8000 Upgrade to Unicode 10 by rth · Pull Request #56 · unicode-rs/unicode-segmentation · GitHub
[go: up one dir, main page]
Skip to content

Upgrade to Unicode 10 #56

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

Merged
merged 1 commit into from
Oct 22, 2019
Merged

Upgrade to Unicode 10 #56

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
4 changes: 2 additions & 2 deletions scripts/unicode.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -59,7 +59,7 @@ def is_surrogate(n):

def fetch(f):
if not os.path.exists(os.path.basename(f)):
os.system("curl -O http://www.unicode.org/Public/9.0.0/ucd/%s"
os.system("curl -O http://www.unicode.org/Public/10.0.0/ucd/%s"
% f)

if not os.path.exists(os.path.basename(f)):
Expand Down Expand Up @@ -357,4 +357,4 @@ def emit_break_module(f, break_table, break_cats, name):
for cat in sentence_cats:
sentence_table.extend([(x, y, cat) for (x, y) in sentence_cats[cat]])
sentence_table.sort(key=lambda w: w[0])
emit_break_module(rf, sentence_table, list(sentence_cats.keys()), "sentence")
emit_break_module(rf, sentence_table, list(sentence_cats.keys()), "sentence")
6 changes: 3 additions & 3 deletions scripts/unicode_gen_breaktests.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -172,7 +172,7 @@ def create_grapheme_data(f):
stype = "&'static [(&'static str, &'static [&'static str])]"
dtype = "&'static [(&'static str, &'static [&'static str], &'static [&'static str])]"
f.write(" // official Unicode test data\n")
f.write(" // http://www.unicode.org/Public/9.0.0/ucd/auxiliary/GraphemeBreakTest.txt\n")
f.write(" // http://www.unicode.org/Public/10.0.0/ucd/auxiliary/GraphemeBreakTest.txt\n")
unicode.emit_table(f, "TEST_SAME", test_same, stype, True, showfun, True)
unicode.emit_table(f, "TEST_DIFF", test_diff, dtype, True, showfun, True)

Expand All @@ -187,7 +187,7 @@ def create_words_data(f):

wtype = "&'static [(&'static str, &'static [&'static str])]"
f.write(" // official Unicode test data\n")
f.write(" // http://www.unicode.org/Public/9.0.0/ucd/auxiliary/WordBreakTest.txt\n")
f.write(" // http://www.unicode.org/Public/10.0.0/ucd/auxiliary/WordBreakTest.txt\n")
unicode.emit_table(f, "TEST_WORD", test, wtype, True, showfun, True)

def create_sentence_data(f):
Expand All @@ -201,7 +201,7 @@ def create_sentence_data(f):

wtype = "&'static [(&'static str, &'static [&'static str])]"
f.write(" // official Unicode test data\n")
f.write(" // http://www.unicode.org/Public/UNIDATA/auxiliary/SentenceBreakTest.txt\n")
542C f.write(" // http://www.unicode.org/Public/10.0.0/ucd/auxiliary/SentenceBreakTest.txt\n")
unicode.emit_table(f, "TEST_SENTENCE", test, wtype, True, showfun, True)

if __name__ == "__main__":
Expand Down
Loading
0