update NFC data from Unicode 13.0.0 to Unicode 14.0.0.

src/nfc_sets.cc

@@ -416,6 +416,23 @@ const std::map<unsigned, unsigned char> NFC_CombiningClass = {
 	{0x0859, 220},
 	{0x085A, 220},
 	{0x085B, 220},
+	{0x0898, 230},
+	{0x0899, 220},
+	{0x089A, 220},
+	{0x089B, 220},
+	{0x089C, 230},
+	{0x089D, 230},
+	{0x089E, 230},
+	{0x089F, 230},
+	{0x08CA, 230},
+	{0x08CB, 230},
+	{0x08CC, 230},
+	{0x08CD, 230},
+	{0x08CE, 230},
+	{0x08CF, 220},
+	{0x08D0, 220},
+	{0x08D1, 220},
+	{0x08D2, 220},
 	{0x08D3, 220},
 	{0x08D4, 230},
 	{0x08D5, 230},
@@ -476,6 +493,7 @@ const std::map<unsigned, unsigned char> NFC_CombiningClass = {
 	{0x0B3C, 7},
 	{0x0B4D, 9},
 	{0x0BCD, 9},
+	{0x0C3C, 7},
 	{0x0C4D, 9},
 	{0x0C55, 84},
 	{0x0C56, 91},
@@ -526,6 +544,7 @@ const std::map<unsigned, unsigned char> NFC_CombiningClass = {
 	{0x135E, 230},
 	{0x135F, 230},
 	{0x1714, 9},
+	{0x1715, 9},
 	{0x1734, 9},
 	{0x17D2, 9},
 	{0x17DD, 230},
@@ -561,6 +580,20 @@ const std::map<unsigned, unsigned char> NFC_CombiningClass = {
 	{0x1ABD, 220},
 	{0x1ABF, 220},
 	{0x1AC0, 220},
+	{0x1AC1, 230},
+	{0x1AC2, 230},
+	{0x1AC3, 220},
+	{0x1AC4, 220},
+	{0x1AC5, 230},
+	{0x1AC6, 230},
+	{0x1AC7, 230},
+	{0x1AC8, 230},
+	{0x1AC9, 230},
+	{0x1ACA, 220},
+	{0x1ACB, 230},
+	{0x1ACC, 230},
+	{0x1ACD, 230},
+	{0x1ACE, 230},
 	{0x1B34, 7},
 	{0x1B44, 9},
 	{0x1B6B, 230},
@@ -663,6 +696,7 @@ const std::map<unsigned, unsigned char> NFC_CombiningClass = {
 	{0x1DF7, 228},
 	{0x1DF8, 228},
 	{0x1DF9, 220},
+	{0x1DFA, 218},
 	{0x1DFB, 230},
 	{0x1DFC, 233},
 	{0x1DFD, 220},
@@ -840,7 +874,12 @@ const std::map<unsigned, unsigned char> NFC_CombiningClass = {
 	{0x10F4E, 220},
 	{0x10F4F, 220},
 	{0x10F50, 220},
+	{0x10F82, 230},
+	{0x10F83, 220},
+	{0x10F84, 230},
+	{0x10F85, 220},
 	{0x11046, 9},
+	{0x11070, 9},
 	{0x1107F, 9},
 	{0x110B9, 9},
 	{0x110BA, 7},
@@ -989,6 +1028,7 @@ const std::map<unsigned, unsigned char> NFC_CombiningClass = {
 	{0x1E134, 230},
 	{0x1E135, 230},
 	{0x1E136, 230},
+	{0x1E2AE, 230},
 	{0x1E2EC, 230},
 	{0x1E2ED, 230},
 	{0x1E2EE, 230},

src/scripts/README.md

@@ -0,0 +1,17 @@
+# How to update the Unicode data set
+
+1. Downlowd the newest version, e.g.
+   https://www.unicode.org/Public/zipped/latest/UCD.zip
+
+2. Extract the ZIP file to a folder of your choice.
+
+3. Copy/link "DerivedNormalizationProps.txt" and "UnicodeData.txt"
+   into this directory
+
+4. Run ./gen_sets.sh
+
+5. Copy the generated files nfc_sets.cc and nfc_sets.hh to the source directory.
+
+6. Commit it with message "update NFC data from Unicode X.X.X to Unicode Y.Y.Y."
+
+7. That's it.