futokb/dictionaries/sample.xml

<!-- This is a sample wordlist that can be converted to a binary dictionary
     for use by the Latin IME.
     The format of the word list is a flat list of word entries.
     Each entry has a frequency between 255 and 0.
     Highest frequency words get more weight in the prediction algorithm. As a
     special case, a weight of 0 is taken to mean profanity - words that should
     not be considered a typo, but that should never be suggested explicitly.
     You can capitalize words that must always be capitalized, such as "January".
     You can have a capitalized and a non-capitalized word as separate entries,
     such as "robin" and "Robin".
-->
<wordlist>
  <w f="255">this</w>
  <w f="255">is</w>
  <w f="128">sample</w>
  <w f="1">wordlist</w>
</wordlist>