Modernize Python 2 code to get ready for Python 3

add_aliases.py

@@ -14,6 +14,7 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
+from __future__ import print_function
 import argparse
 import glob
 import os
@@ -31,7 +32,7 @@
 def str_to_seq(seq_str):
   res = [int(s, 16) for s in seq_str.split('_')]
   if 0xfe0f in res:
-    print '0xfe0f in file name: %s' % seq_str
+    print('0xfe0f in file name: %s' % seq_str)
     res = [x for x in res if x != 0xfe0f]
   return tuple(res)
 
@@ -66,7 +67,7 @@ def read_emoji_aliases(filename):
         als_seq = tuple([int(x, 16) for x in als.split('_')])
         trg_seq = tuple([int(x, 16) for x in trg.split('_')])
       except:
-        print 'cannot process alias %s -> %s' % (als, trg)
+        print('cannot process alias %s -> %s' % (als, trg))
         continue
       result[als_seq] = trg_seq
   return result
@@ -82,7 +83,7 @@ def add_aliases(
   be done.  Dstdir will be created if necessary, even if dry_run is true."""
 
   if not path.isdir(srcdir):
-    print >> sys.stderr, '%s is not a directory' % srcdir
+    print('%s is not a directory' % srcdir, file=sys.stderr)
     return
 
   if not dstdir:
@@ -104,16 +105,16 @@ def add_aliases(
   alias_exists = False
   for als, trg in sorted(aliases.items()):
     if trg not in seq_to_file:
-      print >> sys.stderr, 'target %s for %s does not exist' % (
-          seq_to_str(trg), seq_to_str(als))
+      print('target %s for %s does not exist' % (
+          seq_to_str(trg), seq_to_str(als)), file=sys.stderr)
       continue
     alias_name = '%s%s.%s' % (prefix, seq_to_str(als), ext)
     alias_path = path.join(dstdir, alias_name)
     if path.exists(alias_path):
       if replace:
         aliases_to_replace.append(alias_name)
       else:
-        print >> sys.stderr, 'alias %s exists' % seq_to_str(als)
+        print('alias %s exists' % seq_to_str(als), file=sys.stderr)
         alias_exists = True
         continue
     target_file = seq_to_file[trg]
@@ -123,15 +124,15 @@ def add_aliases(
     if not dry_run:
       for k in sorted(aliases_to_replace):
         os.remove(path.join(dstdir, k))
-    print 'replacing %d files' % len(aliases_to_replace)
+    print('replacing %d files' % len(aliases_to_replace))
   elif alias_exists:
-    print >> sys.stderr, 'aborting, aliases exist.'
+    print('aborting, aliases exist.', file=sys.stderr)
     return
 
   for k, v in sorted(aliases_to_create.items()):
     if dry_run:
       msg = 'replace ' if k in aliases_to_replace else ''
-      print '%s%s -> %s' % (msg, k, v)
+      print('%s%s -> %s' % (msg, k, v))
     else:
       try:
         if copy:
@@ -143,10 +144,10 @@ def add_aliases(
           else:
             raise Exception('can\'t create cross-directory symlinks yet')
       except Exception as e:
-        print >> sys.stderr, 'failed to create %s -> %s' % (k, v)
+        print('failed to create %s -> %s' % (k, v), file=sys.stderr)
         raise Exception('oops, ' + str(e))
-  print 'created %d %s' % (
-      len(aliases_to_create), 'copies' if copy else 'symlinks')
+  print('created %d %s' % (
+      len(aliases_to_create), 'copies' if copy else 'symlinks'))
 
 
 def main():

add_svg_glyphs.py

@@ -16,6 +16,7 @@
 # Google Author(s): Doug Felt
 
 """Tool to update GSUB, hmtx, cmap, glyf tables with svg image glyphs."""
+from __future__ import print_function
 
 import argparse
 import glob

check_emoji_sequences.py

@@ -15,6 +15,7 @@
 # limitations under the License.
 
