slackbuilds/academic/cld2/README

The Compact Language Detection library can detect the language of
UTF8-encoded text. CLD2 supports over 160 languages and can parse both
plain text and HTML.

The Slackware script builds two shared libraries, libcld2 and
libcld2_full. The libcld2 library can recognise the core 83 languages
while the libcld2_full library has support for the entire set of 160+
language tables.

The script also builds a commandline tool, cld2, which is compiled
against the libcld2_full library.