@qvac/translation-nmtcpp 0.1.0

package/third-party/indic-processor-deps/sacremoses/data/nonbreaking_prefixes/nonbreaking_prefix.sl

@@ -0,0 +1,78 @@
+dr
+Dr
+itd
+itn
+št #NUMERIC_ONLY#
+Št #NUMERIC_ONLY#
+d
+jan
+Jan
+feb
+Feb
+mar
+Mar
+apr
+Apr
+jun
+Jun
+jul
+Jul
+avg
+Avg
+sept
+Sept
+sep
+Sep
+okt
+Okt
+nov
+Nov
+dec
+Dec
+tj
+Tj
+npr
+Npr
+sl
+Sl
+op
+Op
+gl
+Gl
+oz
+Oz
+prev
+dipl
+ing
+prim
+Prim
+cf
+Cf
+gl
+Gl
+A
+B
+C
+D
+E
+F
+G
+H
+I
+J
+K
+L
+M
+N
+O
+P
+Q
+R
+S
+T
+U
+V
+W
+X
+Y
+Z

package/third-party/indic-processor-deps/sacremoses/data/nonbreaking_prefixes/nonbreaking_prefix.sv

@@ -0,0 +1,97 @@
+#single upper case letter are usually initials
+A
+B
+C
+D
+E
+F
+G
+H
+I
+J
+K
+L
+M
+N
+O
+P
+Q
+R
+S
+T
+U
+V
+W
+X
+Y
+Z
+Å
+Ä
+Ö  
+#misc abbreviations
+#If all words in text are in small case, then tex, mao, tom, maj, may be confused with names, and iaf, etc with named entities.
+AB
+VG
+dvs
+d.v.s
+d. v. s
+etc
+from
+fr.o.m
+fr. o. m
+iaf
+i.a.f
+i. a. f
+jfr
+kl
+kr
+mao
+m.a.o
+m. a. o
+mfl
+m.fl
+m. fl
+mm
+m.m
+m. m.
+osv
+o.s.v
+o. s. v
+pga
+p.g.a
+p. g. a
+tex
+t.ex
+t. ex
+#tom. is risky, as tom is a word, and can be at end of sentence. One recent text has 9 tom., and 52 tom not at end of sentence. 
+tom
+t.o.m
+t. o. m
+vs
+adv
+jur
+kand
+mag
+fil
+lic
+prop
+d
+f
+s
+mha
+m.h.a
+m. h. a
+vol
+#months
+jan
+feb
+mar
+apr
+#maj is a full word
+jun
+jul
+aug
+sep
+okt
+nov
+dec

package/third-party/indic-processor-deps/sacremoses/data/nonbreaking_prefixes/nonbreaking_prefix.ta

@@ -0,0 +1,71 @@
+#Anything in this file, followed by a period (and an upper-case word), does NOT indicate an end-of-sentence marker.
+
+#common exceptions
+# Rs
+ர
+# Rs
+ூ
+# Mr
+திரு
+
+#others
+
+
+#phonetics
+# A
+ஏ
+# B
+பீ
+# C
+சீ
+# D
+டீ
+# E
+ஈ
+# F
+எஃப்
+# G
+ஜீ
+# H
+எச்
+ஹெச்
+# I
+ஐ
+# J
+ஜே
+ஜை
+# K
+கே
+# L
+எல்
+# M
+எம்
+# N
+என்
+# O
+ஓ
+# P
+ப்பீ
+# Q
+கியூ
+# R
+ஆர்
+# S
+எஸ்
+# T
+ட்டீ
+# U
+யூ
+# V
+வீ
+# W
+டபிள்-யூ
+# X
+எக்ஸ்
+# Y
+வை
+# Z
+செட்
+
+#consonants
+

package/third-party/indic-processor-deps/sacremoses/data/nonbreaking_prefixes/nonbreaking_prefix.tdt

