mirror of
https://gitlab.freedesktop.org/uchardet/uchardet.git
synced 2025-12-14 15:40:06 +08:00
2bade77bf9
ISO-8859-2 and Windows-1250 are absolutely similar for all letters in the Hungarian alphabet. So for most texts, it is not an error to return one charset or the other. What could make the difference is for instance that Windows-1250 has some symbols where ISO-8859-2 has control characters, like quotes, dashes, the euro symbol… Since control characters have a negative impact on confidence now, texts with such symbols would tend towards Windows-1250 decision. The new test file has such quote symbols.
49 lines
1.3 KiB
CMake
49 lines
1.3 KiB
CMake
set(
|
|
UCHARDET_TEST_SOURCES
|
|
uchardet-tests.c
|
|
)
|
|
|
|
add_executable(
|
|
uchardet-tests
|
|
${UCHARDET_TEST_SOURCES}
|
|
)
|
|
|
|
target_link_libraries(
|
|
uchardet-tests
|
|
libuchardet
|
|
)
|
|
|
|
set_target_properties(
|
|
uchardet-tests
|
|
PROPERTIES
|
|
LINKER_LANGUAGE
|
|
C
|
|
OUTPUT_NAME
|
|
uchardet-tests
|
|
)
|
|
|
|
# Iterate through all langs.
|
|
file(GLOB dirs "[a-z][a-z]")
|
|
foreach(dir ${dirs})
|
|
get_filename_component(lang ${dir} NAME)
|
|
file(GLOB files "${dir}/*")
|
|
# Iterate through all files.
|
|
foreach(file ${files})
|
|
get_filename_component(charset ${file} NAME_WE)
|
|
# These are tests known to fail (not supported or not efficient
|
|
# enough). We will have to take a closer look and fix these, but
|
|
# there is no need to break the whole `make test` right now,
|
|
# which may make actual regressions harder to notice.
|
|
if ("${lang}:${charset}" STREQUAL "el:windows-1253" OR
|
|
"${lang}:${charset}" STREQUAL "ja:utf-16le" OR
|
|
"${lang}:${charset}" STREQUAL "ja:utf-16be" OR
|
|
"${lang}:${charset}" STREQUAL "he:iso-8859-8")
|
|
message(STATUS "Skipping test ${lang}:${charset} (known broken)")
|
|
else()
|
|
add_test(NAME "${lang}:${charset}"
|
|
COMMAND uchardet-tests ${file})
|
|
endif()
|
|
endforeach()
|
|
endforeach()
|
|
|