Fix 'AND' detection failures and filter redundant 'OR' matches

src/licensedcode/data/rules/apache-2.0_and_mit_2.RULE

@@ -0,0 +1,7 @@
+---
+license_expression: apache-2.0 AND mit
+is_license_reference: yes
+relevance: 100
+minimum_coverage: 100
+---
+licensed under Apache-2.0 AND MIT

src/licensedcode/data/rules/apache-2.0_or_mit_55.RULE

@@ -0,0 +1,7 @@
+---
+license_expression: apache-2.0 OR mit
+is_license_reference: yes
+relevance: 100
+minimum_coverage: 100
+---
+licensed under Apache-2.0 OR MIT

tests/formattedcode/data/common/manifests-expected.yaml

@@ -11,6 +11,7 @@ headers:
       --license-references: yes
       --license-text: yes
       --package: yes
+      --processes: -1
       --summary: yes
       --url: yes
       --yaml: <file>
@@ -21,17 +22,17 @@ headers:
       for any legal advice.
       ScanCode is a free software code scanning tool from nexB Inc. and others.
       Visit https://github.com/nexB/scancode-toolkit/ for support and download.
-    output_format_version: 4.0.0
+    output_format_version: 4.1.0
     message:
     errors: []
     warnings: []
     extra_data:
       system_environment:
         operating_system: linux
         cpu_architecture: 64
-        platform: Linux-5.15.0-141-generic-x86_64-with-glibc2.35
-        platform_version: '#151-Ubuntu SMP Sun May 18 21:35:19 UTC 2025'
-        python_version: 3.10.12 (main, Feb  4 2025, 14:57:36) [GCC 11.4.0]
+        platform: Linux-6.6.87.2-microsoft-standard-WSL2-x86_64-with-glibc2.39
+        platform_version: '#1 SMP PREEMPT_DYNAMIC Thu Jun  5 18:30:46 UTC 2025'
+        python_version: 3.12.3 (main, Jan  8 2026, 11:30:50) [GCC 13.3.0]
       spdx_license_list_version: '3.27'
       files_count: 4
 summary:

tests/formattedcode/data/yaml/package-and-licenses-expected.yaml

@@ -11,6 +11,7 @@ headers:
       --license-references: yes
       --license-text: yes
       --package: yes
+      --processes: -1
       --summary: yes
       --url: yes
       --yaml: <file>
@@ -21,17 +22,17 @@ headers:
       for any legal advice.
       ScanCode is a free software code scanning tool from nexB Inc. and others.
       Visit https://github.com/nexB/scancode-toolkit/ for support and download.
-    output_format_version: 4.0.0
+    output_format_version: 4.1.0
     message:
     errors: []
     warnings: []
     extra_data:
       system_environment:
         operating_system: linux
         cpu_architecture: 64
-        platform: Linux-5.15.0-141-generic-x86_64-with-glibc2.35
-        platform_version: '#151-Ubuntu SMP Sun May 18 21:35:19 UTC 2025'
-        python_version: 3.10.12 (main, Feb  4 2025, 14:57:36) [GCC 11.4.0]
+        platform: Linux-6.6.87.2-microsoft-standard-WSL2-x86_64-with-glibc2.39
+        platform_version: '#1 SMP PREEMPT_DYNAMIC Thu Jun  5 18:30:46 UTC 2025'
+        python_version: 3.12.3 (main, Jan  8 2026, 11:30:50) [GCC 13.3.0]
       spdx_license_list_version: '3.27'
       files_count: 4
 summary:
@@ -47,7 +48,7 @@ summary:
   declared_holder: Example Corp.
   primary_language: Python
   other_license_expressions:
-    - value: apache-2.0 AND (apache-2.0 OR mit)
+    - value: apache-2.0 OR mit
       count: 1
     - value: mit
       count: 1
@@ -316,36 +317,23 @@ license_detections:
         rule_identifier: apache-2.0_65.RULE
         rule_url: https://github.com/nexB/scancode-toolkit/tree/develop/src/licensedcode/data/rules/apache-2.0_65.RULE
         matched_text: license = Apache-2.0
-  - identifier: apache_2_0_and__apache_2_0_or_mit-ab5115d2-1eff-af76-1473-34378a32b2bb
-    license_expression: apache-2.0 AND (apache-2.0 OR mit)
-    license_expression_spdx: Apache-2.0 AND (Apache-2.0 OR MIT)
+  - identifier: apache_2_0_or_mit-63aee60b-3389-cc69-da5a-7dd28d1b8e2e
+    license_expression: apache-2.0 OR mit
+    license_expression_spdx: Apache-2.0 OR MIT
     detection_count: 1
     reference_matches:
-      - license_expression: apache-2.0
-        license_expression_spdx: Apache-2.0
-        from_file: package-and-licenses/README.txt
-        start_line: 3
-        end_line: 3
-        matcher: 2-aho
-        score: '100.0'
-        matched_length: 5
-        match_coverage: '100.0'
-        rule_relevance: 100
-        rule_identifier: apache-2.0_1109.RULE
-        rule_url: https://github.com/nexB/scancode-toolkit/tree/develop/src/licensedcode/data/rules/apache-2.0_1109.RULE
-        matched_text: This is licensed under Apache-2.0 or MIT
       - license_expression: apache-2.0 OR mit
         license_expression_spdx: Apache-2.0 OR MIT
         from_file: package-and-licenses/README.txt
         start_line: 3
         end_line: 3
         matcher: 2-aho
         score: '100.0'
-        matched_length: 5
+        matched_length: 7
         match_coverage: '100.0'
         rule_relevance: 100
-        rule_identifier: apache-2.0_or_mit_36.RULE
-        rule_url: https://github.com/nexB/scancode-toolkit/tree/develop/src/licensedcode/data/rules/apache-2.0_or_mit_36.RULE
+        rule_identifier: apache-2.0_or_mit_55.RULE
+        rule_url: https://github.com/nexB/scancode-toolkit/tree/develop/src/licensedcode/data/rules/apache-2.0_or_mit_55.RULE
         matched_text: This is licensed under Apache-2.0 or MIT
   - identifier: mit-cacd5c0c-204a-85c2-affc-e4c125b2492a
     license_expression: mit
@@ -356,7 +344,7 @@ license_detections:
         license_expression_spdx: MIT
         from_file: package-and-licenses/mit.LICENSE
         start_line: 2
-        end_line: '19'
+        end_line: 19
         matcher: 1-hash
         score: '100.0'
         matched_length: 161
@@ -846,33 +834,6 @@ license_rule_references:
       WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
       See the License for the specific language governing permissions and
       limitations under the License.
-  - license_expression: apache-2.0
-    identifier: apache-2.0_1109.RULE
-    language: en
-    rule_url: https://github.com/nexB/scancode-toolkit/tree/develop/src/licensedcode/data/rules/apache-2.0_1109.RULE
-    is_license_text: no
-    is_license_notice: yes
-    is_license_reference: no
-    is_license_tag: no
-    is_license_intro: no
-    is_license_clue: no
-    is_required_phrase: no
-    skip_for_required_phrase_generation: no
-    is_continuous: no
-    is_builtin: yes
-    is_from_license: no
-    is_synthetic: no
-    length: 5
-    relevance: 100
-    minimum_coverage: 80
-    referenced_filenames: []
-    notes:
-    ignorable_copyrights: []
-    ignorable_holders: []
-    ignorable_authors: []
-    ignorable_urls: []
-    ignorable_emails: []
-    text: licenced under {{Apache 2.0}}
   - license_expression: apache-2.0
     identifier: apache-2.0_65.RULE
     language: en
@@ -901,22 +862,22 @@ license_rule_references:
     ignorable_emails: []
     text: license="Apache-2.0
   - license_expression: apache-2.0 OR mit
-    identifier: apache-2.0_or_mit_36.RULE
+    identifier: apache-2.0_or_mit_55.RULE
     language: en
-    rule_url: https://github.com/nexB/scancode-toolkit/tree/develop/src/licensedcode/data/rules/apache-2.0_or_mit_36.RULE
+    rule_url: https://github.com/nexB/scancode-toolkit/tree/develop/src/licensedcode/data/rules/apache-2.0_or_mit_55.RULE
     is_license_text: no
     is_license_notice: no
     is_license_reference: yes
     is_license_tag: no
     is_license_intro: no
     is_license_clue: no
-    is_required_phrase: yes
+    is_required_phrase: no
     skip_for_required_phrase_generation: no
     is_continuous: no
     is_builtin: yes
     is_from_license: no
     is_synthetic: no
-    length: 5
+    length: 7
     relevance: 100
     minimum_coverage: 80
     referenced_filenames: []
@@ -926,7 +887,8 @@ license_rule_references:
     ignorable_authors: []
     ignorable_urls: []
     ignorable_emails: []
-    text: apache-2.0 OR MIT
+    text: |
+      licensed under Apache-2.0 OR MIT
   - license_expression: mit
     identifier: mit.LICENSE
     language: en
@@ -1069,39 +1031,26 @@ files:
     package_data: []
     for_packages:
       - pkg:pypi/codebase?uuid=fixed-uid-done-for-testing-5642512d1758
-    detected_license_expression: apache-2.0 AND (apache-2.0 OR mit)
-    detected_license_expression_spdx: Apache-2.0 AND (Apache-2.0 OR MIT)
+    detected_license_expression: apache-2.0 OR mit
+    detected_license_expression_spdx: Apache-2.0 OR MIT
     license_detections:
-      - license_expression: apache-2.0 AND (apache-2.0 OR mit)
-        license_expression_spdx: Apache-2.0 AND (Apache-2.0 OR MIT)
+      - license_expression: apache-2.0 OR mit
+        license_expression_spdx: Apache-2.0 OR MIT
         matches:
-          - license_expression: apache-2.0
-            license_expression_spdx: Apache-2.0
-            from_file: package-and-licenses/README.txt
-            start_line: 3
-            end_line: 3
-            matcher: 2-aho
-            score: '100.0'
-            matched_length: 5
-            match_coverage: '100.0'
-            rule_relevance: 100
-            rule_identifier: apache-2.0_1109.RULE
-            rule_url: https://github.com/nexB/scancode-toolkit/tree/develop/src/licensedcode/data/rules/apache-2.0_1109.RULE
-            matched_text: This is licensed under Apache-2.0 or MIT
           - license_expression: apache-2.0 OR mit
             license_expression_spdx: Apache-2.0 OR MIT
             from_file: package-and-licenses/README.txt
             start_line: 3
             end_line: 3
             matcher: 2-aho
             score: '100.0'
-            matched_length: 5
+            matched_length: 7
             match_coverage: '100.0'
             rule_relevance: 100
-            rule_identifier: apache-2.0_or_mit_36.RULE
-            rule_url: https://github.com/nexB/scancode-toolkit/tree/develop/src/licensedcode/data/rules/apache-2.0_or_mit_36.RULE
+            rule_identifier: apache-2.0_or_mit_55.RULE
+            rule_url: https://github.com/nexB/scancode-toolkit/tree/develop/src/licensedcode/data/rules/apache-2.0_or_mit_55.RULE
             matched_text: This is licensed under Apache-2.0 or MIT
-        identifier: apache_2_0_and__apache_2_0_or_mit-ab5115d2-1eff-af76-1473-34378a32b2bb
+        identifier: apache_2_0_or_mit-63aee60b-3389-cc69-da5a-7dd28d1b8e2e
     license_clues: []
     percentage_of_license_text: '50.0'
     copyrights:
@@ -1324,8 +1273,8 @@ files:
         start_line: 4
         end_line: 4
       - url: http://www.apache.org/licenses/LICENSE-2.0
-        start_line: '196'
-        end_line: '196'
+        start_line: 196
+        end_line: 196
     files_count: '0'
     dirs_count: '0'
     size_count: '0'
@@ -1368,7 +1317,7 @@ files:
             license_expression_spdx: MIT
             from_file: package-and-licenses/mit.LICENSE
             start_line: 2
-            end_line: '19'
+            end_line: 19
             matcher: 1-hash
             score: '100.0'
             matched_length: 161

