diff --git a/README.md b/README.md --- a/README.md +++ b/README.md @@ -1,5 +1,4 @@ # Wordchoice Command-Line Tool -[![Build Status](https://travis-ci.org/vmchale/wordchoice.svg?branch=master)](https://travis-ci.org/vmchale/wordchoice) ## Usage @@ -28,7 +27,8 @@ ## Installation -### Binary Release - - ### Cabal + +``` +cabal new-install wordchoice +``` diff --git a/Setup.hs b/Setup.hs deleted file mode 100644 --- a/Setup.hs +++ /dev/null @@ -1,2 +0,0 @@ -import Distribution.Simple -main = defaultMain diff --git a/app/Main.hs b/app/Main.hs --- a/app/Main.hs +++ b/app/Main.hs @@ -1,13 +1,11 @@ -module Main where +module Main (main) where import Control.Arrow ((&&&)) -import Control.Lens (over, _2) import Data.Binary (decode, encode) import qualified Data.ByteString as BS import qualified Data.ByteString.Lazy as BSL import qualified Data.IntMap as IM import Data.Maybe -import Data.Monoid import qualified Data.Text.IO as TIO import qualified Data.Text.Lazy as TL import Data.Text.WordCount @@ -60,12 +58,14 @@ wrapper :: ParserInfo Program wrapper = info (helper <*> versionInfo <*> program) (fullDesc - <> progDesc "Word choice is a command-line tool meant to help you improve your writing. Simply point it to a file containing text and it will list your most frequently used words and their frequencies." + <> progDesc "Word choice is a command-line meant to help you improve your writing. Simply point it to a file containing text and it will list your most frequently used words and their frequencies." <> header "Word choice command-line utility") -- | Actual executable main :: IO () main = execParser wrapper >>= pick + +-- TODO stream output nicely? -- | Run parsed record pick :: Program -> IO () diff --git a/bench/Bench.hs b/bench/Bench.hs --- a/bench/Bench.hs +++ b/bench/Bench.hs @@ -1,10 +1,11 @@ -module Main where +module Main (main) where import Criterion.Main import Data.Text.Lazy (fromStrict) import Data.Text.WordCount import Text.Pandoc +main :: IO () main = do defaultMain [ env ulysses $ \file -> bgroup "ulysses all" @@ -13,5 +14,5 @@ bgroup "beowulf all" [ bench "226" $ nf (fun 10000000) file ] ] where fun n = topN n . fromStrict - ulysses = runIOorExplode $ processFile "test/ulysses.txt" - beowulf = runIOorExplode $ processFile "test/beowulf.txt" + ulysses = runIOorExplode $ processFile "test/data/ulysses.txt" + beowulf = runIOorExplode $ processFile "test/data/beowulf.txt" diff --git a/cabal.project.local b/cabal.project.local --- a/cabal.project.local +++ b/cabal.project.local @@ -1,2 +1,1 @@ -with-compiler: ghc-8.2.2 optimization: 2 diff --git a/src/Data/Text/WordCount.hs b/src/Data/Text/WordCount.hs --- a/src/Data/Text/WordCount.hs +++ b/src/Data/Text/WordCount.hs @@ -1,5 +1,6 @@ {-# LANGUAGE FlexibleContexts #-} +-- Have a look at: https://sparverius.github.io/tmplats-doc/docs/CountingWords module Data.Text.WordCount ( topN , displayWords @@ -24,8 +25,6 @@ import qualified Data.IntMap as IM import Data.List import qualified Data.Map.Lazy as M -import Data.Map.Lens -import Data.Monoid import Data.Ord import qualified Data.Text as T import qualified Data.Text.Lazy as TL @@ -72,16 +71,7 @@ order = sortBy (flip (comparing fst)) . fmap swap . M.toList count :: [TL.Text] -> M.Map TL.Text Int -count words = foldr ((.) . go) id words M.empty - where go word m = case m^.at word of - Nothing -> at word ?