 """Compare emoji image file namings against unicode property data."""
+from __future__ import print_function
 
 import argparse
 import collections
@@ -95,9 +96,9 @@ def _check_valid_emoji(sorted_seq_to_filepath):
         not_emoji[cp].append(fp)
 
   if len(not_emoji):
-    print >> sys.stderr, '%d non-emoji found:' % len(not_emoji)
+    print('%d non-emoji found:' % len(not_emoji), file=sys.stderr)
     for cp in sorted(not_emoji):
-      print >> sys.stderr, '%04x (in %s)' % (cp, ', '.join(not_emoji[cp]))
+      print('%04x (in %s)' % (cp, ', '.join(not_emoji[cp])), file=sys.stderr)
 
 
 def _check_zwj(sorted_seq_to_filepath):
@@ -109,21 +110,21 @@ def _check_zwj(sorted_seq_to_filepath):
     if ZWJ not in seq:
       continue
     if seq[0] == 0x200d:
-      print >> sys.stderr, 'zwj at head of sequence in %s' % fp
+      print('zwj at head of sequence in %s' % fp, file=sys.stderr)
     if len(seq) == 1:
       continue
     if seq[-1] == 0x200d:
-      print >> sys.stderr, 'zwj at end of sequence in %s' % fp
+      print('zwj at end of sequence in %s' % fp, file=sys.stderr)
     for i, cp in enumerate(seq):
       if cp == ZWJ:
         if i > 0:
           pcp = seq[i-1]
           if pcp != EMOJI_PRESENTATION_VS and not unicode_data.is_emoji(pcp):
-            print >> sys.stderr, 'non-emoji %04x preceeds ZWJ in %s' % (pcp, fp)
+            print('non-emoji %04x preceeds ZWJ in %s' % (pcp, fp), file=sys.stderr)
         if i < len(seq) - 1:
           fcp = seq[i+1]
           if not unicode_data.is_emoji(fcp):
-            print >> sys.stderr, 'non-emoji %04x follows ZWJ in %s' % (fcp, fp)
+            print('non-emoji %04x follows ZWJ in %s' % (fcp, fp), file=sys.stderr)
 
 
 def _check_flags(sorted_seq_to_filepath):
@@ -136,11 +137,11 @@ def _check_flags(sorted_seq_to_filepath):
       if have_reg == None:
         have_reg = is_reg
       elif have_reg != is_reg:
-        print >> sys.stderr, 'mix of regional and non-regional in %s' % fp
+        print('mix of regional and non-regional in %s' % fp, file=sys.stderr)
     if have_reg and len(seq) > 2:
       # We provide dummy glyphs for regional indicators, so there are sequences
       # with single regional indicator symbols.
-      print >> sys.stderr, 'regional indicator sequence length != 2 in %s' % fp
+      print('regional indicator sequence length != 2 in %s' % fp, file=sys.stderr)
 
 
 def _check_skintone(sorted_seq_to_filepath):
@@ -153,23 +154,23 @@ def _check_skintone(sorted_seq_to_filepath):
       if _is_skintone_modifier(cp):
         if i == 0:
           if len(seq) > 1:
-            print >> sys.stderr, 'skin color selector first in sequence %s' % fp
+            print('skin color selector first in sequence %s' % fp, file=sys.stderr)
           # standalone are ok
           continue
         pcp = seq[i-1]
         if not unicode_data.is_emoji_modifier_base(pcp):
-          print >> sys.stderr, (
-              'emoji skintone modifier applied to non-base at %d: %s' % (i, fp))
+          print((
+              'emoji skintone modifier applied to non-base at %d: %s' % (i, fp)), file=sys.stderr)
       elif unicode_data.is_emoji_modifier_base(cp):
         if i < len(seq) - 1 and _is_skintone_modifier(seq[i+1]):
           base_to_modifiers[cp].add(seq[i+1])
         elif cp not in base_to_modifiers:
           base_to_modifiers[cp] = set()
   for cp, modifiers in sorted(base_to_modifiers.iteritems()):
     if len(modifiers) != 5:
-      print >> sys.stderr, 'emoji base %04x has %d modifiers defined (%s) in %s' % (
+      print('emoji base %04x has %d modifiers defined (%s) in %s' % (
           cp, len(modifiers),
-          ', '.join('%04x' % cp for cp in sorted(modifiers)), fp)
+          ', '.join('%04x' % cp for cp in sorted(modifiers)), fp), file=sys.stderr)
 
