diff --git a/README.md b/README.md --- a/README.md +++ b/README.md @@ -25,6 +25,7 @@ $ wordchoice test/ulysses.txt -n10 -o distribution.html ``` + ## Installation ### Manual 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 @@ -16,7 +16,7 @@ import qualified Data.Map.Lazy as M import Data.Map.Lens import Control.Lens hiding (argument) -import qualified Data.Text as T +import qualified Data.Text as TL -- .Lazy as TL import Data.Tuple import Data.Monoid import Data.List @@ -25,7 +25,6 @@ import Graphics.Rendering.Chart.Backend.Diagrams import Data.Char import Data.Text.WordCount.FileRead -import Graphics.Rendering.Chart.State -- | Return top n words and their frequencies -- @@ -33,21 +32,21 @@ -- >>> topN 2 "hello hello goodbye it is time is it why why why it it" -- [(4,"it"),(3,"why")] -- @ -topN :: Int -> T.Text -> [(Int,T.Text)] +topN :: Int -> TL.Text -> [(Int,TL.Text)] topN n = take n . order . buildFreq -displayWords :: [(Int,T.Text)] -> T.Text +displayWords :: [(Int,TL.Text)] -> TL.Text displayWords [] = "" displayWords (pair:pairs) = display pair <> "\n" <> displayWords pairs - where display (n,str) = (T.pack . show) n <> ": " <> str + where display (n,str) = (TL.pack . show) n <> ": " <> str -buildFreq :: T.Text -> M.Map T.Text Int -buildFreq = count . T.words . T.map toLower +buildFreq :: TL.Text -> M.Map TL.Text Int +buildFreq = count . TL.words . TL.map toLower -order :: M.Map T.Text Int -> [(Int, T.Text)] +order :: M.Map TL.Text Int -> [(Int, TL.Text)] order = sortBy (flip (comparing fst)) . fmap swap . M.toList -count :: [T.Text] -> M.Map T.Text Int +count :: [TL.Text] -> M.Map TL.Text Int count words = foldr ((.) . wordFunction) id words M.empty where wordFunction word map = case map ^. at word of Nothing -> at word ?~ 1 $ map @@ -59,14 +58,12 @@ -- makeFile :: IO () -- makeFile [(4,"it"),(3,"why")] "out.html" -- @ -makeFile :: BarsPlotValue a => [(a, T.Text)] -> FilePath -> IO () +makeFile :: [(Int,TL.Text)] -> FilePath -> IO () makeFile points out = toFile def out (makeDistribution points) --- | Make a plot from values -makeDistribution :: BarsPlotValue a => [(a, T.Text)] -> EC (Layout PlotIndex a) () makeDistribution points = do let values = addIndexes (fmap fst points) - let alabels = fmap (T.unpack . snd) points + let alabels = fmap (TL.unpack . snd) points let fillStyle = solidFillStyle (opaque lightblue) layout_title .= "Word Frequencies" layout_x_axis . laxis_generate .= autoIndexAxis alabels diff --git a/src/Data/Text/WordCount/Exec.hs b/src/Data/Text/WordCount/Exec.hs --- a/src/Data/Text/WordCount/Exec.hs +++ b/src/Data/Text/WordCount/Exec.hs @@ -10,16 +10,17 @@ import Data.Text.WordCount.FileRead -- | Program datatype to be parsed -data Program = Program { file :: [FilePath] +data Program = Program { file :: FilePath , num :: Maybe Int , output :: Maybe FilePath } -- TODO add option for separators -- | Command line argument parser program :: Parser Program program = Program - <$> (many (argument str + <$> (argument str (metavar "FILEPATH" - <> help "Files to analyze together"))) + <> completer (bashCompleter "file -o plusdirs") + <> help "File to analyze")) <*> (optional (read <$> strOption (short 'n' <> long "number" diff --git a/src/Data/Text/WordCount/FileRead.hs b/src/Data/Text/WordCount/FileRead.hs --- a/src/Data/Text/WordCount/FileRead.hs +++ b/src/Data/Text/WordCount/FileRead.hs @@ -11,8 +11,10 @@ eitherError = either (error . show) id -- | Process files given a filename glob -globFile :: [String] -> IO T.Text -globFile files = fmap T.concat . sequence $ fmap processFile files +globFile :: String -> IO T.Text +globFile str = do + files <- glob str + fmap T.concat . sequence $ fmap processFile files -- | Process a file given a filename. Return text only, discarding superflouous material. processFile :: String -> IO T.Text diff --git a/stack.yaml b/stack.yaml --- a/stack.yaml +++ b/stack.yaml @@ -1,6 +1,66 @@ -resolver: lts-8.12 +# This file was automatically generated by 'stack init' +# +# Some commonly used options have been documented as comments in this file. +# For advanced use and comprehensive documentation of the format, please see: +# http://docs.haskellstack.org/en/stable/yaml_configuration/ + +# Resolver to choose a 'specific' stackage snapshot or a compiler version. +# A snapshot resolver dictates the compiler version and the set of packages +# to be used for project dependencies. For example: +# +# resolver: lts-3.5 +# resolver: nightly-2015-09-21 +# resolver: ghc-7.10.2 +# resolver: ghcjs-0.1.0_ghc-7.10.2 +# resolver: +# name: custom-snapshot +# location: "./custom-snapshot.yaml" +resolver: lts-8.18 + +# User packages to be built. +# Various formats can be used as shown in the example below. +# +# packages: +# - some-directory +# - https://example.com/foo/bar/baz-0.0.2.tar.gz +# - location: +# git: