hledger/hledger-lib/Hledger/Utils.hs

177 lines
5.5 KiB
Haskell
Raw Normal View History

{-|
Standard imports and utilities which are useful everywhere, or needed low
in the module hierarchy. This is the bottom of hledger's module graph.
-}
2011-05-28 08:11:44 +04:00
module Hledger.Utils (---- provide these frequently used modules - or not, for clearer api:
-- module Control.Monad,
-- module Data.List,
-- module Data.Maybe,
-- module Data.Time.Calendar,
-- module Data.Time.Clock,
-- module Data.Time.LocalTime,
-- module Data.Tree,
-- module Text.RegexPR,
-- module Test.HUnit,
-- module Text.Printf,
---- all of this one:
2011-08-08 05:34:00 +04:00
module Hledger.Utils,
2014-10-29 03:21:33 +03:00
module Hledger.Utils.Debug,
2015-08-19 23:47:26 +03:00
module Hledger.Utils.Parse,
module Hledger.Utils.Regex,
2015-08-19 23:47:26 +03:00
module Hledger.Utils.String,
lib: textification begins! account names The first of several conversions from String to (strict) Text, hopefully reducing space and time usage. This one shows a small improvement, with GHC 7.10.3 and text-1.2.2.1: hledger -f data/100x100x10.journal stats string: <<ghc: 39471064 bytes, 77 GCs, 198421/275048 avg/max bytes residency (3 samples), 2M in use, 0.000 INIT (0.001 elapsed), 0.015 MUT (0.020 elapsed), 0.010 GC (0.014 elapsed) :ghc>> text: <<ghc: 39268024 bytes, 77 GCs, 197018/270840 avg/max bytes residency (3 samples), 2M in use, 0.000 INIT (0.002 elapsed), 0.016 MUT (0.022 elapsed), 0.009 GC (0.011 elapsed) :ghc>> hledger -f data/1000x100x10.journal stats string: <<ghc: 318555920 bytes, 617 GCs, 2178997/7134472 avg/max bytes residency (7 samples), 16M in use, 0.000 INIT (0.001 elapsed), 0.129 MUT (0.136 elapsed), 0.067 GC (0.077 elapsed) :ghc>> text: <<ghc: 314248496 bytes, 612 GCs, 2074045/6617960 avg/max bytes residency (7 samples), 16M in use, 0.000 INIT (0.003 elapsed), 0.137 MUT (0.145 elapsed), 0.067 GC (0.079 elapsed) :ghc>> hledger -f data/10000x100x10.journal stats string: <<ghc: 3114763608 bytes, 6026 GCs, 18858950/75552024 avg/max bytes residency (11 samples), 201M in use, 0.000 INIT (0.000 elapsed), 1.331 MUT (1.372 elapsed), 0.699 GC (0.812 elapsed) :ghc>> text: <<ghc: 3071468920 bytes, 5968 GCs, 14120344/62951360 avg/max bytes residency (9 samples), 124M in use, 0.000 INIT (0.003 elapsed), 1.272 MUT (1.349 elapsed), 0.513 GC (0.578 elapsed) :ghc>> hledger -f data/100000x100x10.journal stats string: <<ghc: 31186579432 bytes, 60278 GCs, 135332581/740228992 avg/max bytes residency (13 samples), 1697M in use, 0.000 INIT (0.008 elapsed), 14.677 MUT (15.508 elapsed), 7.081 GC (8.074 elapsed) :ghc>> text: <<ghc: 30753427672 bytes, 59763 GCs, 117595958/666457240 avg/max bytes residency (14 samples), 1588M in use, 0.000 INIT (0.008 elapsed), 13.713 MUT (13.966 elapsed), 6.220 GC (7.108 elapsed) :ghc>>
2016-05-24 04:16:21 +03:00
module Hledger.Utils.Text,
2015-08-19 23:47:26 +03:00
module Hledger.Utils.Test,
module Hledger.Utils.Tree,
2014-10-29 03:21:33 +03:00
-- Debug.Trace.trace,
-- module Data.PPrint,
-- module Hledger.Utils.UTF8IOCompat
SystemString,fromSystemString,toSystemString,error',userError',
-- the rest need to be done in each module I think
2011-05-28 08:11:44 +04:00
)
where
2014-10-29 03:21:33 +03:00
import Control.Monad (liftM)
2015-08-19 23:47:26 +03:00
-- import Data.Char
-- import Data.List
-- import Data.Maybe