 
 def _check_zwj_sequences(seq_to_filepath):
@@ -189,7 +190,7 @@ def _check_zwj_sequences(seq_to_filepath):
   for seq, fp in zwj_seq_to_filepath.iteritems():
     if seq not in zwj_sequence_to_name:
       if seq not in zwj_sequence_without_vs_to_name_canonical:
-        print >> sys.stderr, 'zwj sequence not defined: %s' % fp
+        print('zwj sequence not defined: %s' % fp, file=sys.stderr)
       else:
         _, can = zwj_sequence_without_vs_to_name_canonical[seq]
         # print >> sys.stderr, 'canonical sequence %s contains vs: %s' % (
@@ -211,7 +212,7 @@ def read_emoji_aliases():
       try:
         trg_seq = tuple([int(x, 16) for x in trg.split('_')])
       except:
-        print 'cannot process alias %s -> %s' % (als, trg)
+        print('cannot process alias %s -> %s' % (als, trg))
         continue
       result[als_seq] = trg_seq
   return result
@@ -229,11 +230,11 @@ def _check_coverage(seq_to_filepath):
   aliases = read_emoji_aliases()
   for k, v in sorted(aliases.items()):
     if v not in seq_to_filepath and v not in non_vs_to_canonical:
-      print 'alias %s missing target %s' % (_seq_string(k), _seq_string(v))
+      print('alias %s missing target %s' % (_seq_string(k), _seq_string(v)))
       continue
     if k in seq_to_filepath or k in non_vs_to_canonical:
-      print 'alias %s already exists as %s (%s)' % (
-          _seq_string(k), _seq_string(v), seq_name(v))
+      print('alias %s already exists as %s (%s)' % (
+          _seq_string(k), _seq_string(v), seq_name(v)))
       continue
     filename = seq_to_filepath.get(v) or seq_to_filepath[non_vs_to_canonical[v]]
     seq_to_filepath[k] = 'alias:' + filename
@@ -242,13 +243,13 @@ def _check_coverage(seq_to_filepath):
   emoji = sorted(unicode_data.get_emoji(age=age))
   for cp in emoji:
     if tuple([cp]) not in seq_to_filepath:
-      print 'missing single %04x (%s)' % (cp, unicode_data.name(cp, '<no name>'))
+      print('missing single %04x (%s)' % (cp, unicode_data.name(cp, '<no name>')))
 
   # special characters
   # all but combining enclosing keycap are currently marked as emoji
   for cp in [ord('*'), ord('#'), ord(u'\u20e3')] + range(0x30, 0x3a):
     if cp not in emoji and tuple([cp]) not in seq_to_filepath:
-      print 'missing special %04x (%s)' % (cp, unicode_data.name(cp))
+      print('missing special %04x (%s)' % (cp, unicode_data.name(cp)))
 
   # combining sequences
   comb_seq_to_name = sorted(
@@ -258,22 +259,22 @@ def _check_coverage(seq_to_filepath):
       # strip vs and try again
       non_vs_seq = strip_vs(seq)
       if non_vs_seq not in seq_to_filepath:
-        print 'missing combining sequence %s (%s)' % (_seq_string(seq), name)
+        print('missing combining sequence %s (%s)' % (_seq_string(seq), name))
 
   # flag sequences
   flag_seq_to_name = sorted(
       unicode_data.get_emoji_flag_sequences(age=age).iteritems())
   for seq, name in flag_seq_to_name:
     if seq not in seq_to_filepath:
-      print 'missing flag sequence %s (%s)' % (_seq_string(seq), name)
+      print('missing flag sequence %s (%s)' % (_seq_string(seq), name))
 
   # skin tone modifier sequences
   mod_seq_to_name = sorted(
       unicode_data.get_emoji_modifier_sequences(age=age).iteritems())
   for seq, name in mod_seq_to_name:
     if seq not in seq_to_filepath:
-      print 'missing modifier sequence %s (%s)' % (
-          _seq_string(seq), name)
+      print('missing modifier sequence %s (%s)' % (
+          _seq_string(seq), name))
 
   # zwj sequences
   # some of ours include the emoji presentation variation selector and some
@@ -294,14 +295,14 @@ def _check_coverage(seq_to_filepath):
     else:
       test_seq = seq
     if test_seq not in zwj_seq_without_vs:
-      print 'missing (canonical) zwj sequence %s (%s)' % (
-          _seq_string(seq), name)
+      print('missing (canonical) zwj sequence %s (%s)' % (
+          _seq_string(seq), name))
 