@@ -0,0 +1,210 @@
+#File adapted for TDT from PT by Raphael Merx. Last update: 10.11.2009.
+#Anything in this file, followed by a period (and an upper-case word), does NOT indicate an end-of-sentence marker.
+#Special cases are included for prefixes that ONLY appear before 0-9 numbers.
+
+#any single upper case letter  followed by a period is not a sentence ender (excluding I occasionally, but we leave it in)
+#usually upper case letters are initials in a name
+A
+B
+C
+D
+E
+F
+G
+H
+I
+J
+K
+L
+M
+N
+O
+P
+Q
+R
+S
+T
+U
+V
+W
+X
+Y
+Z
+a
+b
+c
+d
+e
+f
+g
+h
+i
+j
+k
+l
+m
+n
+o
+p
+q
+r
+s
+t
+u
+v
+w
+x
+y
+z
+
+
+#Roman Numerals. A dot after one of these is not a sentence break in Portuguese.
+I
+II
+III
+IV
+V
+VI
+VII
+VIII
+IX
+X
+XI
+XII
+XIII
+XIV
+XV
+XVI
+XVII
+XVIII
+XIX
+XX
+i
+ii
+iii
+iv
+v
+vi
+vii
+viii
+ix
+x
+xi
+xii
+xiii
+xiv
+xv
+xvi
+xvii
+xviii
+xix
+xx
+
+#List of titles. These are often followed by upper-case names, but do not indicate sentence breaks
+Adj
+Adm
+Adv
+Art
+Ca
+Capt
+Cmdr
+Col
+Comdr
+Con
+Corp
+Cpl
+DR
+DRA
+Dr
+Dra
+Dras
+Drs
+Eng
+Enga
+Engas
+Engos
+Ex
+Exo
+Exmo
+Fig
+Gen
+Hosp
+Insp
+Lda
+MM
+MR
+MRS
+MS
+Maj
+Mrs
+Ms
+Msgr
+Op
+Ord
+Pfc
+Ph
+Prof
+Pvt
+Rep
+Reps
+Res
+Rev
+Rt
+Sen
+Sens
+Sfc
+Sgt
+Sr
+Sra
+Sras
+Srs
+Sto
+Supt
+Surg
+adj
+adm
+adv
+art
+cit
+col
+con
+corp
+cpl
+dr
+dra
+dras
+drs
+eng
+enga
+engas
+engos
+ex
+exo
+exmo
+fig
+op
+prof
+sr
+sra
+sras
+srs
+sto
+
+#misc - odd period-ending items that NEVER indicate breaks (p.m. does NOT fall into this category - it sometimes ends a sentence)
+v
+vs
+i.e
+rev
+e.g
+
+#Numbers only. These should only induce breaks when followed by a numeric sequence
+# add NUMERIC_ONLY after the word for this function
+#This case is mostly for the english "No." which can either be a sentence of its own, or
+#if followed by a number, a non-breaking prefix
+No #NUMERIC_ONLY# 
+Nos
+Art #NUMERIC_ONLY#
+Nr
+p #NUMERIC_ONLY#
+pp #NUMERIC_ONLY#
+

package/third-party/indic-processor-deps/sacremoses/data/nonbreaking_prefixes/nonbreaking_prefix.te

@@ -0,0 +1,70 @@
+#Anything in this file, followed by a period (and an upper-case word), does NOT indicate an end-of-sentence marker.
+
+#common exceptions
+# Rs
+ర
+# Rs
+ూ
+# Mr
+శ్రీ
+
+#others
+
+
+#phonetics
+# A
+ఎ
+# B
+బి
+# C
+సి
+# D
+డి
+# E
+ఇ
+# F
+ఎఫ్
+# G
+జి
+# H
+హెచ్‌
+# I
+ఐ
+# J
+జె
+# K
+కె
+# L
+ఎల్
+# M
+ఎం
+ఎమ్
+# N
+ఎన్
+# O
+ఓ
+# P
+పి
+# Q
+క్యూ
+# R
+ఆర్
+# S
+ఎస్
+# T
+టి
+# U
+యు
+# V
+వి
+# W
+డబ్ల్యూ
+# X
+ఎక్స్
+# Y
+వై
+# Z
+జెడ్
+
+#consonants
+

package/third-party/indic-processor-deps/sacremoses/data/nonbreaking_prefixes/nonbreaking_prefix.yue

@@ -0,0 +1,53 @@
+#
+# Cantonese (Chinese)
+#
+# Anything in this file, followed by a period, 
+# does NOT indicate an end-of-sentence marker.
+#
+# English/Euro-language given-name initials (appearing in
+# news, periodicals, etc.)
+A
+Ā
+B
+C
+Č
+D
+E
+Ē
+F
+G
+Ģ
+H
+I
+Ī
+J
+K
+Ķ
+L
+Ļ
+M
+N
+Ņ
+O
+P
+Q
+R
+S
+Š
+T
+U
+Ū
+V
+W
+X
+Y
+Z
+Ž
+
+# Numbers only. These should only induce breaks when followed by
+# a numeric sequence.
+# Add NUMERIC_ONLY after the word for this function. This case is
+# mostly for the english "No." which can either be a sentence of its
+# own, or if followed by a number, a non-breaking prefix.
+No #NUMERIC_ONLY#
+Nr #NUMERIC_ONLY#

package/third-party/indic-processor-deps/sacremoses/data/nonbreaking_prefixes/nonbreaking_prefix.zh

@@ -0,0 +1,53 @@
+#
+# Mandarin (Chinese)
+#
+# Anything in this file, followed by a period, 
+# does NOT indicate an end-of-sentence marker.
+#
+# English/Euro-language given-name initials (appearing in
+# news, periodicals, etc.)
+A
+Ā
+B
+C
+Č
+D
+E
+Ē
+F
+G
+Ģ
+H
+I
+Ī
+J
+K
+Ķ
+L
+Ļ
+M
+N
+Ņ
+O
+P
+Q
+R
+S
+Š
+T
+U
+Ū
+V
+W
+X
+Y
+Z
+Ž
+
+# Numbers only. These should only induce breaks when followed by
+# a numeric sequence.
+# Add NUMERIC_ONLY after the word for this function. This case is
+# mostly for the english "No." which can either be a sentence of its
+# own, or if followed by a number, a non-breaking prefix.
+No #NUMERIC_ONLY#
+Nr #NUMERIC_ONLY#