-- import Data.PPrint
lib: textification: parse stream 10% more allocation, but 35% lower maximum residency, and slightly quicker. hledger -f data/100x100x10.journal stats <<ghc: 39327768 bytes, 77 GCs, 196834/269496 avg/max bytes residency (3 samples), 2M in use, 0.000 INIT (0.010 elapsed), 0.020 MUT (0.092 elapsed), 0.014 GC (0.119 elapsed) :ghc>> <<ghc: 42842136 bytes, 84 GCs, 194010/270912 avg/max bytes residency (3 samples), 2M in use, 0.000 INIT (0.009 elapsed), 0.016 MUT (0.029 elapsed), 0.012 GC (0.120 elapsed) :ghc>> hledger -f data/1000x1000x10.journal stats <<ghc: 314291440 bytes, 612 GCs, 2070776/6628048 avg/max bytes residency (7 samples), 16M in use, 0.000 INIT (0.000 elapsed), 0.128 MUT (0.144 elapsed), 0.059 GC (0.070 elapsed) :ghc>> <<ghc: 349558872 bytes, 681 GCs, 1397597/4106384 avg/max bytes residency (7 samples), 11M in use, 0.000 INIT (0.004 elapsed), 0.124 MUT (0.133 elapsed), 0.047 GC (0.053 elapsed) :ghc>> hledger -f data/10000x1000x10.journal stats <<ghc: 3070026824 bytes, 5973 GCs, 12698030/62951784 avg/max bytes residency (10 samples), 124M in use, 0.000 INIT (0.002 elapsed), 1.268 MUT (1.354 elapsed), 0.514 GC (0.587 elapsed) :ghc>> <<ghc: 3424013128 bytes, 6658 GCs, 11405501/41071624 avg/max bytes residency (11 samples), 111M in use, 0.000 INIT (0.001 elapsed), 1.343 MUT (1.406 elapsed), 0.511 GC (0.573 elapsed) :ghc>> hledger -f data/100000x1000x10.journal stats <<ghc: 30753387392 bytes, 59811 GCs, 117615462/666703600 avg/max bytes residency (14 samples), 1588M in use, 0.000 INIT (0.000 elapsed), 12.068 MUT (12.238 elapsed), 6.015 GC (7.190 elapsed) :ghc>> <<ghc: 34306530696 bytes, 66727 GCs, 76806196/414629312 avg/max bytes residency (14 samples), 1009M in use, 0.000 INIT (0.010 elapsed), 14.357 MUT (16.370 elapsed), 5.298 GC (6.534 elapsed) :ghc>>
2016-05-25 01:58:23 +03:00
import Data.Text (Text)
import qualified Data.Text.IO as T
2008-11-22 15:18:19 +03:00
import Data.Time.Clock
import Data.Time.LocalTime
lib: textification begins! account names The first of several conversions from String to (strict) Text, hopefully reducing space and time usage. This one shows a small improvement, with GHC 7.10.3 and text-1.2.2.1: hledger -f data/100x100x10.journal stats string: <<ghc: 39471064 bytes, 77 GCs, 198421/275048 avg/max bytes residency (3 samples), 2M in use, 0.000 INIT (0.001 elapsed), 0.015 MUT (0.020 elapsed), 0.010 GC (0.014 elapsed) :ghc>> text: <<ghc: 39268024 bytes, 77 GCs, 197018/270840 avg/max bytes residency (3 samples), 2M in use, 0.000 INIT (0.002 elapsed), 0.016 MUT (0.022 elapsed), 0.009 GC (0.011 elapsed) :ghc>> hledger -f data/1000x100x10.journal stats string: <<ghc: 318555920 bytes, 617 GCs, 2178997/7134472 avg/max bytes residency (7 samples), 16M in use, 0.000 INIT (0.001 elapsed), 0.129 MUT (0.136 elapsed), 0.067 GC (0.077 elapsed) :ghc>> text: <<ghc: 314248496 bytes, 612 GCs, 2074045/6617960 avg/max bytes residency (7 samples), 16M in use, 0.000 INIT (0.003 elapsed), 0.137 MUT (0.145 elapsed), 0.067 GC (0.079 elapsed) :ghc>> hledger -f data/10000x100x10.journal stats string: <<ghc: 3114763608 bytes, 6026 GCs, 18858950/75552024 avg/max bytes residency (11 samples), 201M in use, 0.000 INIT (0.000 elapsed), 1.331 MUT (1.372 elapsed), 0.699 GC (0.812 elapsed) :ghc>> text: <<ghc: 3071468920 bytes, 5968 GCs, 14120344/62951360 avg/max bytes residency (9 