~ 1 $ m - _ -> ix word %~ (+1) $ m - -count' :: [TL.Text] -> M.Map TL.Text Int -count' = M.fromListWith (+) . (`zip` repeat 1) - -count'' :: [TL.Text] -> [(TL.Text, Int)] -count'' = fmap (head &&& length) . group . sort +count = M.fromListWith (+) . (`zip` repeat 1) -- | Make a bar graph from the word frequencies -- @@ -90,11 +80,11 @@ -- makeFile [(4,"it"),(3,"why")] "out.html" -- @ makeFile :: [(Int,TL.Text)] -> FilePath -> IO () -makeFile points out = toFile def out (makeDistribution points) +makeFile ps out = toFile def out (makeDistribution ps) -makeDistribution points = do - let values = addIndexes (fmap fst points) - let alabels = fmap (TL.unpack . snd) points +makeDistribution ps = do + let values = addIndexes (fst <$> ps) + let alabels = fmap (TL.unpack . snd) ps let fillStyle = solidFillStyle (opaque lightblue) layout_title .= "Word Frequencies" layout_x_axis . laxis_generate .= autoIndexAxis alabels diff --git a/stack.yaml b/stack.yaml deleted file mode 100644 --- a/stack.yaml +++ /dev/null @@ -1,16 +0,0 @@ -resolver: lts-9.10 -packages: -- '.' -extra-deps: -- cmark-gfm-0.1.3 -- composition-prelude-0.1.1.0 -- pandoc-2.0 -- hslua-0.9.2 -- doctemplates-0.2.1 -- check-gfm-0.1.3 -- pandoc-types-1.17.2 -- skylighting-0.4.2 -flags: - wordchoice: - llvm-fast: true -extra-package-dbs: [] diff --git a/wordchoice.cabal b/wordchoice.cabal --- a/wordchoice.cabal +++ b/wordchoice.cabal @@ -1,35 +1,34 @@ -cabal-version: >=1.10 -name: wordchoice -version: 0.1.2.7 -license: BSD3 -license-file: LICENSE -copyright: 2017,2018 Vanessa McHale -maintainer: vamchale@gmail.com -author: Vanessa McHale -synopsis: Get word counts and distributions +cabal-version: >=1.10 +name: wordchoice +version: 0.1.2.8 +license: BSD3 +license-file: LICENSE +copyright: 2017,2018 Vanessa McHale +maintainer: vamchale@gmail.com +author: Vanessa McHale +synopsis: Get word counts and distributions description: A command line tool to compute the word distribution from various types of document, converting to text with pandoc. -category: Web -build-type: Simple + +category: Web +build-type: Simple extra-source-files: README.md - stack.yaml cabal.project.local source-repository head - type: git + type: git location: https://hub.darcs.net/vmchale/wordchoice library - exposed-modules: - Data.Text.WordCount - hs-source-dirs: src - other-modules: - Data.Text.WordCount.FileRead - default-language: Haskell2010 + exposed-modules: Data.Text.WordCount + hs-source-dirs: src + other-modules: Data.Text.WordCount.FileRead + default-language: Haskell2010 default-extensions: OverloadedStrings + ghc-options: -Wall build-depends: - base >=4.8 && <5, + base >=4.11 && <5, pandoc >=2.0, containers -any, Glob -any, @@ -46,11 +45,11 @@ transformers -any executable wrd - main-is: Main.hs - hs-source-dirs: app - other-modules: - Paths_wordchoice + main-is: Main.hs + hs-source-dirs: app + other-modules: Paths_wordchoice default-language: Haskell2010 + ghc-options: -Wall build-depends: base -any, optparse-applicative -any, @@ -63,20 +62,21 @@ wordchoice -any test-suite wordchoice-test - type: exitcode-stdio-1.0 - main-is: Spec.hs - hs-source-dirs: test + type: exitcode-stdio-1.0 + main-is: Spec.hs + hs-source-dirs: test default-language: Haskell2010 - ghc-options: -threaded -rtsopts -with-rtsopts=-N + ghc-options: -threaded -rtsopts -with-rtsopts=-N -Wall build-depends: base -any, wordchoice -any benchmark wordchoice-bench - type: exitcode-stdio-1.0 - main-is: Bench.hs - hs-source-dirs: bench + type: exitcode-stdio-1.0 + main-is: Bench.hs + hs-source-dirs: bench default-language: Haskell2010 + ghc-options: -Wall build-depends: base -any, criterion -any,