diff options
Diffstat (limited to 'debian')
-rw-r--r-- | debian/README.Debian | 75 |
1 files changed, 75 insertions, 0 deletions
diff --git a/debian/README.Debian b/debian/README.Debian index 162e3f0..382d20d 100644 --- a/debian/README.Debian +++ b/debian/README.Debian @@ -4,6 +4,81 @@ unicode for Debian This package is the Debian version of unicode, a C++ library for Unicode encoding. +CLI interface (package unicode-tools) +------------------------------------- + +* unicode-recode + + Usage: recode <from-format> <from-file> <to-format> <to-file> + Format: + UTF-8 UTF-8 + UTF-16 UTF-16, native endian + UTF-16LE UTF-16, little endian + UTF-16BE UTF-16, big endian + UTF-32 UTF-32, native endian + UTF-32LE UTF-32, little endian + UTF-32BE UTF-32, big endian + ISO-8859-1 ISO-8859-1 (Latin-1) + ISO-8859-15 ISO-8859-15 (Latin-9) + Exit code: 0 if valid, 1 otherwise. + +* unicode-validate + + Usage: validate <format> <file> + Format: + UTF-8 UTF-8 + UTF-16 UTF-16, big or little endian + UTF-16LE UTF-16, little endian + UTF-16BE UTF-16, big endian + UTF-32 UTF-32, big or little endian + UTF-32LE UTF-32, little endian + UTF-32BE UTF-32, big endian + Exit code: 0 if valid, 1 otherwise. + + +C++ interface (package libunicode-dev) +-------------------------------------- + +Example: + +#include <unicode.h> +... + + std::string utf8_value {u8"äöü"}; + std::u16string utf16_value{unicode::convert<char, char16_t>(utf8_value)}; + +And for C++20: + + std::u8string utf8_value {u8"äöü"}; + std::u16string utf16_value{unicode::convert<char8_t, char16_t>(utf8_value)}; + +The following encodings are implicitly deducted from types: + * char resp. char8_t (C++20): UTF-8 + * char16_t: UTF-16 + * char32_t: UTF-32 + +Explicit encoding specification is also possible: + + std::string value {"äöü"}; + std::u32string utf32_value{unicode::convert<unicode::ISO_8859_1, unicode::UTF_32>(value)}; + +Supported encodings are: + + * unicode::UTF_8 + * unicode::UTF_16 + * unicode::UTF_32 + * unicode::ISO_8859_1 + * unicode::ISO_8859_15 + +Validation can be done like this: + + bool valid{unicode::is_valid_utf<char16_t>(utf16_value)}; + +Or via explicit encoding specification: + + bool valid{unicode::is_valid_utf<unicode::UTF_8>(utf8_value)}; + + Contact ------- |