Add Rust output to emoji generator

This commit is contained in:
Behdad Esfahbod committed 2026-03-03 05:38:25 -03:00
1 parent 80c5b48db0
commit 93175405e9
1 file changed
+52 -16
+52 -16
View File
@@ -1,16 +1,23 @@
#!/usr/bin/env python3
"""usage: ./gen-emoji-table.py emoji-data.txt emoji-test.txt
"""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__)
@@ -43,7 +50,8 @@ print ("/* == Start of generated table == */")
print ("/*")
print (" * The following tables are generated by running:")
print (" *")
print (" * ./gen-emoji-table.py emoji-data.txt")
print (" * ./gen-emoji-table.py %semoji-data.txt" %
("--rust " if language.name == "rust" else ""))
print (" *")
print (" * on file with this header:")
print (" *")
@@ -51,11 +59,20 @@ for l in header:
print (" * %s" % (l.strip()))
print (" */")
print ()
print ("#ifndef HB_UNICODE_EMOJI_TABLE_HH")
print ("#define HB_UNICODE_EMOJI_TABLE_HH")
print ()
print ('#include "hb-unicode.hh"')
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
@@ -67,12 +84,26 @@ for typ, s in ranges.items():
sol = packTab.pack_table(arr, 0, compression=9)
code = packTab.Code('_hb_emoji')
sol.genCode(code, 'is_'+typ)
code.print_c()
print()
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 ()
print ("#endif /* HB_UNICODE_EMOJI_TABLE_HH */")
if language.name == "c":
print ("#endif /* HB_UNICODE_EMOJI_TABLE_HH */")
print ()
print ("/* == End of generated table == */")
@@ -91,8 +122,13 @@ with open(sys.argv[2]) as f:
continue
sequences.append(line)
with open("../test/shape/data/in-house/tests/emoji-clusters.tests", "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")
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