Merge pull request #52 from github/ajhenry/extract-licenses

Add method for extracting licenses from expression

Author: ajhenry

README.md

@@ -131,6 +131,30 @@ assert.True(valid)
 assert.NotContains(invalidLicenses, "MIT AND APACHE-2.0")
 ```
 
+### ExtractLicenses
+
+```go
+func ExtractLicenses(expression string) ([]string, error)
+```
+
+Function `ExtractLicenses` is used to extract licenses from the given expression without duplicates.
+
+**parameter: expression**
+
+`expression` is an SPDX expression string.
+
+**returns**
+
+Function `ExtractLicenses` has 2 return values. First is `[]string` which contains all of the SPDX licenses without duplicates.
+
+The second return value is an `error` which is not `nil` if the given expression is not a valid SPDX expression.
+
+#### Example
+
+```go
+licenses, err := ExtractLicenses("(MIT AND APACHE-2.0) OR (APACHE-2.0)")
+assert.Equal(licenses, []string{"MIT", "Apache-2.0"})
+```
 
 ## Background
 

spdxexp/extracts.go

@@ -0,0 +1,21 @@
+package spdxexp
+
+// ExtractLicenses extracts licenses from the given expression without duplicates.
+// Returns an array of licenses or error if error occurs during processing.
+func ExtractLicenses(expression string) ([]string, error) {
+	node, err := parse(expression)
+	if err != nil {
+		return nil, err
+	}
+
+	expanded := node.expand(true)
+	licenses := make([]string, 0)
+	allLicenses := flatten(expanded)
+	for _, licenseNode := range allLicenses {
+		licenses = append(licenses, *licenseNode.reconstructedLicenseString())
+	}
+
+	licenses = removeDuplicateStrings(licenses)
+
+	return licenses, nil
+}

spdxexp/extracts_test.go

@@ -0,0 +1,34 @@
+package spdxexp
+
+import (
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+)
+
+func TestExtractLicenses(t *testing.T) {
+	tests := []struct {
+		name              string
+		inputExpression   string
+		extractedLicenses []string
+	}{
+		{"Single license", "MIT", []string{"MIT"}},
+		{"AND'ed licenses", "MIT AND Apache-2.0", []string{"MIT", "Apache-2.0"}},
+		{"AND'ed & OR'ed licenses", "(MIT AND Apache-2.0) OR GPL-3.0", []string{"GPL-3.0", "MIT", "Apache-2.0"}},
+		{"ONLY modifiers", "LGPL-2.1-only OR MIT OR BSD-3-Clause", []string{"MIT", "BSD-3-Clause", "LGPL-2.1-only"}},
+		{"WITH modifiers", "GPL-2.0-or-later WITH Bison-exception-2.2", []string{"GPL-2.0-or-later+ WITH Bison-exception-2.2"}},
+		{"Invalid SPDX expression", "MIT OR INVALID", nil},
+	}
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			licenses, err := ExtractLicenses(test.inputExpression)
+			assert.ElementsMatch(t, test.extractedLicenses, licenses)
+			if test.extractedLicenses == nil {
+				assert.Error(t, err)
+			} else {
+				assert.NoError(t, err)
+			}
+		})
+	}
+}

spdxexp/helpers.go

@@ -0,0 +1,24 @@
+package spdxexp
+
+// flatten will take an array of nested array and return
+// all nested elements in an array. e.g. [[1,2,[3]],4] -> [1,2,3,4]
+func flatten[T any](lists [][]T) []T {
+	var res []T
+	for _, list := range lists {
+		res = append(res, list...)
+	}
+	return res
+}
+
+// removeDuplicateStrings will remove all duplicates from a slice
+func removeDuplicateStrings(sliceList []string) []string {
+	allKeys := make(map[string]bool)
+	list := []string{}
+	for _, item := range sliceList {
+		if _, value := allKeys[item]; !value {
+			allKeys[item] = true
+			list = append(list, item)
+		}
+	}
+	return list
+}