samples), 124M in use, 0.000 INIT (0.003 elapsed), 1.272 MUT (1.349 elapsed), 0.513 GC (0.578 elapsed) :ghc>> hledger -f data/100000x100x10.journal stats string: <<ghc: 31186579432 bytes, 60278 GCs, 135332581/740228992 avg/max bytes residency (13 samples), 1697M in use, 0.000 INIT (0.008 elapsed), 14.677 MUT (15.508 elapsed), 7.081 GC (8.074 elapsed) :ghc>> text: <<ghc: 30753427672 bytes, 59763 GCs, 117595958/666457240 avg/max bytes residency (14 samples), 1588M in use, 0.000 INIT (0.008 elapsed), 13.713 MUT (13.966 elapsed), 6.220 GC (7.108 elapsed) :ghc>>
2016-05-24 04:16:21 +03:00
-- import Data.Text (Text)
-- import qualified Data.Text as T
import System.Directory (getHomeDirectory)
import System.FilePath((</>), isRelative)
import System.IO
2015-08-19 23:47:26 +03:00
-- import Text.Printf
2011-05-28 08:11:44 +04:00
-- import qualified Data.Map as Map
2014-10-29 03:21:33 +03:00
import Hledger.Utils.Debug
2015-08-19 23:47:26 +03:00
import Hledger.Utils.Parse
import Hledger.Utils.Regex
2015-08-19 23:47:26 +03:00
import Hledger.Utils.String
lib: textification begins! account names The first of several conversions from String to (strict) Text, hopefully reducing space and time usage. This one shows a small improvement, with GHC 7.10.3 and text-1.2.2.1: hledger -f data/100x100x10.journal stats string: <<ghc: 39471064 bytes, 77 GCs, 198421/275048 avg/max bytes residency (3 samples), 2M in use, 0.000 INIT (0.001 elapsed), 0.015 MUT (0.020 elapsed), 0.010 GC (0.014 elapsed) :ghc>> text: <<ghc: 39268024 bytes, 77 GCs, 197018/270840 avg/max bytes residency (3 samples), 2M in use, 0.000 INIT (0.002 elapsed), 0.016 MUT (0.022 elapsed), 0.009 GC (0.011 elapsed) :ghc>> hledger -f data/1000x100x10.journal stats string: <<ghc: 318555920 bytes, 617 GCs, 2178997/7134472 avg/max bytes residency (7 samples), 16M in use, 0.000 INIT (0.001 elapsed), 0.129 MUT (0.136 elapsed), 0.067 GC (0.077 elapsed) :ghc>> text: <<ghc: 314248496 bytes, 612 GCs, 2074045/6617960 avg/max bytes residency (7 samples), 16M in use, 0.000 INIT (0.003 elapsed), 0.137 MUT (0.145 elapsed), 0.067 GC (0.079 elapsed) :ghc>> hledger -f data/10000x100x10.journal stats string: <<ghc: 3114763608 bytes, 6026 GCs, 18858950/75552024 avg/max bytes residency (11 samples), 201M in use, 0.000 INIT (0.000 elapsed), 1.331 MUT (1.372 elapsed), 0.699 GC (0.812 elapsed) :ghc>> text: <<ghc: 3071468920 bytes, 5968 GCs, 14120344/62951360 avg/max bytes residency (9 samples), 124M in use, 0.000 INIT (0.003 elapsed), 1.272 MUT (1.349 elapsed), 0.513 GC (0.578 elapsed) :ghc>> hledger -f data/100000x100x10.journal stats string: <<ghc: 31186579432 bytes, 60278 GCs, 135332581/740228992 avg/max bytes residency (13 samples), 1697M in use, 0.000 INIT (0.008 elapsed), 14.677 MUT (15.508 elapsed), 7.081 GC (8.074 elapsed) :ghc>> text: <<ghc: 30753427672 bytes, 59763 GCs, 117595958/666457240 avg/max bytes residency (14 samples), 1588M in use, 0.000 INIT (0.008 elapsed), 13.713 MUT (13.966 elapsed), 6.220 GC (7.108 elapsed) :ghc>>
2016-05-24 04:16:21 +03:00
import Hledger.Utils.Text
2015-08-19 23:47:26 +03:00
import Hledger.Utils.Test
import Hledger.Utils.Tree
-- import Prelude hiding (readFile,writeFile,appendFile,getContents,putStr,putStrLn)
-- import Hledger.Utils.UTF8IOCompat (readFile,writeFile,appendFile,getContents,putStr,putStrLn)
