From 09cf1e47f045399a9c0817c649f68cd7290054f3 Mon Sep 17 00:00:00 2001 From: Olly Betts Date: Wed, 16 May 2018 15:33:02 +1200 Subject: [PATCH] Add Indonesian stopword list Imported from snowball website. --- xapian-core/languages/Makefile.mk | 1 + xapian-core/languages/stopwords/indonesian.txt | 91 ++++++++++++++++++++++++++ 2 files changed, 92 insertions(+) create mode 100644 xapian-core/languages/stopwords/indonesian.txt diff --git a/xapian-core/languages/Makefile.mk b/xapian-core/languages/Makefile.mk index 61f6a14d6..4c96756bd 100644 --- a/xapian-core/languages/Makefile.mk +++ b/xapian-core/languages/Makefile.mk @@ -68,6 +68,7 @@ snowball_stopwords = \ languages/stopwords/french.txt\ languages/stopwords/german.txt\ languages/stopwords/hungarian.txt\ + languages/stopwords/indonesian.txt\ languages/stopwords/italian.txt\ languages/stopwords/norwegian.txt\ languages/stopwords/portuguese.txt\ diff --git a/xapian-core/languages/stopwords/indonesian.txt b/xapian-core/languages/stopwords/indonesian.txt new file mode 100644 index 000000000..c433b01b2 --- /dev/null +++ b/xapian-core/languages/stopwords/indonesian.txt @@ -0,0 +1,91 @@ +yang | that +dan | and +di | in +dari | from +ini | this +pada kepada | at, to [person] +ada adalah | there is, is +dengan | with +untuk | for +dalam | in the +oleh | by +sebagai | as +juga | also, too +ke | to +atau | or +tidak | not +itu | that +sebuah | a +tersebut | the +dapat | can, may +ia | he/she, yes +telah | already +satu | one +memiliki | have +mereka | they +bahwa | that +lebih | more, more than +karena | because, since +seorang | one person, same +akan | will, about to +seperti | as, like +secara | on +kemudian | later, then +beberapa | some +banyak | many +antara | between +setelah | after +yaitu | that is +hanya | only +hingga | to +serta | along with +sama | same, and +dia | he/she/it (informal) +tetapi | but +namun | however +melalui | through +bisa | can +sehingga | so +ketika | when +suatu | a +sendiri | own (adverb) +bagi | for +semua | all +harus | must +setiap | each, every +maka | then +maupun | as well +tanpa | without +saja | only +jika | if +bukan | not +belum | not yet +sedangkan | while +yakni | i.e. +meskipun | although +hampir | almost +kita | we/us (inclusive) +demikian | thereby +daripada | from/than/instead of +apa | what/which/or/eh +ialah | is +sana | there +begitu | so +seseorang | someone +selain | besides +terlalu | too +ataupun | or +saya | me/I (formal) +bila | if/when +bagaimana | how +tapi | but +apabila | when/if +kalau | if +kami | we/us (exclusive) +melainkan | but (rather) +boleh | may,can +aku | I/me (informal) +anda | you (formal) +kamu | you (informal) +beliau | he/she/it (formal) +kalian | you (plural) -- 2.11.4.GIT