slaesvuo/hledger
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

add: note another algorithm

Browse Source
This commit is contained in:
Simon Michael 2015-08-28 17:57:16 -07:00
parent 9f2d59948e
commit dab12e2d10
1 changed files with 3 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
hledger/Hledger/Cli/Add.hs
View File

@ -400,8 +400,8 @@ transactionsSimilarTo j q desc =
-- | Return a similarity measure, from 0 to 1, for two transaction -- | Return a similarity measure, from 0 to 1, for two transaction
-- descriptions. This is like compareStrings, but first strips out -- descriptions. This is like compareStrings, but first strips out
-- numbers, which often appear in transaction descriptions without -- any numbers, to improve accuracy eg when there are bank transaction
-- being helpful for checking similarity. -- ids from imported data.
compareDescriptions :: String -> String -> Double compareDescriptions :: String -> String -> Double
compareDescriptions s t = compareStrings s' t' compareDescriptions s t = compareStrings s' t'
where s' = simplify s where s' = simplify s
@ -413,6 +413,7 @@ compareDescriptions s t = compareStrings s' t'
-- (http://www.catalysoft.com/articles/StrikeAMatch.html), later found -- (http://www.catalysoft.com/articles/StrikeAMatch.html), later found
-- to be https://en.wikipedia.org/wiki/S%C3%B8rensen%E2%80%93Dice_coefficient, -- to be https://en.wikipedia.org/wiki/S%C3%B8rensen%E2%80%93Dice_coefficient,
-- modified to handle short strings better. -- modified to handle short strings better.
-- Todo: check out http://nlp.fi.muni.cz/raslan/2008/raslan08.pdf#page=14 .
compareStrings :: String -> String -> Double compareStrings :: String -> String -> Double
compareStrings "" "" = 1 compareStrings "" "" = 1
compareStrings (_:[]) "" = 0 compareStrings (_:[]) "" = 0