Thanks to visit codestin.com
Credit goes to github.com

Skip to content

Update to Unicode 16 #6

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

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

Update to Unicode 16 #6

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
68 changes: 68 additions & 0 deletions gen-blocks.awk
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,68 @@
# Script to regenerate src/unicode_blocks.rs from Blocks.txt
#
# Usage awk -f gen-blocks.awk Blocks.txt > src/unicode_blocks.rs
#
# where Blocks.txt is fetched from:
# https://www.unicode.org/Public/UNIDATA/Blocks.txt

BEGIN { FS=";" }

/^# Blocks-[[:digit:]]+\.[[:digit:]]+\.[[:digit:]]+\.txt/ {
pos = match($0, "[[:digit:]]+\\.[[:digit:]]+\\.[[:digit:]]+");
if (pos < 1) {
printf("unable to extract version from: %s\n", $0);
exit(1);
}

version = substr($0, RSTART, RLENGTH);

print "// The dataset is from https://www.unicode.org/Public/UNIDATA/Blocks.txt"
print ""
print "use crate::UnicodeBlock;"
print ""
printf("pub const VERSION: &str = \"%s\";\n", version);

idx = 1
}

# Only process non-comment lines
/^[[:digit:]A-F]/ {
split($1, range, "\\.\\.");
start = range[1];
end = range[2];

name = $2
# trim leading spaces
if (match(name, "^ +") > 0) {
name = substr(name, RLENGTH + 1);
}

# build Rust constant name
const = name
gsub("[ -]", "_", const);
const = toupper(const);

printf("pub const %s: UnicodeBlock = UnicodeBlock {\n", const);
printf(" name: \"%s\", start: 0x%s, end: 0x%s\n", name, start, end);
print "};"

# skip blocks that end in _SURROGATES as these are not valid as Unicode
# escapes in Rust.
if (match(const, "_SURROGATES$") < 1) {
match_line = sprintf(" '\\u{%s}'..='\\u{%s}' => Some(%s),", start, end, const);
match_lines[idx++] = match_line;
}
}

END {
print ""
print "/// Given a character, determine what unicode block contains it."
print "pub fn find_unicode_block(c: char) -> Option<UnicodeBlock> {"
print " match c {"
for (i = 1; i < idx; i++) {
print match_lines[i];
}
print " _ => None,"
print " }"
print "}"
}
Loading