Skip to content

Support Unicode 17 #75

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
wants to merge 1 commit into
base: master
Choose a base branch
from
Draft

Support Unicode 17 #75

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
48 changes: 26 additions & 22 deletions scripts/unicode.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -43,7 +43,7 @@
from itertools import batched
from typing import Callable, Iterable

UNICODE_VERSION = "16.0.0"
UNICODE_VERSION = "17.0.0"
"""The version of the Unicode data files to download."""

NUM_CODEPOINTS = 0x110000
Expand Down Expand Up @@ -178,7 +178,9 @@ class WidthState(enum.IntEnum):
(if set, should also set 3rd and 4th)
- 6th bit: if 4th is set but this one is not, then this is a ZWJ ligature state
where no ZWJ has been encountered yet; encountering one flips this on
- Seventh bit: is VS1 (if CJK) or is VS2 (not CJK)
- Seventh bit:
- CJK mode: is VS1 or VS3
- Not CJK: is VS2
"""

# BASIC WIDTHS
Expand Down Expand Up @@ -275,8 +277,8 @@ class WidthState(enum.IntEnum):

# VARIATION SELECTORS

VARIATION_SELECTOR_1_OR_2 = 0b0000_0010_0000_0000
"\\uFE00 if CJK, or \\uFE01 otherwise"
VARIATION_SELECTOR_1_2_OR_3 = 0b0000_0010_0000_0000
"\\uFE00 or \\uFE02 if CJK, or \\uFE01 otherwise"

# Text presentation sequences (not CJK)
VARIATION_SELECTOR_15 = 0b0100_0000_0000_0000
Expand Down Expand Up @@ -373,7 +375,7 @@ def width_alone(self) -> int:
| WidthState.COMBINING_LONG_SOLIDUS_OVERLAY
| WidthState.VARIATION_SELECTOR_15
| WidthState.VARIATION_SELECTOR_16
| WidthState.VARIATION_SELECTOR_1_OR_2
| WidthState.VARIATION_SELECTOR_1_2_OR_3
):
return 0
case (
Expand Down Expand Up @@ -657,11 +659,12 @@ def load_width_maps() -> tuple[list[WidthState], list[WidthState]]:
ea[cp] = width

# East-Asian only
ea[0xFE00] = WidthState.VARIATION_SELECTOR_1_OR_2
ea[0x0338] = WidthState.COMBINING_LONG_SOLIDUS_OVERLAY
ea[0xFE00] = WidthState.VARIATION_SELECTOR_1_2_OR_3
ea[0xFE02] = WidthState.VARIATION_SELECTOR_1_2_OR_3

# Not East Asian only
not_ea[0xFE01] = WidthState.VARIATION_SELECTOR_1_OR_2
not_ea[0xFE01] = WidthState.VARIATION_SELECTOR_1_2_OR_3
not_ea[0xFE0E] = WidthState.VARIATION_SELECTOR_15

return (not_ea, ea)
Expand Down Expand Up @@ -759,7 +762,7 @@ def load_solidus_transparent(
num_chars = len(ccc_above_1)

for cp in ccc_above_1:
if cp not in [0xFE00, 0xFE0F]:
if cp not in [0xFE00, 0xFE02, 0xFE0F]:
assert (
cjk_width_map[cp].table_width() != CharWidthInTable.SPECIAL
), f"U+{cp:X}"
Expand Down Expand Up @@ -1317,14 +1320,14 @@ def lookup_fns(

if is_cjk:
s += """
if c == '\\u{FE00}' {
return (0, next_info.set_vs1_2());
if matches!(c, '\\u{FE00}' | '\\u{FE02}') {
return (0, next_info.set_vs1_2_3());
}
"""
else:
s += """
if c == '\\u{FE01}' {
return (0, next_info.set_vs1_2());
return (0, next_info.set_vs1_2_3());
}
if c == '\\u{FE0E}' {
return (0, next_info.set_text_presentation());
Expand All @@ -1337,15 +1340,15 @@ def lookup_fns(
}
} else """

