Update gen-break-table.py for Unicode 13

1 files changed, 19 insertions, 8 deletions

diff --git a/tools/gen-break-table.py b/tools/gen-break-table.py
index 2c8a7d70..5d346c8c 100755
--- a/tools/gen-break-table.py
+++ b/tools/gen-break-table.py
@@ -9,20 +9,21 @@ from collections import OrderedDict
 header = []
 ranges = OrderedDict()
 
-def load_data(filename):
+def load_data(filename, prefix=""):
         global header, ranges
         f = open(filename)
         lines = f.readlines()
         for line in lines:
-                header.append(line)
                 if not line.startswith("#"):
                         break
+                header.append(line)
 
         for line in lines:
 	        line = line.strip()
 	        if not line or line[0] == '#':
 		        continue
 	        rang, typ = [s.strip() for s in line.split('#')[0].split(';')[:2]]
+	        typ = prefix + typ
 
 	        rang = [int(s, 16) for s in rang.split('..')]
 	        if len(rang) > 1:
@@ -87,6 +88,7 @@ def print_ranges(ranges):
 def print_balanced_search(ranges):
         if 4 >= len(ranges):
                 print_ranges(ranges)
+                print("return FALSE;")
                 return
 
         length = len(ranges)
@@ -116,7 +118,7 @@ def print_table():
         print("/*")
         print(" * The following tables are generated by running:")
         print(" *")
-        print(" *   ./gen-break-table.py SentenceBreakProperty.txt IndicSyllabicCategory.txt | indent")
+        print(" *   ./gen-break-table.py SentenceBreakProperty.txt IndicSyllabicCategory.txt EastAsianWidth.txt | indent")
         print(" *")
         print(" * on files with these headers:")
         print(" *")
@@ -132,14 +134,22 @@ def print_table():
 
         for typ,s in ranges.items():
 	        if typ not in ['STerm',
-		               'Virama',
-		               'Vowel_Dependent']: continue
+	                       'Virama',
+	                       'Vowel_Dependent',
+	                       'Consonant_Prefixed',
+	                       'Consonant_Preceding_Repha']: continue
 	        print()
 	        print("static inline gboolean _pango_is_%s (gunichar wc)" % typ)
 	        print("{")
-                print_balanced_search(sorted(s))
+	        print_balanced_search(sorted(s))
 	        print("}")
 
+        s = ranges["EastAsian_F"] + ranges["EastAsian_W"] + ranges["EastAsian_H"]
+        print("static inline gboolean _pango_is_EastAsianWide (gunichar wc)")
+        print("{")
+        print_balanced_search(sorted(s))
+        print("}")
+
         print()
         print("#endif /* PANGO_BREAK_TABLE_H */")
         print()
@@ -147,10 +157,11 @@ def print_table():
 
 
 if __name__ == "__main__":
-        if len (sys.argv) != 3:
-	        print("usage: ./gen-break-table.py SentenceBreakProperty.txt IndicSyllabicCategory.txt | indent", file=sys.stderr)
+        if len (sys.argv) != 4:
+	        print("usage: ./gen-break-table.py SentenceBreakProperty.txt IndicSyllabicCategory.txt EastAsianWidth.txt | indent", file=sys.stderr)
 	        sys.exit (1)
 
         load_data(sys.argv[1])
         load_data(sys.argv[2])
+        load_data(sys.argv[3], "EastAsian_")
         print_table()