src/gen-emoji-table.py

#!/usr/bin/env python3

"""usage: ./gen-emoji-table.py [--rust] emoji-data.txt emoji-test.txt

Input file:
* https://www.unicode.org/Public/UCD/latest/ucd/emoji/emoji-data.txt
* https://www.unicode.org/Public/emoji/latest/emoji-test.txt
"""

import os
import sys
from collections import OrderedDict
import packTab

if len(sys.argv) > 1 and sys.argv[1] == "--rust":
	del sys.argv[1]
	language = packTab.languages["rust"]
else:
	language = packTab.languages["c"]

if len (sys.argv) != 3:
	sys.exit (__doc__)

f = open(sys.argv[1])
header = [f.readline () for _ in range(10)]

ranges = OrderedDict()
for line in f.readlines():
	line = line.strip()
	if not line or line[0] == '#':
		continue
	rang, typ = [s.strip() for s in line.split('#')[0].split(';')[:2]]

	rang = [int(s, 16) for s in rang.split('..')]
	if len(rang) > 1:
		start, end = rang
	else:
		start = end = rang[0]

	if typ not in ranges:
		ranges[typ] = []
	if ranges[typ] and ranges[typ][-1][1] == start - 1:
		ranges[typ][-1] = (ranges[typ][-1][0], end)
	else:
		ranges[typ].append((start, end))



print ("/* == Start of generated table == */")
print ("/*")
print (" * The following tables are generated by running:")
print (" *")
print (" *   ./gen-emoji-table.py %semoji-data.txt" %
		("--rust " if language.name == "rust" else ""))
print (" *")
print (" * on file with this header:")
print (" *")
for l in header:
	print (" * %s" % (l.strip()))
print (" */")
print ()
if language.name == "c":
	print ("#ifndef HB_UNICODE_EMOJI_TABLE_HH")
	print ("#define HB_UNICODE_EMOJI_TABLE_HH")
	print ()
	print ('#include "hb-unicode.hh"')
	print ()
elif language.name == "rust":
	print ("#![allow(unused_parens)]")
	print ("#![allow(clippy::unnecessary_cast, clippy::unreadable_literal, clippy::double_parens)]")
	print ()
	print ("use crate::hb::unicode::Codepoint;")
	print ()
else:
	assert False, "Unknown language: %s" % language.name

for typ, s in ranges.items():
	if typ != "Extended_Pictographic": continue

	arr = dict()
	for start,end in s:
		for i in range(start, end + 1):
			arr[i] = 1

	sol = packTab.pack_table(arr, 0, compression=9)
	code = packTab.Code('_hb_emoji')
	if language.name == "c":
		sol.genCode(code, 'is_'+typ, language=language)
		code.print_code(language=language)
		print()
	elif language.name == "rust":
		sol.genCode(code, 'is_'+typ+'_u8', language=language, private=False)
		code.print_code(language=language, private=False)
		print()
		print ("#[inline]")
		print ("pub(crate) fn is_%s (u: Codepoint) -> bool" % typ)
		print ("{")
		print ("  _hb_emoji_is_%s_u8 (u as usize) != 0" % typ)
		print ("}")
		print()
	else:
		assert False, "Unknown language: %s" % language.name

print ()
if language.name == "c":
	print ("#endif /* HB_UNICODE_EMOJI_TABLE_HH */")
print ()
print ("/* == End of generated table == */")


# Generate test file.
sequences = []
with open(sys.argv[2]) as f:
    for line in f.readlines():
        if "#" in line:
            line = line[:line.index("#")]
        if ";" in line:
            line = line[:line.index(";")]
        line = line.strip()
        line = line.split(" ")
        if len(line) < 2:
            continue
        sequences.append(line)

test_path = os.path.join(os.path.dirname(__file__), "..", "test", "shape", "data", "in-house", "tests", "emoji-clusters.tests")
if os.path.isdir(os.path.dirname(test_path)):
    try:
        with open(test_path, "w") as f:
            for sequence in sequences:
                f.write("../fonts/AdobeBlank2.ttf;--no-glyph-names --no-positions --font-funcs=ot")
                f.write(";" + ",".join(sequence))
                f.write(";[" + "|".join("1=0" for c in sequence) + "]\n")
    except OSError:
        pass