tests/formattedcode/data/yaml/simple-expected.yaml

@@ -6,6 +6,7 @@ headers:
       --info: yes
       --license: yes
       --package: yes
+      --processes: -1
       --yaml: <file>
     notice: |
       Generated with ScanCode and provided on an "AS IS" BASIS, WITHOUT WARRANTIES
@@ -14,17 +15,17 @@ headers:
       for any legal advice.
       ScanCode is a free software code scanning tool from nexB Inc. and others.
       Visit https://github.com/nexB/scancode-toolkit/ for support and download.
-    output_format_version: 4.0.0
+    output_format_version: 4.1.0
     message:
     errors: []
     warnings: []
     extra_data:
       system_environment:
         operating_system: linux
         cpu_architecture: 64
-        platform: Linux-5.15.0-141-generic-x86_64-with-glibc2.35
-        platform_version: '#151-Ubuntu SMP Sun May 18 21:35:19 UTC 2025'
-        python_version: 3.10.12 (main, Feb  4 2025, 14:57:36) [GCC 11.4.0]
+        platform: Linux-6.6.87.2-microsoft-standard-WSL2-x86_64-with-glibc2.39
+        platform_version: '#1 SMP PREEMPT_DYNAMIC Thu Jun  5 18:30:46 UTC 2025'
+        python_version: 3.12.3 (main, Jan  8 2026, 11:30:50) [GCC 13.3.0]
       spdx_license_list_version: '3.27'
       files_count: 1
 packages: []

tests/licensedcode/data/datadriven/lic1/apache-2.0_and_mit_issue_4690.txt

@@ -0,0 +1 @@
+licensed under Apache-2.0 AND MIT

tests/licensedcode/data/datadriven/lic1/apache-2.0_and_mit_issue_4690.txt.yml

@@ -0,0 +1,2 @@
+license_expressions:
+  - apache-2.0 AND mit

tests/licensedcode/data/datadriven/lic1/apache-2.0_or_mit_issue_4690.txt

@@ -0,0 +1 @@
+licensed under Apache-2.0 OR MIT

tests/licensedcode/data/datadriven/lic1/apache-2.0_or_mit_issue_4690.txt.yml

@@ -0,0 +1,2 @@
+license_expressions:
+  - apache-2.0 OR mit