Merge pull request #101 from dougfelt/emoji_html_title

Emoji html title

add_aliases.py

@@ -35,7 +35,7 @@ def seq_to_str(seq):
   return '_'.join('%04x' % cp for cp in seq)
 
 
-def read_emoji_aliases():
+def read_default_emoji_aliases():
   alias_path = path.join(DATA_ROOT, 'emoji_aliases.txt')
   return read_emoji_aliases(alias_path)
 

generate_emoji_html.py

@@ -23,6 +23,7 @@ builds an html page presenting the images along with their composition
 import argparse
 import codecs
 import collections
+import datetime
 import glob
 import os
 from os import path
@@ -33,6 +34,8 @@ import sys
 from nototools import tool_utils
 from nototools import unicode_data
 
+import add_aliases
+
 _default_dir = 'png/128'
 _default_ext = 'png'
 _default_prefix = 'emoji_u'
@@ -54,12 +57,14 @@ def _merge_keys(dicts):
   return frozenset(keys)
 
 
-def _generate_row_cells(key, font, dir_infos, basepaths, colors):
+def _generate_row_cells(key, font, aliases, dir_infos, basepaths, colors):
   CELL_PREFIX = '<td>'
   indices = range(len(basepaths))
   def _cell(info, basepath):
     if key in info.filemap:
       return '<img src="%s">' % path.join(basepath, info.filemap[key])
+    if key in aliases:
+      return '-alias-'
     return '-missing-'
 
   def _text_cell(text_dir):
@@ -82,17 +87,31 @@ def _generate_row_cells(key, font, dir_infos, basepaths, colors):
   return row_cells
 
 
-def _get_desc(key_tuple, dir_infos, basepaths):
+def _get_desc(key_tuple, aliases, dir_infos, basepaths):
   CELL_PREFIX = '<td>'
   def _get_filepath(cp):
-    cp_key = tuple([cp])
+    def get_key_filepath(key):
       for i in range(len(dir_infos)):
         info = dir_infos[i]
-      if cp_key in info.filemap:
+        if key in info.filemap:
           basepath = basepaths[i]
-        return path.join(basepath, info.filemap[cp_key])
+          return path.join(basepath, info.filemap[key])
       return None
 
+    cp_key = tuple([cp])
+    cp_key = unicode_data.get_canonical_emoji_sequence(cp_key) or cp_key
+    fp = get_key_filepath(cp_key)
+    if not fp:
+      if cp_key in aliases:
+        fp = get_key_filepath(aliases[cp_key])
+      else:
+        print 'no alias for %s' % unicode_data.seq_to_string(cp_key)
+    if not fp:
+      print 'no part for %s in %s' % (
+          unicode_data.seq_to_string(cp_key),
+          unicode_data.seq_to_string(key_tuple))
+    return fp
+
   def _get_part(cp):
     if cp == 0x200d:  # zwj, common so replace with '+'
       return '+'
@@ -164,7 +183,7 @@ def _collect_aux_info(dir_infos, keys):
 
 
 def _generate_content(
-    basedir, font, dir_infos, keys, annotations, standalone, colors):
+    basedir, font, dir_infos, keys, aliases, annotations, standalone, colors):
   """Generate an html table for the infos.  Basedir is the parent directory of
   the content, filenames will be made relative to this if underneath it, else
   absolute. If font is not none, generate columns for the text rendered in the
@@ -230,8 +249,8 @@ def _generate_content(
   lines.append('<th>'.join(header_row))
 
   for key in keys:
-    row = _generate_row_cells(key, font, dir_infos, basepaths, colors)
+    row = _generate_row_cells(key, font, aliases, dir_infos, basepaths, colors)
-    row.append(_get_desc(key, dir_infos, basepaths))
+    row.append(_get_desc(key, aliases, dir_infos, basepaths))
     row.append(_get_name(key, annotations))
     lines.append(''.join(row))
 