   # check for 'unknown flag'
   # this is either emoji_ufe82b or 'unknown_flag', we filter out things that
   # don't start with our prefix so 'unknown_flag' would be excluded by default.
   if tuple([0xfe82b]) not in seq_to_filepath:
-    print 'missing unknown flag PUA fe82b'
+    print('missing unknown flag PUA fe82b')
 
 
 def check_sequence_to_filepath(seq_to_filepath):
@@ -322,20 +323,20 @@ def create_sequence_to_filepath(name_to_dirpath, prefix, suffix):
   result = {}
   for name, dirname in name_to_dirpath.iteritems():
     if not name.startswith(prefix):
-      print 'expected prefix "%s" for "%s"' % (prefix, name)
+      print('expected prefix "%s" for "%s"' % (prefix, name))
       continue
 
     segments = name[len(prefix): -len(suffix)].split('_')
     segfail = False
     seq = []
     for s in segments:
       if not segment_re.match(s):
-        print 'bad codepoint name "%s" in %s/%s' % (s, dirname, name)
+        print('bad codepoint name "%s" in %s/%s' % (s, dirname, name))
         segfail = True
         continue
       n = int(s, 16)
       if n > 0x10ffff:
-        print 'codepoint "%s" out of range in %s/%s' % (s, dirname, name)
+        print('codepoint "%s" out of range in %s/%s' % (s, dirname, name))
         segfail = True
         continue
       seq.append(n)
@@ -356,8 +357,8 @@ def collect_name_to_dirpath(directory, prefix, suffix):
       if not f.endswith(suffix):
         continue
       if f in result:
-        print >> sys.stderr, 'duplicate file "%s" in %s and %s ' % (
-            f, dirname, result[f])
+        print('duplicate file "%s" in %s and %s ' % (
+            f, dirname, result[f]), file=sys.stderr)
         continue
       result[f] = dirname
   return result
@@ -375,15 +376,15 @@ def collect_name_to_dirpath_with_override(dirs, prefix, suffix):
 
 
 def run_check(dirs, prefix, suffix):
-  print 'Checking files with prefix "%s" and suffix "%s" in:\n  %s' % (
-      prefix, suffix, '\n  '.join(dirs))
+  print('Checking files with prefix "%s" and suffix "%s" in:\n  %s' % (
+      prefix, suffix, '\n  '.join(dirs)))
   name_to_dirpath = collect_name_to_dirpath_with_override(
       dirs, prefix=prefix, suffix=suffix)
-  print 'checking %d names' % len(name_to_dirpath)
+  print('checking %d names' % len(name_to_dirpath))
   seq_to_filepath = create_sequence_to_filepath(name_to_dirpath, prefix, suffix)
-  print 'checking %d sequences' % len(seq_to_filepath)
+  print('checking %d sequences' % len(seq_to_filepath))
   check_sequence_to_filepath(seq_to_filepath)
-  print 'done.'
+  print('done.')
 
 
 def main():

flag_glyph_name.py

@@ -15,6 +15,7 @@
 # limitations under the License.
 
 """Generate a glyph name for flag emojis."""
+from __future__ import print_function
 
 __author__ = '[email protected] (Roozbeh Pournader)'
 
@@ -48,8 +49,8 @@ def flag_code_to_glyph_name(flag_code):
 
 
 def main():
-    print ' '.join([
-        flag_code_to_glyph_name(flag_code) for flag_code in sys.argv[1:]])
+    print(' '.join([
+        flag_code_to_glyph_name(flag_code) for flag_code in sys.argv[1:]]))
 
 if __name__ == '__main__':
     main()

flag_info.py

@@ -17,6 +17,7 @@
 """Quick tool to display count/ids of flag images in a directory named
 either using ASCII upper case pairs or the emoji_u+codepoint_sequence
 names."""
+from __future__ import print_function
 
 import argparse
 import re
@@ -44,22 +45,22 @@ def _flag_names_from_file_names(src):
   for f in glob.glob(path.join(src, '*.png')):
     m = flag_re.match(path.basename(f))
     if not m:
-      print 'no match'
+      print('no match')
       continue
     flags.add(m.group(1))
   return flags
 
 
 def _dump_flag_info(names):
   prev = None
-  print '%d flags' % len(names)
+  print('%d flags' % len(names))
   for n in sorted(names):
     if n[0] != prev:
       if prev:
-        print
+        print()
       prev = n[0]
-    print n,
-  print
+    print(n, end=' ')
+  print()
 
 
 def main():
@@ -76,7 +77,7 @@ def main():
     names = _flag_names_from_file_names(args.srcdir)
   else:
     names = _flag_names_from_emoji_file_names(args.srcdir)
-  print args.srcdir
+  print(args.srcdir)
   _dump_flag_info(names)