import Hledger.Utils.UTF8IOCompat (SystemString,fromSystemString,toSystemString,error',userError')
2008-10-10 11:39:20 +04:00
2008-12-06 10:15:19 +03:00
2014-03-26 22:15:04 +04:00
-- tuples
first3 (x,_,_) = x
second3 (_,x,_) = x
third3 (_,_,x) = x
first4 (x,_,_,_) = x
second4 (_,x,_,_) = x
third4 (_,_,x,_) = x
fourth4 (_,_,_,x) = x
first5 (x,_,_,_,_) = x
second5 (_,x,_,_,_) = x
third5 (_,_,x,_,_) = x
fourth5 (_,_,_,x,_) = x
fifth5 (_,_,_,_,x) = x
2015-08-23 03:42:19 +03:00
first6 (x,_,_,_,_,_) = x
second6 (_,x,_,_,_,_) = x
third6 (_,_,x,_,_,_) = x
fourth6 (_,_,_,x,_,_) = x
fifth6 (_,_,_,_,x,_) = x
sixth6 (_,_,_,_,_,x) = x
2007-07-03 03:54:17 +04:00
-- lists
splitAtElement :: Eq a => a -> [a] -> [[a]]
splitAtElement x l =
case l of
[] -> []
e:es | e==x -> split es
es -> split es
where
split es = let (first,rest) = break (x==) es
in first : splitAtElement x rest
lib: textification begins! account names The first of several conversions from String to (strict) Text, hopefully reducing space and time usage. This one shows a small improvement, with GHC 7.10.3 and text-1.2.2.1: hledger -f data/100x100x10.journal stats string: <<ghc: 39471064 bytes, 77 GCs, 198421/275048 avg/max bytes residency (3 samples), 2M in use, 0.000 INIT (0.001 elapsed), 0.015 MUT (0.020 elapsed), 0.010 GC (0.014 elapsed) :ghc>> text: <<ghc: 39268024 bytes, 77 GCs, 197018/270840 avg/max bytes residency (3 samples), 2M in use, 0.000 INIT (0.002 elapsed), 0.016 MUT (0.022 elapsed), 0.009 GC (0.011 elapsed) :ghc>> hledger -f data/1000x100x10.journal stats string: <<ghc: 318555920 bytes, 617 GCs, 2178997/7134472 avg/max bytes residency (7 samples), 16M in use, 0.000 INIT (0.001 elapsed), 0.129 MUT (0.136 elapsed), 0.067 GC (0.077 elapsed) :ghc>> text: <<ghc: 314248496 bytes, 612 GCs, 2074045/6617960 avg/max bytes residency (7 samples), 16M in use, 0.000 INIT (0.003 elapsed), 0.137 MUT (0.145 elapsed), 0.067 GC (0.079 elapsed) :ghc>> hledger -f data/10000x100x10.journal stats string: <<ghc: 3114763608 bytes, 6026 GCs, 18858950/75552024 avg/max bytes residency (11 samples), 201M in use, 0.000 INIT (0.000 elapsed), 1.331 MUT (1.372 elapsed), 0.699 GC (0.812 elapsed) :ghc>> text: <<ghc: 3071468920 bytes, 5968 GCs, 14120344/62951360 avg/max bytes residency (9 samples), 124M in use, 0.000 INIT (0.003 elapsed), 1.272 MUT (1.349 elapsed), 0.513 GC (0.578 elapsed) :ghc>> hledger -f data/100000x100x10.journal stats string: <<ghc: 31186579432 bytes, 60278 GCs, 135332581/740228992 avg/max bytes residency (13 samples), 1697M in use, 0.000 INIT (0.008 elapsed), 14.677 MUT (15.508 elapsed), 7.081 GC (8.074 elapsed) :ghc>> text: <<ghc: 30753427672 bytes, 59763 GCs, 117595958/666457240 avg/max bytes residency (14 samples), 1588M in use, 0.000 INIT (0.008 elapsed), 13.713 MUT (13.966 elapsed), 6.220 GC (7.108 elapsed) :ghc>>
2016-05-24 04:16:21 +03:00
-- text
2009-01-25 09:47:05 +03:00
-- time
getCurrentLocalTime :: IO LocalTime
getCurrentLocalTime = do
t <- getCurrentTime
tz <- getCurrentTimeZone
return $ utcToLocalTime tz t
2016-10-21 21:47:07 +03:00
getCurrentZonedTime :: IO ZonedTime
getCurrentZonedTime = do
t <- getCurrentTime
tz <- getCurrentTimeZone
return $ utcToZonedTime tz t
-- misc
isLeft :: Either a b -> Bool
isLeft (Left _) = True
isLeft _ = False
isRight :: Either a b -> Bool
isRight = not . isLeft
-- | Apply a function the specified number of times. Possibly uses O(n) stack ?
