into this crate, which contains all of the licenses from the
+# SPDX crate that the crate version was packaged with
+detection-inline-cache = ["detection-cache"]
+# Performs license detection in parallel within the same text
+detection-parallel = ["detection", "rayon"]
 
 [dependencies]
+rayon = { version = "1.11", optional = true }
+regex = { version = "1.12", optional = true }
 # In most cases expressions are quite small so we can avoid heap allocations
 smallvec = "1.15"
+unicode-normalization = { version = "0.1", optional = true }
+zstd = { version = "0.13", optional = true }
 
 [dev-dependencies]
 # Used to print colored diffs in case of test failures