cld2 - Compact Language Detector 2

Tu as vu l’outil (open source de Google) qui est là-dessous ?

►https://code.google.com/p/cld2

CLD2 Summary — Compact Language Detection 2
Dick Sites ------@google.com
2013.07.28
CLD2 probabilistically detects over 80 languages in Unicode UTF-8 text, either plain text or HTML/XML. Legacy encodings must be converted to valid UTF-8 by the caller. For mixed-language input, CLD2 returns the top three languages found and their approximate percentages of the total text bytes (e.g. 80% English and 20% French out of 1000 bytes of text means about 800 bytes of English and 200 bytes of French). Optionally, it also returns a vector of text spans with the language of each identified. This may be useful for applying different spelling-correction dictionaries or different machine translation requests to each span. The design target is web pages of at least 200 characters (about two sentences); CLD2 is not designed to do well on very short text, lists of proper names, part numbers, etc.

comme le prouve la flèche noire, oui :)

Oups !
En plus, je l’avais étoilé, à l’époque.
Neurona volant, curiositas manet.

compilation:
# cd internal/ && ./compile_full.sh

usage :
# curl seenthis.net | ./compact_lang_det_test_full0720

ExtLanguage FRENCH(64% 696p), ENGLISH(32% 743p), LATIN(1% 256p), 10/109 KB of non-tag letters, Summary : FRENCH
SummaryLanguage FRENCH at 4 of 112441 4904us (22 MB/sec), (null)

et une réponse de @fwix_ :

guess_language: a #python, compact and light #language recognition ▻https://bitbucket.org/spirit/guess_language #détection #langue