license-scan: add latest spdx license data

The latest SPDX data includes the Pixar license, which is a modified
Apache-2.0 license. This rare license often confuses the scanner when it
encounters the common Apache-2.0 license, so a new config option
`spdx.ignore-licenses` has been added to ignore specific licenses from
the input SPDX data.

This change also adds the ability to skip directories when scanning
sources. This is useful for scanning the source directory filled with
sample license texts in the spdx crate itself.

Author: cbgbt

configs/cargo-deny/clarify.toml

@@ -1,3 +1,10 @@
+[spdx]
+ignore-licenses = [
+    # Apache-2.0 is often misclassified as Pixar, which is a significantly more rare
+    # https://github.com/jpeddicord/askalono/issues/94
+    "Pixar"
+]
+
 [clarify.askalono]
 expression = "Apache-2.0"
 license-files = [

configs/cargo-make/clarify.toml

@@ -1,3 +1,10 @@
+[spdx]
+ignore-licenses = [
+    # Apache-2.0 is often misclassified as Pixar, which is a significantly more rare
+    # https://github.com/jpeddicord/askalono/issues/94
+    "Pixar"
+]
+
 [clarify.bstr]
 expression = "(MIT OR Apache-2.0) AND Unicode-DFS-2016"
 license-files = [

license-scan/Cargo.lock

@@ -17,8 +17,9 @@ ignore = "0.4"
 lazy_static = "1"
 semver = { version = "1", features = ["serde"] }
 serde = { version = "1", features = ["derive"] }
-spdx = "0.3"
+spdx = "0.10"
 structopt = { version = "0.3", default-features = false }
+tempfile = "3"
 toml = "0.8"
 twox-hash = "1"
 walkdir = "2"

license-scan/Cargo.toml

@@ -1,3 +1,10 @@
+[spdx]
+ignore-licenses = [
+    # Apache-2.0 is often misclassified as Pixar, which is a significantly more rare
+    # https://github.com/jpeddicord/askalono/issues/94
+    "Pixar"
+]
+
 [clarify.askalono]
 expression = "Apache-2.0"
 license-files = [
@@ -21,7 +28,6 @@ license-files = [
     { path = "COPYING", hash = 0x278afbcf },
     { path = "LICENSE-APACHE", hash = 0x24b54f4b },
     { path = "LICENSE-MIT", hash = 0x462dee44 },
-    { path = "src/unicode/data/LICENSE-UNICODE", hash = 0x70f7339 },
 ]
 
 [clarify.crossbeam-channel]
@@ -58,12 +64,16 @@ license-files = [
     { path = "src/unicode_tables/LICENSE-UNICODE", hash = 0xa7f28b93 },
 ]
 
-[clarify.unicode-ident]
-expression = "(MIT OR Apache-2.0) AND Unicode-DFS-2016"
+[clarify.spdx]
+expression = "MIT OR Apache-2.0"
 license-files = [
-    { path = "LICENSE-APACHE", hash = 0xb5518783 },
-    { path = "LICENSE-MIT", hash = 0x386ca1bc },
-    { path = "LICENSE-UNICODE", hash = 0x9698cbbe },
+    { path = "LICENSE-MIT", hash = 0xa502ee8a },
+    { path = "LICENSE-APACHE", hash = 0x4fccb6b7 },
+]
+skip-dirs = [
+    # The spdx crate contains the full text of referred licenses
+    "src/text/licenses",
+    "src/text/exceptions",
 ]
 
 [clarify.zstd-safe]