diff options
| author | Chris Dyer <redpony@gmail.com> | 2014-12-29 02:01:38 -0500 | 
|---|---|---|
| committer | Chris Dyer <redpony@gmail.com> | 2014-12-29 02:01:38 -0500 | 
| commit | 4c4ab517897a217734e7a7e5942735712b561981 (patch) | |
| tree | 8e11ab45ae3b374b7474a2eae17e15d71933d5ff /corpus | |
| parent | 5bc712f5bfa3ec7924a52ded4a7d6b3bab9539f0 (diff) | |
| parent | 8646b68e5b124f612fd65b51ea40624f65a2f3d6 (diff) | |
foo
Diffstat (limited to 'corpus')
| -rw-r--r-- | corpus/support/token_list | 49 | ||||
| -rw-r--r-- | corpus/support/token_patterns | 1 | 
2 files changed, 48 insertions, 2 deletions
| diff --git a/corpus/support/token_list b/corpus/support/token_list index c857b363..00daa82b 100644 --- a/corpus/support/token_list +++ b/corpus/support/token_list @@ -1,9 +1,54 @@  ##################### hyphenated words added by Fei since 3/7/05  ##X-ray -# Finnish abbreviation patterns +# Finnish  eaa. -v. +ap. +arv. +ay. +eKr. +em. +engl. +esim. +fil. +lis. +fil. +maist. +fil.toht. +harv. +ilt. +jatk. +jKr. +jms. +jne. +joht. +klo +ko. +ks. +leht. +lv. +lyh. +mm. +mon. +nim. +nro. +ns. +nti. +os. +oy. +pj. +pnä. +puh. +pvm. +rva. +tms. +ts. +vars. +vrt. +ym. +yms. +yo. +>>>>>>> 8646b68e5b124f612fd65b51ea40624f65a2f3d6  # hindi abbreviation patterns  जन. diff --git a/corpus/support/token_patterns b/corpus/support/token_patterns index de64fb2a..e51e5e72 100644 --- a/corpus/support/token_patterns +++ b/corpus/support/token_patterns @@ -1,5 +1,6 @@  /^(al|el|ul|e)\-[a-z]+$/  /^((а|А)(ль|ш)|уль)-\p{Cyrillic}+$/ +/^(юл)-\p{Cyrillic}+$/  /^\p{Cyrillic}\.\p{Cyrillic}\.$/  /^(\d|\d\d|\d\d\d)\.$/ | 