applyN :: Int -> (a -> a) -> a -> a
applyN n f = (!! n) . iterate f
2016-12-29 22:23:22 +03:00
-- from protolude, compare
-- applyN :: Int -> (a -> a) -> a -> a
-- applyN n f = X.foldr (.) identity (X.replicate n f)
-- | Convert a possibly relative, possibly tilde-containing file path to an absolute one,
-- given the current directory. ~username is not supported. Leave "-" unchanged.
-- Can raise an error.
expandPath :: FilePath -> FilePath -> IO FilePath -- general type sig for use in reader parsers
expandPath _ "-" = return "-"
expandPath curdir p = (if isRelative p then (curdir </>) else id) `liftM` expandPath' p
where
expandPath' ('~':'/':p) = (</> p) <$> getHomeDirectory
expandPath' ('~':'\\':p) = (</> p) <$> getHomeDirectory
expandPath' ('~':_) = ioError $ userError "~USERNAME in paths is not supported"
expandPath' p = return p
firstJust ms = case dropWhile (==Nothing) ms of
[] -> Nothing
(md:_) -> md
lib: textification: parse stream 10% more allocation, but 35% lower maximum residency, and slightly quicker. hledger -f data/100x100x10.journal stats <<ghc: 39327768 bytes, 77 GCs, 196834/269496 avg/max bytes residency (3 samples), 2M in use, 0.000 INIT (0.010 elapsed), 0.020 MUT (0.092 elapsed), 0.014 GC (0.119 elapsed) :ghc>> <<ghc: 42842136 bytes, 84 GCs, 194010/270912 avg/max bytes residency (3 samples), 2M in use, 0.000 INIT (0.009 elapsed), 0.016 MUT (0.029 elapsed), 0.012 GC (0.120 elapsed) :ghc>> hledger -f data/1000x1000x10.journal stats <<ghc: 314291440 bytes, 612 GCs, 2070776/6628048 avg/max bytes residency (7 samples), 16M in use, 0.000 INIT (0.000 elapsed), 0.128 MUT (0.144 elapsed), 0.059 GC (0.070 elapsed) :ghc>> <<ghc: 349558872 bytes, 681 GCs, 1397597/4106384 avg/max bytes residency (7 samples), 11M in use, 0.000 INIT (0.004 elapsed), 0.124 MUT (0.133 elapsed), 0.047 GC (0.053 elapsed) :ghc>> hledger -f data/10000x1000x10.journal stats <<ghc: 3070026824 bytes, 5973 GCs, 12698030/62951784 avg/max bytes residency (10 samples), 124M in use, 0.000 INIT (0.002 elapsed), 1.268 MUT (1.354 elapsed), 0.514 GC (0.587 elapsed) :ghc>> <<ghc: 3424013128 bytes, 6658 GCs, 11405501/41071624 avg/max bytes residency (11 samples), 111M in use, 0.000 INIT (0.001 elapsed), 1.343 MUT (1.406 elapsed), 0.511 GC (0.573 elapsed) :ghc>> hledger -f data/100000x1000x10.journal stats <<ghc: 30753387392 bytes, 59811 GCs, 117615462/666703600 avg/max bytes residency (14 samples), 1588M in use, 0.000 INIT (0.000 elapsed), 12.068 MUT (12.238 elapsed), 6.015 GC (7.190 elapsed) :ghc>> <<ghc: 34306530696 bytes, 66727 GCs, 76806196/414629312 avg/max bytes residency (14 samples), 1009M in use, 0.000 INIT (0.010 elapsed), 14.357 MUT (16.370 elapsed), 5.298 GC (6.534 elapsed) :ghc>>
2016-05-25 01:58:23 +03:00
-- | Read a file in universal newline mode, handling any of the usual line ending conventions.
