Update emoji html page generation.

- Support --ignore_missing flag to skip missing data on output.
  When all_images is set, this skips sequences for which we have
  no image files.  When all_images is not set, this skips sequences
  for which we have image files but are not in the canonical
  sequence list (e.g. older sequences for which we included skin
  tone variants but which later versions of unicode decided there
  shouldn't be).
- Use alias information to add alias sequences when not using
  all_images and we have an image for the target sequence.
- Use alias information to mark missing images with '-alias-' when
  we expect an alias (note, not only when we actually have one)
- Embed tool name, date, and arguments in a comment in the generated
  html.
pull/101/head
Doug Felt 2017-03-07 14:28:21 -08:00
parent b9cbe2324c
commit 0d0db39af0
2 changed files with 63 additions and 20 deletions

View File

@ -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)

View File

@ -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):
@ -164,7 +169,7 @@ 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
@ -230,7 +235,7 @@ 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_name(key, annotations))
lines.append(''.join(row))
@ -323,18 +328,38 @@ def _get_dir_infos(
return infos
def _get_keys(dir_infos, limit, all_emoji, emoji_sort):
def _add_aliases(keys, aliases):
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()
elif len(dir_infos) == 1 or limit:
keys = frozenset(dir_infos[0].filemap.keys())
if all_emoji or ignore_missing:
all_keys = unicode_data.get_emoji_sequences()
if not all_emoji or ignore_missing:
if len(dir_infos) == 1 or limit:
avail_keys = frozenset(dir_infos[0].filemap.keys())
else:
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 = _merge_keys([info.filemap for info in dir_infos])
keys = set(all_keys) & avail_keys
if emoji_sort:
sorted_keys = unicode_data.get_sorted_emoji_sequences(keys)
else:
@ -342,6 +367,13 @@ 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 +441,10 @@ TEMPLATE = """<!DOCTYPE html>
<style>{{style}}</style>
</head>
<body>
<!--
{{info}}
-->
<h3>{{title}}</h3>
{{content}}
</body>
</html>
@ -431,8 +467,8 @@ STYLE = """
"""
def write_html_page(
filename, page_title, font, dir_infos, keys, annotations, standalone,
colors):
filename, page_title, font, dir_infos, keys, aliases, annotations,
standalone, colors, info):
out_dir = path.dirname(filename)
if font:
@ -457,13 +493,13 @@ 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,
colors)
path.dirname(filename), font, dir_infos, keys, aliases, annotations,
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:
@ -478,7 +514,7 @@ 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)
@ -526,6 +562,9 @@ 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 +587,16 @@ def main():
args.image_dirs, args.exts, args.prefixes, args.titles,
args.default_ext, args.default_prefix)
aliases = add_aliases.read_default_emoji_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,
annotations, args.standalone, args.colors)
args.outfile, args.page_title, args.font, dir_infos, keys, aliases,
annotations, args.standalone, args.colors, info)
if __name__ == "__main__":