utf8proc

A clean C library for processing UTF-8 Unicode data
git clone https://git.sinitax.com/juliastrings/utf8proc
Log | Files | Refs | README | LICENSE | sfeed.txt

commit 243875b456f23717dfc4b0de4d275b23145c91d1
parent f645f2a70085f9745a647f56ca8cbfb35ab9d2ef
Author: Steven G. Johnson <stevenj@alum.mit.edu>
Date:   Sun, 29 Mar 2020 09:35:32 -0400

fixes

Diffstat:
Mdata/Makefile | 18+++++++++---------
Mtest/tests.c | 4++--
2 files changed, 11 insertions(+), 11 deletions(-)

diff --git a/data/Makefile b/data/Makefile @@ -25,31 +25,31 @@ CharWidths.txt: charwidths.jl EastAsianWidth.txt UNICODE_VERSION=13.0.0 UnicodeData.txt: - $(CURL) $(CURLFLAGS) -o $@ -O http://www.unicode.org/Public/$(UNICODE_VERSION)/ucd/UnicodeData.txt + $(CURL) $(CURLFLAGS) -o $@ http://www.unicode.org/Public/$(UNICODE_VERSION)/ucd/UnicodeData.txt EastAsianWidth.txt: - $(CURL) $(CURLFLAGS) -o $@ -O $(URLCACHE)http://www.unicode.org/Public/$(UNICODE_VERSION)/ucd/EastAsianWidth.txt + $(CURL) $(CURLFLAGS) -o $@ $(URLCACHE)http://www.unicode.org/Public/$(UNICODE_VERSION)/ucd/EastAsianWidth.txt GraphemeBreakProperty.txt: - $(CURL) $(CURLFLAGS) -o $@ -O $(URLCACHE)http://www.unicode.org/Public/$(UNICODE_VERSION)/ucd/auxiliary/GraphemeBreakProperty.txt + $(CURL) $(CURLFLAGS) -o $@ $(URLCACHE)http://www.unicode.org/Public/$(UNICODE_VERSION)/ucd/auxiliary/GraphemeBreakProperty.txt DerivedCoreProperties.txt: - $(CURL) $(CURLFLAGS) -o $@ -O $(URLCACHE)http://www.unicode.org/Public/$(UNICODE_VERSION)/ucd/DerivedCoreProperties.txt + $(CURL) $(CURLFLAGS) -o $@ $(URLCACHE)http://www.unicode.org/Public/$(UNICODE_VERSION)/ucd/DerivedCoreProperties.txt CompositionExclusions.txt: - $(CURL) $(CURLFLAGS) -o $@ -O $(URLCACHE)http://www.unicode.org/Public/$(UNICODE_VERSION)/ucd/CompositionExclusions.txt + $(CURL) $(CURLFLAGS) -o $@ $(URLCACHE)http://www.unicode.org/Public/$(UNICODE_VERSION)/ucd/CompositionExclusions.txt CaseFolding.txt: - $(CURL) $(CURLFLAGS) -o $@ -O $(URLCACHE)http://www.unicode.org/Public/$(UNICODE_VERSION)/ucd/CaseFolding.txt + $(CURL) $(CURLFLAGS) -o $@ $(URLCACHE)http://www.unicode.org/Public/$(UNICODE_VERSION)/ucd/CaseFolding.txt NormalizationTest.txt: - $(CURL) $(CURLFLAGS) -o $@ -O $(URLCACHE)http://www.unicode.org/Public/$(UNICODE_VERSION)/ucd/NormalizationTest.txt + $(CURL) $(CURLFLAGS) -o $@ $(URLCACHE)http://www.unicode.org/Public/$(UNICODE_VERSION)/ucd/NormalizationTest.txt GraphemeBreakTest.txt: - $(CURL) $(CURLFLAGS) -o $@ -O $(URLCACHE)http://www.unicode.org/Public/$(UNICODE_VERSION)/ucd/auxiliary/GraphemeBreakTest.txt + $(CURL) $(CURLFLAGS) -o $@ $(URLCACHE)http://www.unicode.org/Public/$(UNICODE_VERSION)/ucd/auxiliary/GraphemeBreakTest.txt emoji-data.txt: - $(CURL) $(CURLFLAGS) -o $@ -O $(URLCACHE)http://unicode.org/Public/$(UNICODE_VERSION)/ucd/emoji/emoji-data.txt + $(CURL) $(CURLFLAGS) -o $@ $(URLCACHE)http://unicode.org/Public/$(UNICODE_VERSION)/ucd/emoji/emoji-data.txt clean: rm -f UnicodeData.txt EastAsianWidth.txt GraphemeBreakProperty.txt DerivedCoreProperties.txt CompositionExclusions.txt CaseFolding.txt NormalizationTest.txt GraphemeBreakTest.txt CharWidths.txt emoji-data.txt diff --git a/test/tests.c b/test/tests.c @@ -48,10 +48,10 @@ size_t encode(char *dest, const char *buf) /* simplistic, portable replacement for getline, sufficient for our tests */ size_t simple_getline(char buf[8192], FILE *f) { size_t i = 0; - while (i < 1023) { + while (i < 8191) { int c = getc(f); if (c == EOF || c == '\n') break; - buf[i++] = (char) c; + buf[i++] = (char) ((uint8_t) c); } buf[i] = 0; return i;