readFile' :: FilePath -> IO Text
readFile' name = do
h <- openFile name ReadMode
hSetNewlineMode h universalNewlineMode
T.hGetContents h
lib: textification: parse stream 10% more allocation, but 35% lower maximum residency, and slightly quicker. hledger -f data/100x100x10.journal stats <<ghc: 39327768 bytes, 77 GCs, 196834/269496 avg/max bytes residency (3 samples), 2M in use, 0.000 INIT (0.010 elapsed), 0.020 MUT (0.092 elapsed), 0.014 GC (0.119 elapsed) :ghc>> <<ghc: 42842136 bytes, 84 GCs, 194010/270912 avg/max bytes residency (3 samples), 2M in use, 0.000 INIT (0.009 elapsed), 0.016 MUT (0.029 elapsed), 0.012 GC (0.120 elapsed) :ghc>> hledger -f data/1000x1000x10.journal stats <<ghc: 314291440 bytes, 612 GCs, 2070776/6628048 avg/max bytes residency (7 samples), 16M in use, 0.000 INIT (0.000 elapsed), 0.128 MUT (0.144 elapsed), 0.059 GC (0.070 elapsed) :ghc>> <<ghc: 349558872 bytes, 681 GCs, 1397597/4106384 avg/max bytes residency (7 samples), 11M in use, 0.000 INIT (0.004 elapsed), 0.124 MUT (0.133 elapsed), 0.047 GC (0.053 elapsed) :ghc>> hledger -f data/10000x1000x10.journal stats <<ghc: 3070026824 bytes, 5973 GCs, 12698030/62951784 avg/max bytes residency (10 samples), 124M in use, 0.000 INIT (0.002 elapsed), 1.268 MUT (1.354 elapsed), 0.514 GC (0.587 elapsed) :ghc>> <<ghc: 3424013128 bytes, 6658 GCs, 11405501/41071624 avg/max bytes residency (11 samples), 111M in use, 0.000 INIT (0.001 elapsed), 1.343 MUT (1.406 elapsed), 0.511 GC (0.573 elapsed) :ghc>> hledger -f data/100000x1000x10.journal stats <<ghc: 30753387392 bytes, 59811 GCs, 117615462/666703600 avg/max bytes residency (14 samples), 1588M in use, 0.000 INIT (0.000 elapsed), 12.068 MUT (12.238 elapsed), 6.015 GC (7.190 elapsed) :ghc>> <<ghc: 34306530696 bytes, 66727 GCs, 76806196/414629312 avg/max bytes residency (14 samples), 1009M in use, 0.000 INIT (0.010 elapsed), 14.357 MUT (16.370 elapsed), 5.298 GC (6.534 elapsed) :ghc>>
2016-05-25 01:58:23 +03:00
-- | Read a file in universal newline mode, handling any of the usual line ending conventions.
readFileAnyLineEnding :: FilePath -> IO Text
readFileAnyLineEnding path = do
h <- openFile path ReadMode
hSetNewlineMode h universalNewlineMode
T.hGetContents h
-- | Read the given file, or standard input if the path is "-", using
-- universal newline mode.
readFileOrStdinAnyLineEnding :: String -> IO Text
readFileOrStdinAnyLineEnding f = do
h <- fileHandle f
hSetNewlineMode h universalNewlineMode
T.hGetContents h
where
fileHandle "-" = return stdin
fileHandle f = openFile f ReadMode
-- | Total version of maximum, for integral types, giving 0 for an empty list.
maximum' :: Integral a => [a] -> a
maximum' [] = 0
maximum' xs = maximum xs