Skip to content

Fix qutf8 decode bug #24

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 4 commits into
base: main
Choose a base branch
from
Open

Fix qutf8 decode bug #24

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
83f251b
Update common.c
dingmaotu Jan 18, 2024
033b9b4
Update CMakeLists.txt
dingmaotu Jan 18, 2024
690c9b0
Update CMakeLists.txt
dingmaotu Jan 18, 2024
daee8f0
Update common.c
dingmaotu Jan 18, 2024
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
21 changes: 12 additions & 9 deletions CMakeLists.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,6 +12,7 @@ option(IC_DEBUG_UBSAN "Build with undefined behaviour sanitizer" OFF)
option(IC_DEBUG_ASAN "Build with address sanitizer" OFF)
option(IC_DEBUG_MSG "Enable printing debug messages stderr (only if also ISOCLINE_DEBUG=1 is set in the environment)" ON)
option(IC_SEPARATE_OBJS "Compile with separate object files instead of one (warning: exports internal symbols)" OFF)
option(IC_BUILD_TESTS "Build test binaries (example & test_colors)" ON)

set(ic_version "0.1")
set(ic_sources src/isocline.c)
Expand Down Expand Up @@ -151,12 +152,14 @@ target_include_directories(isocline PUBLIC
$<INSTALL_INTERFACE:${ic_install_dir}/include>
)

add_executable(example test/example.c)
target_compile_options(example PRIVATE ${ic_cflags})
target_include_directories(example PRIVATE include)
target_link_libraries(example PRIVATE isocline)

add_executable(test_colors test/test_colors.c)
target_compile_options(test_colors PRIVATE ${ic_cflags})
target_include_directories(test_colors PRIVATE include)
target_link_libraries(test_colors PRIVATE isocline)
if (IC_BUILD_TESTS)
add_executable(example test/example.c)
target_compile_options(example PRIVATE ${ic_cflags})
target_include_directories(example PRIVATE include)
target_link_libraries(example PRIVATE isocline)

add_executable(test_colors test/test_colors.c)
target_compile_options(test_colors PRIVATE ${ic_cflags})
target_include_directories(test_colors PRIVATE include)
target_link_libraries(test_colors PRIVATE isocline)
endif()
15 changes: 13 additions & 2 deletions src/common.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -232,10 +232,21 @@ ic_private unicode_t unicode_from_qutf8(const uint8_t* s, ssize_t len, ssize_t*
return (((c0 & 0x1F) << 6) | (s[1] & 0x3F));
}
// 3 bytes: reject overlong and surrogate halves
/*
Fix: unicode_from_qutf8 ingores 0xED and 0xEF cases;

see https://github.com/koka-lang/koka/blob/master/kklib/src/string.c
line 252 (kk_utf8_read_validate)

// 3 byte encoding; reject overlong and utf-16 surrogate halves (0xD800 - 0xDFFF)
if ((b == 0xE0 && s[1] >= 0xA0 && s[1] <= 0xBF && kk_utf8_is_cont(s[2]))
|| ((b >= 0xE1 && b <= 0xEF && b != 0xED) && kk_utf8_is_cont(s[1]) && kk_utf8_is_cont(s[2]))
|| (b == 0xED && s[1] >= 0x80 && s[1] <= 0x9F && kk_utf8_is_cont(s[2])))
*/
else if (len >= 3 &&
((c0 == 0xE0 && s[1] >= 0xA0 && s[1] <= 0xBF && utf8_is_cont(s[2])) ||
(c0 >= 0xE1 && c0 <= 0xEC && utf8_is_cont(s[1]) && utf8_is_cont(s[2]))
))
(c0 >= 0xE1 && c0 <= 0xEF && c0 != 0xED && utf8_is_cont(s[1]) && utf8_is_cont(s[2])) ||
(c0 == 0xED && s[1] > 0x80 && s[1] <= 0x9F && utf8_is_cont(s[2]))))
{
if (count != NULL) *count = 3;
return (((c0 & 0x0F) << 12) | ((unicode_t)(s[1] & 0x3F) << 6) | (s[2] & 0x3F));
Expand Down