summaryrefslogtreecommitdiff
path: root/libtextcat
diff options
context:
space:
mode:
authorThomas Lange <tl@openoffice.org>2009-09-24 08:26:57 +0000
committerThomas Lange <tl@openoffice.org>2009-09-24 08:26:57 +0000
commit76812dd089689fc486535d7748a21a1e1f55e503 (patch)
tree0f7fb61255c88847a3b2eace09b6034602e05037 /libtextcat
parentb182d1f3dbcd6590e03475301e1ba4bfffdbf505 (diff)
#i105261# zulu fingerprint for language guessing added
Diffstat (limited to 'libtextcat')
-rw-r--r--libtextcat/data/new_fingerprints/fpdb.conf1
-rw-r--r--libtextcat/data/new_fingerprints/zulu.lm400
2 files changed, 401 insertions, 0 deletions
diff --git a/libtextcat/data/new_fingerprints/fpdb.conf b/libtextcat/data/new_fingerprints/fpdb.conf
index 5b54fef1d7ad..df56f9e270ef 100644
--- a/libtextcat/data/new_fingerprints/fpdb.conf
+++ b/libtextcat/data/new_fingerprints/fpdb.conf
@@ -82,3 +82,4 @@ ukrainian.lm uk--utf8
vietnamese.lm vi--utf8
welsh.lm cy--utf8
yiddish_utf.lm yi--utf8
+zulu.lm zu--utf8
diff --git a/libtextcat/data/new_fingerprints/zulu.lm b/libtextcat/data/new_fingerprints/zulu.lm
new file mode 100644
index 000000000000..f30c09ced93f
--- /dev/null
+++ b/libtextcat/data/new_fingerprints/zulu.lm
@@ -0,0 +1,400 @@
+_
+a
+e
+i
+n
+u
+o
+l
+k
+h
+s
+a_
+b
+t
+m
+g
+w
+z
+e_
+i_
+ng
+ku
+d
+y
+la
+an
+_n
+th
+le
+_u
+o_
+el
+ba
+_k
+en
+in
+wa
+p
+_e
+zi
+.
+hi
+si
+al
+ha
+uk
+ab
+_i
+r
+is
+ka
+_a
+kh
+we
+li
+ni
+ma
+_ng
+he
+ul
+._
+ga
+thi
+la_
+be
+ak
+c
+on
+nd
+na
+ok
+am
+lo
+ho
+,
+se
+ph
+hi_
+ut
+es
+nga
+_ku
+,_
+ez
+thi_
+un
+uth
+le_
+uku
+hu
+f
+u_
+um
+ek
+ne
+go
+q
+_uk
+at
+aba
+_l
+sh
+lu
+M
+_uku
+ol
+_b
+hl
+ni_
+ngo
+kw
+-
+N
+ik
+oku
+em
+nt
+as
+ge
+az
+ya
+iz
+sa
+_o
+S
+uthi
+A
+za
+_w
+wa_
+_s
+mb
+kut
+kuth
+ela
+ye
+_y
+uthi_
+il
+ay
+ele
+ba_
+I
+dl
+nge
+ath
+ub
+ke
+U
+zo
+na_
+yi
+us
+kuthi
+esi
+ob
+v
+om
+ama
+it
+lo_
+bu
+L
+ezi
+j
+ny
+im
+ing
+li_
+_ab
+eni
+no
+de
+ela_
+ze
+ang
+ko
+ala
+lw
+yo
+zin
+_U
+lel
+eng
+mi
+_ngo
+eb
+uz
+me
+gi
+ti
+ukut
+so
+ukuth
+bo
+da
+_ba
+nz
+_aba
+the
+eli
+akh
+eni_
+E
+ban
+s_
+aka
+_kw
+ma_
+ap
+_ukut
+he_
+ini
+di
+K
+ka_
+ib
+kwa
+ulu
+ele_
+kho
+nj
+bi
+_z
+khu
+we_
+lal
+enz
+ho_
+et
+C
+gu
+zi_
+and
+hla
+ngi
+pha
+_um
+_ka
+isi
+_nge
+isa
+aph
+ung
+izi
+dla
+ala_
+zw
+nde
+to
+n_
+ne_
+nk
+ke_
+_I
+athi
+_no
+lan
+_wa
+kul
+B
+ind
+fu
+wen
+ikh
+azi
+ule
+kub
+e.
+_S
+x
+o.
+ona
+kha
+_iz
+je
+bh
+_M
+er
+kwe
+oba
+ane
+O
+_N
+sa_
+a.
+lwa
+_ez
+kus
+ki
+mu
+od
+"
+ebe
+P
+_nga
+hul
+_m
+ase
+ben
+_be
+T
+ic
+nda
+_si
+_na
+/
+ant
+ngu
+ad
+anga
+nje
+ith
+a._
+ye_
+athi_
+R
+os
+alo
+tha
+za_
+eth
+_es
+uma
+ana
+ile
+te
+ale
+aban
+:
+_A
+oba_
+hat
+kun
+ha_
+phe
+be_
+ali
+_am
+si_
+wo
+uy
+sik
+ise
+kan
+hath
+dlal
+_ne
+zwe
+aw
+han
+tu
+nye
+qe
+_ko
+ah
+hel
+thu
+isa_
+gob
+_K
+_lo
+ta
+_ama
+ot
+ula
+_em
+ze_
+i.
+ngob
+_izi
+hol
+ar
+ani
+ole
+uba
+_in
+up
+eka
+ini_
+goba
+tho
+hon
+_ezi
+ona_
+ezin
+ngoba
+lu_
+goba_
+ip
+a,
+eli_
+t_
+nya
+ndl
+sha
+_is
+the_
+i._
+amb