Update CI workflows to install gawk and modify check command for UTF-8 support

The `make check`used to suppose that every chinese character is composed by 3 bytes when it is utf8 encoding. However, 𰻝 has 4 bytes.

Author: zonble

.github/workflows/continuous-build-data.yml

@@ -18,6 +18,8 @@ jobs:
       - uses: actions/setup-python@v6
         with:
           python-version: '3.12'
+      - name: Install gawk
+        run: brew install gawk
       - name: Test data files
         run: make check
         working-directory: Source/Data

.github/workflows/continuous-integration-workflow-xcode-latest.yml

@@ -88,6 +88,8 @@ jobs:
         run: xcodebuild -scheme McBopomofo -configuration Release build
       - name: Build McBopomofoInstaller
         run: xcodebuild -scheme McBopomofoInstaller -configuration Release build
+      - name: Install gawk
+        run: brew install gawk
       - name: Test data files
         run: make check
         working-directory: Source/Data

Source/Data/Makefile

@@ -61,12 +61,13 @@ sort:
 	@mv tmp exclusion.txt
 
 check: SHELL:=/bin/bash
-check: export LC_ALL=C
+check: export LC_ALL=UTF-8
 check:
-	@awk 'length($$1)/3!=NF-1' BPMFMappings.txt
-	@awk '{print $$2,$$3,$$4,$$5,$$6,$$7}' BPMFMappings.txt | awk '/一/'
-	@diff -u <(awk '{print $$1}' BPMFMappings.txt|sort -u) \
-                 <(awk 'length($$1)>4{print $$1}' phrase.occ|sort -u)
+# 	@brew install gawk
+	@gawk 'length($$1)!=NF-1' BPMFMappings.txt
+	@gawk '{print $$2,$$3,$$4,$$5,$$6,$$7}' BPMFMappings.txt | gawk '/一/'
+	@diff -u <(gawk 'length($$1)>1{print $$1}' BPMFMappings.txt|sort -u) \
+                 <(gawk 'length($$1)>1{print $$1}' phrase.occ|sort -u)
 
 tidy:
 	@sed -i '' -e 's/ //g' phrase.occ