From 038871fdb36359e1ec2027de1ef0227162f5473a Mon Sep 17 00:00:00 2001 From: Achim Date: Mon, 18 Mar 2013 17:17:35 -0400 Subject: Hungarian and Latvian non-breaking prefix files --- .../nonbreaking_prefixes/nonbreaking_prefix.lv | 100 +++++++++++++++++++++ 1 file changed, 100 insertions(+) create mode 100644 scripts/share/nonbreaking_prefixes/nonbreaking_prefix.lv (limited to 'scripts/share/nonbreaking_prefixes/nonbreaking_prefix.lv') diff --git a/scripts/share/nonbreaking_prefixes/nonbreaking_prefix.lv b/scripts/share/nonbreaking_prefixes/nonbreaking_prefix.lv new file mode 100644 index 000000000..81754a17a --- /dev/null +++ b/scripts/share/nonbreaking_prefixes/nonbreaking_prefix.lv @@ -0,0 +1,100 @@ +#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 +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 + +#List of titles. These are often followed by upper-case names, but do not indicate sentence breaks +dr +Dr +med +prof +Prof +inž +Inž +ist.loc +Ist.loc +kor.loc +Kor.loc +v.i +vietn +Vietn + +#misc - odd period-ending items that NEVER indicate breaks (p.m. does NOT fall into this category - it sometimes ends a sentence) +a.l +t.p +pārb +Pārb +vec +Vec +inv +Inv +sk +Sk +spec +Spec +vienk +Vienk +virz +Virz +māksl +Māksl +mūz +Mūz +akad +Akad +soc +Soc +galv +Galv +vad +Vad +sertif +Sertif +folkl +Folkl +hum +Hum + +#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 +Nr #NUMERIC_ONLY# -- cgit v1.2.3