@@ -323,18 +342,46 @@ def _get_dir_infos(
   return infos
 
 
-def _get_keys(dir_infos, limit, all_emoji, emoji_sort):
+def _add_aliases(keys, aliases):
+  for k, v in sorted(aliases.iteritems()):
+    k_str = unicode_data.seq_to_string(k)
+    v_str = unicode_data.seq_to_string(v)
+    if k in keys:
+      msg = '' if v in keys else ' but it\'s not present'
+      print 'have alias image %s, should use %s%s' % (k_str, v_str, msg)
+    elif v not in keys:
+      print 'can\'t use alias %s, no image matching %s' % (k_str, v_str)
+  to_add = {k for k, v in aliases.iteritems() if k not in keys and v in keys}
+  return keys | to_add
+
+
+def _get_keys(dir_infos, aliases, limit, all_emoji, emoji_sort, ignore_missing):
   """Return a list of the key tuples to display.  If all_emoji is
-  True, returns all emoji sequences, else the sequences available
+  true, start with all emoji sequences, else the sequences available
   in dir_infos (limited to the first dir_info if limit is True).
+  If ignore_missing is true and all_emoji is false, ignore sequences
+  that are not valid (e.g. skin tone variants of wrestlers).  If
+  ignore_missing is true and all_emoji is true, ignore sequences
+  for which we have no assets (e.g. newly defined emoji).  If not using
+  all_emoji, aliases are included if we have a target for them.
   The result is in emoji order if emoji_sort is true, else in
   unicode codepoint order."""
-  if all_emoji:
+
-    keys = unicode_data.get_emoji_sequences()
+  if all_emoji or ignore_missing:
-  elif len(dir_infos) == 1 or limit:
+    all_keys = unicode_data.get_emoji_sequences()
-    keys = frozenset(dir_infos[0].filemap.keys())
+  if not all_emoji or ignore_missing:
+    if len(dir_infos) == 1 or limit:
+      avail_keys = frozenset(dir_infos[0].filemap.keys())
     else:
-    keys = _merge_keys([info.filemap for info in dir_infos])
+      avail_keys = _merge_keys([info.filemap for info in dir_infos])
+    if aliases:
+      avail_keys = _add_aliases(avail_keys, aliases)
+
+  if not ignore_missing:
+    keys = all_keys if all_emoji else avail_keys
+  else:
+    keys = set(all_keys) & avail_keys
+
   if emoji_sort:
     sorted_keys = unicode_data.get_sorted_emoji_sequences(keys)
   else:
@@ -342,6 +389,13 @@ def _get_keys(dir_infos, limit, all_emoji, emoji_sort):
   return sorted_keys
 
 
+def _generate_info_text(args):
+  lines = ['%s: %r' % t for t in sorted(args.__dict__.iteritems())]
+  lines.append('generated by %s on %s' % (
+      path.basename(__file__), datetime.datetime.now()))
+  return '\n  '.join(lines)
+
+
 def _parse_annotation_file(afile):
   """Parse file and return a map from sequences to one of 'ok', 'warning',
   or 'error'.
@@ -409,6 +463,10 @@ TEMPLATE = """<!DOCTYPE html>
     <style>{{style}}</style>
   </head>
   <body>
+  <!--
+  {{info}}
+  -->
+  <h3>{{title}}</h3>
   {{content}}
   </body>
 </html>
@@ -431,8 +489,8 @@ STYLE = """
 """
 
 def write_html_page(
-    filename, page_title, font, dir_infos, keys, annotations, standalone,
+    filename, page_title, font, dir_infos, keys, aliases, annotations,
-    colors):
+    standalone, colors, info):
 
   out_dir = path.dirname(filename)
   if font:
@@ -457,13 +515,13 @@ def write_html_page(
         font = path.normpath(path.join(common_prefix, rel_font))
 
   content = _generate_content(
-      path.dirname(filename), font, dir_infos, keys, annotations, standalone,
+      path.dirname(filename), font, dir_infos, keys, aliases, annotations,
-      colors)
+      standalone, colors)
   N_STYLE = STYLE
   if font:
     FONT_FACE_STYLE = """
     <style>@font-face {
-      font-family: "Emoji"; src: url("%s");
+      font-family: "Emoji"; src: local("Noto Color Emoji"), url("%s");
     }</style>""" % font
     N_STYLE += '      span.efont { font-family: "Emoji"; font-size:32pt }\n'
   else:
@@ -478,11 +536,18 @@ def write_html_page(
   text = _instantiate_template(
       TEMPLATE, {
           'title': page_title, 'fontFaceStyle': FONT_FACE_STYLE,
-          'style': N_STYLE, 'content': content})
+          'style': N_STYLE, 'content': content, 'info':info})
   with codecs.open(filename, 'w', 'utf-8') as f:
     f.write(text)
 
 
+def _get_canonical_aliases():
+  def canon(seq):
+    return unicode_data.get_canonical_emoji_sequence(seq) or seq
+  aliases = add_aliases.read_default_emoji_aliases()
+  return {canon(k): canon(v) for k, v in aliases.iteritems()}
+
+
 def main():
   parser = argparse.ArgumentParser()
   parser.add_argument(
@@ -526,6 +591,9 @@ def main():
       '--all_emoji', help='use all emoji sequences', action='store_true')
   parser.add_argument(
       '--emoji_sort', help='use emoji sort order', action='store_true')
+  parser.add_argument(
+      '--ignore_missing', help='do not include missing emoji',
+      action='store_true')
 
   args = parser.parse_args()
   file_parts = path.splitext(args.outfile)
@@ -548,12 +616,16 @@ def main():
       args.image_dirs, args.exts, args.prefixes, args.titles,
       args.default_ext, args.default_prefix)
 
+  aliases = _get_canonical_aliases()
   keys = _get_keys(
-      dir_infos, args.limit, args.all_emoji, args.emoji_sort)
+      dir_infos, aliases, args.limit, args.all_emoji, args.emoji_sort,
+      args.ignore_missing)
+
+  info = _generate_info_text(args)
 
   write_html_page(
-      args.outfile, args.page_title, args.font, dir_infos, keys,
+      args.outfile, args.page_title, args.font, dir_infos, keys, aliases,
-      annotations, args.standalone, args.colors)
+      annotations, args.standalone, args.colors, info)
 
 
 if __name__ == "__main__":