feat(classification): add semantic classifier for URL and domain detection

.github/workflows/docs.yml

@@ -36,7 +36,7 @@ jobs:
         uses: jontze/action-mdbook@v4
         with:
           token: ${{ secrets.GITHUB_TOKEN }}
-          mdbook-version: 0.4.52
+          mdbook-version: 0.5.2
           use-mermaid: true
           use-toc: true
           use-admonish: true
@@ -45,7 +45,7 @@ jobs:
         uses: cargo-bins/cargo-binstall@main
 
       - name: Install mdbook plugins
-        run: cargo binstall mdbook-tabs mdbook-i18n-helpers mdbook-alerts mdbook-yml-header mdbook-image-size --no-confirm
+        run: cargo binstall mdbook-tabs mdbook-i18n-helpers mdbook-yml-header mdbook-image-size --no-confirm
 
       - name: Build mdBook
         run: |

Cargo.toml

@@ -22,7 +22,9 @@ path = "src/main.rs"
 clap = { version = "4.5.54", features = ["derive"] }
 entropy = "0.4.2"
 goblin = "0.10.4"
+lazy_static = "1.5"
 pelite = "0.10.0"
+regex = "1.12.2"
 serde = { version = "1.0.228", features = ["derive"] }
 serde_json = "1.0.148"
 thiserror = "2.0.17"

src/classification/mod.rs

@@ -1 +1,4 @@
 // String analysis and tagging
+
+pub mod semantic;
+pub use semantic::SemanticClassifier;