s += """if next_info.is_vs1_2() {
s += """if next_info.is_vs1_2_3() {
if matches!(c, '\\u{2018}' | '\\u{2019}' | '\\u{201C}' | '\\u{201D}') {
return ("""

s += str(2 - is_cjk)

s += """, WidthInfo::DEFAULT);
} else {
next_info = next_info.unset_vs1_2();
next_info = next_info.unset_vs1_2_3();
}
}
if next_info.is_ligature_transparent() {
Expand Down Expand Up @@ -1655,7 +1658,7 @@ def emit_module(
self.0
| WidthInfo::VARIATION_SELECTOR_16.0
& !WidthInfo::VARIATION_SELECTOR_15.0
& !WidthInfo::VARIATION_SELECTOR_1_OR_2.0,
& !WidthInfo::VARIATION_SELECTOR_1_2_OR_3.0,
)
}} else {{
Self::VARIATION_SELECTOR_16
Expand Down Expand Up @@ -1683,7 +1686,7 @@ def emit_module(
self.0
| WidthInfo::VARIATION_SELECTOR_15.0
& !WidthInfo::VARIATION_SELECTOR_16.0
& !WidthInfo::VARIATION_SELECTOR_1_OR_2.0,
& !WidthInfo::VARIATION_SELECTOR_1_2_OR_3.0,
)
}} else {{
Self(WidthInfo::VARIATION_SELECTOR_15.0)
Expand All @@ -1696,27 +1699,28 @@ def emit_module(
}}

/// Has 7th bit set
fn is_vs1_2(self) -> bool {{
(self.0 & WidthInfo::VARIATION_SELECTOR_1_OR_2.0) == WidthInfo::VARIATION_SELECTOR_1_OR_2.0
fn is_vs1_2_3(self) -> bool {{
(self.0 & WidthInfo::VARIATION_SELECTOR_1_2_OR_3.0)
== WidthInfo::VARIATION_SELECTOR_1_2_OR_3.0
}}

/// Set 7th bit
fn set_vs1_2(self) -> Self {{
fn set_vs1_2_3(self) -> Self {{
if (self.0 & LIGATURE_TRANSPARENT_MASK) == LIGATURE_TRANSPARENT_MASK {{
Self(
self.0
| WidthInfo::VARIATION_SELECTOR_1_OR_2.0
| WidthInfo::VARIATION_SELECTOR_1_2_OR_3.0
& !WidthInfo::VARIATION_SELECTOR_15.0
& !WidthInfo::VARIATION_SELECTOR_16.0,
)
}} else {{
Self(WidthInfo::VARIATION_SELECTOR_1_OR_2.0)
Self(WidthInfo::VARIATION_SELECTOR_1_2_OR_3.0)
}}
}}

/// Clear 7th bit
fn unset_vs1_2(self) -> Self {{
Self(self.0 & !WidthInfo::VARIATION_SELECTOR_1_OR_2.0)
fn unset_vs1_2_3(self) -> Self {{
Self(self.0 & !WidthInfo::VARIATION_SELECTOR_1_2_OR_3.0)
}}
}}

Expand Down
4 changes: 2 additions & 2 deletions src/lib.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -62,8 +62,8 @@
//! - Outside of an East Asian context, [text presentation sequences] have width 1 if their base character:
//! - Has the [`Emoji_Presentation`] property, and
//! - Is not in the [Enclosed Ideographic Supplement] block.
//! - [`'\u{2018}'`, `'\u{2019}'`, `'\u{201C}'`, and `'\u{201D}'`][General Punctuation] always have width 1 when followed by '\u{FE00}',
//! and width 2 when followed by '\u{FE01}'.
//! - [`'\u{2018}'`, `'\u{2019}'`, `'\u{201C}'`, and `'\u{201D}'`][General Punctuation] always have width 1
//! when followed by '\u{FE00}' or '\u{FE02}', and width 2 when followed by '\u{FE01}'.
//! - Script-specific ligatures:
//! - For all the following ligatures, the insertion of any number of [default-ignorable][`Default_Ignorable_Code_Point`]
//! [combining marks] anywhere in the sequence will not change the total width. In addition, for all non-Arabic
Expand Down
Loading
Loading