diff options
Diffstat (limited to 'JLanguageTool/src/resource/uk')
-rw-r--r-- | JLanguageTool/src/resource/uk/.cvsignore | 1 | ||||
-rw-r--r-- | JLanguageTool/src/resource/uk/README | 40 | ||||
-rw-r--r-- | JLanguageTool/src/resource/uk/make-dict-uk.sh | 6 | ||||
-rw-r--r-- | JLanguageTool/src/resource/uk/manually_added.txt | 1 | ||||
-rw-r--r-- | JLanguageTool/src/resource/uk/ukrainian.info | 9 |
5 files changed, 57 insertions, 0 deletions
diff --git a/JLanguageTool/src/resource/uk/.cvsignore b/JLanguageTool/src/resource/uk/.cvsignore new file mode 100644 index 0000000..7af46bd --- /dev/null +++ b/JLanguageTool/src/resource/uk/.cvsignore @@ -0,0 +1 @@ +*.dict diff --git a/JLanguageTool/src/resource/uk/README b/JLanguageTool/src/resource/uk/README new file mode 100644 index 0000000..27b28e0 --- /dev/null +++ b/JLanguageTool/src/resource/uk/README @@ -0,0 +1,40 @@ +In this directory initial fsa files for Ukrainian dictionary will reside. + +Currently the only tagger available is based on myspell uk_UA.dic dictionary. +It provides three POS tags "noun", "verb" and "adj" but only for lemmas (no inflection engine yet). +It also provides "plural" tag for nouns which can be only plural. + +Download dictionary from from http://dict.linux.org.ua/other/uk_UA.dic.bz2 +and unpack it in this directory. + + +Список теґів (pos tags): + +1. підтримуються: +noun іменник +verb дієслово +adj прикметник + +2. Плануються: +plural множина (підтримується зараз для іменників тільки множини) +single однина + +musc чоловічий +fem жіночий +neut середній + + відмінки: +v_naz +v_rod +v_dav +v_zna +v_oru +v_mis +v_kly + +future майбутній час +past минулий час +present теперішній час + +refl зворотня форма (дієслова) + diff --git a/JLanguageTool/src/resource/uk/make-dict-uk.sh b/JLanguageTool/src/resource/uk/make-dict-uk.sh new file mode 100644 index 0000000..467381d --- /dev/null +++ b/JLanguageTool/src/resource/uk/make-dict-uk.sh @@ -0,0 +1,6 @@ +#!/bin/sh + +LANG=POSIX +OUTPUT=ukrainian.dict +cat manually_added.txt | fsa_ubuild -O -o $OUTPUT +echo "Output written to $OUTPUT" diff --git a/JLanguageTool/src/resource/uk/manually_added.txt b/JLanguageTool/src/resource/uk/manually_added.txt new file mode 100644 index 0000000..6ac950c --- /dev/null +++ b/JLanguageTool/src/resource/uk/manually_added.txt @@ -0,0 +1 @@ +світанки світанок SUB:NOM:PLU:NEU diff --git a/JLanguageTool/src/resource/uk/ukrainian.info b/JLanguageTool/src/resource/uk/ukrainian.info new file mode 100644 index 0000000..33e4d54 --- /dev/null +++ b/JLanguageTool/src/resource/uk/ukrainian.info @@ -0,0 +1,9 @@ +# +# Dictionary properties. +# + +fsa.dict.separator=+ +fsa.dict.encoding=utf-8 + +fsa.dict.uses-prefixes=false +fsa.dict.uses-infixes=false
\ No newline at end of file |