Make gen-* scripts LC_ALL=C compatible (#942)

src/gen-arabic-table.py

@@ -2,14 +2,13 @@
 
 from __future__ import print_function, division, absolute_import
 
-import sys
-import os.path
+import io, os.path, sys
 
 if len (sys.argv) != 4:
 	print ("usage: ./gen-arabic-table.py ArabicShaping.txt UnicodeData.txt Blocks.txt", file=sys.stderr)
 	sys.exit (1)
 
-files = [open (x) for x in sys.argv[1:]]
+files = [io.open (x, encoding='utf-8') for x in sys.argv[1:]]
 
 headers = [[files[0].readline (), files[0].readline ()], [files[2].readline (), files[2].readline ()]]
 headers.append (["UnicodeData.txt does not have a header."])

src/gen-indic-table.py

@@ -2,7 +2,7 @@
 
 from __future__ import print_function, division, absolute_import
 
-import sys
+import io, sys
 
 if len (sys.argv) != 4:
 	print ("usage: ./gen-indic-table.py IndicSyllabicCategory.txt IndicPositionalCategory.txt Blocks.txt", file=sys.stderr)
@@ -32,7 +32,7 @@ ALLOWED_BLOCKS = [
 	'Myanmar Extended-A',
 ]
 
-files = [open (x) for x in sys.argv[1:]]
+files = [io.open (x, encoding='utf-8') for x in sys.argv[1:]]
 
 headers = [[f.readline () for i in range (2)] for f in files]
 

src/gen-use-table.py

@@ -2,7 +2,7 @@
 
 from __future__ import print_function, division, absolute_import
 
-import sys
+import io, sys
 
 if len (sys.argv) != 5:
 	print ("usage: ./gen-use-table.py IndicSyllabicCategory.txt IndicPositionalCategory.txt UnicodeData.txt Blocks.txt", file=sys.stderr)
@@ -10,7 +10,7 @@ if len (sys.argv) != 5:
 
 BLACKLISTED_BLOCKS = ["Thai", "Lao", "Tibetan"]
 
-files = [open (x) for x in sys.argv[1:]]
+files = [io.open (x, encoding='utf-8') for x in sys.argv[1:]]
 
 headers = [[f.readline () for i in range (2)] for j,f in enumerate(files) if j != 2]
 headers.append (["UnicodeData.txt does not have a header."])