https://github.com/commercialhaskell/stack.git +# commit: e7b331f14bcffb8367cd58fbfc8b40ec7642100a +# - location: https://github.com/commercialhaskell/stack/commit/e7b331f14bcffb8367cd58fbfc8b40ec7642100a +# extra-dep: true +# subdirs: +# - auto-update +# - wai +# +# A package marked 'extra-dep: true' will only be built if demanded by a +# non-dependency (i.e. a user package), and its test suites and benchmarks +# will not be run. This is useful for tweaking upstream packages. packages: - '.' +# Dependency packages to be pulled from upstream that are not in the resolver +# (e.g., acme-missiles-0.3) extra-deps: [] + +# Override default flag values for local packages and extra-deps flags: {} + +# Extra package databases containing global packages extra-package-dbs: [] + +# Control whether we use the GHC we find on the path +# system-ghc: true +# +# Require a specific version of stack, using version ranges +# require-stack-version: -any # Default +# require-stack-version: ">=1.4" +# +# Override the architecture used by stack, especially useful on Windows +# arch: i386 +# arch: x86_64 +# +# Extra directories used by stack for building +# extra-include-dirs: [/path/to/dir] +# extra-lib-dirs: [/path/to/dir] +# +# Allow a newer minor version of GHC than the snapshot specifies +# compiler-check: newer-minor diff --git a/wordchoice.cabal b/wordchoice.cabal --- a/wordchoice.cabal +++ b/wordchoice.cabal @@ -1,73 +1,81 @@ -name: wordchoice -version: 0.1.0.4 -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. -homepage: https://github.com/githubuser/wordchoice#readme -license: BSD3 -license-file: LICENSE -author: Author name here -maintainer: example@example.com -copyright: 2017 Author name here -category: Web -build-type: Simple -extra-source-files: README.md - , stack.yaml - , default.nix - , release.nix -cabal-version: >=1.10 +name: wordchoice +version: 0.1.0.5 +cabal-version: >=1.10 +build-type: Simple +license: BSD3 +license-file: LICENSE +copyright: 2017 Author name here +maintainer: example@example.com +homepage: https://github.com/githubuser/wordchoice#readme +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 +author: Author name here +extra-source-files: + README.md + stack.yaml + default.nix + release.nix -Flag llvm-fast { - Description: Enable build with llvm backend - Default: False -} +source-repository head + type: git + location: https://github.com/githubuser/wordchoice +flag llvm-fast + description: + Enable build with llvm backend + default: False + library - hs-source-dirs: src - exposed-modules: Data.Text.WordCount - , Data.Text.WordCount.Exec - other-modules: Paths_wordchoice - , Data.Text.WordCount.FileRead - build-depends: base >= 4.7 && < 5 - , pandoc - , containers - , Glob - , text - , optparse-applicative - , Chart - , bytestring - , system-filepath - , Chart-diagrams - , lens - default-language: Haskell2010 - default-extensions: OverloadedStrings + exposed-modules: + Data.Text.WordCount + Data.Text.WordCount.Exec + build-depends: + base >=4.7 && <5, + pandoc >=1.19.2.1 && <1.20, + containers >=0.5.7.1 && <0.6, + Glob >=0.7.14 && <0.8, + text >=1.2.2.1 && <1.3, + optparse-applicative >=0.13.2.0 && <0.14, + Chart >=1.8.2 && <1.9, + bytestring >=0.10.8.1 && <0.11, + system-filepath >=0.4.13.4 && <0.5, + Chart-diagrams >=1.8.2 && <1.9, + lens >=4.15.1 && <4.16 + default-language: Haskell2010 + default-extensions: OverloadedStrings + hs-source-dirs: src + other-modules: + Paths_wordchoice + Data.Text.WordCount.FileRead executable wrd - hs-source-dirs: app - main-is: Main.hs - ghc-options: -threaded -rtsopts -with-rtsopts=-N - build-depends: base - , wordchoice - default-language: Haskell2010 + main-is: Main.hs + build-depends: + base >=4.9.1.0 && <4.10, + wordchoice >=0.1.0.5 && <0.2 + default-language: Haskell2010 + hs-source-dirs: app + ghc-options: -threaded -rtsopts -with-rtsopts=-N test-suite wordchoice-test - type: exitcode-stdio-1.0 - hs-source-dirs: test - main-is: Spec.hs - build-depends: base - , wordchoice - ghc-options: -threaded -rtsopts -with-rtsopts=-N - default-language: Haskell2010 + type: exitcode-stdio-1.0 + main-is: Spec.hs + build-depends: + base >=4.9.1.0 && <4.10, + wordchoice >=0.1.0.5 && <0.2 + default-language: Haskell2010 + hs-source-dirs: test + ghc-options: -threaded -rtsopts -with-rtsopts=-N benchmark wordchoice-bench - type: exitcode-stdio-1.0 - hs-source-dirs: bench - main-is: Bench.hs - build-depends: base - , criterion - , wordchoice - ghc-options: -threaded -rtsopts -with-rtsopts=-N -O3 - default-language: Haskell2010 - -source-repository head - type: git - location: https://github.com/githubuser/wordchoice + type: exitcode-stdio-1.0 + main-is: Bench.hs + build-depends: + base >=4.9.1.0 && <4.10, + criterion >=1.1.4.0 && <1.2, + wordchoice >=0.1.0.5 && <0.2 + default-language: Haskell2010 + hs-source-dirs: bench + ghc-options: -threaded -rtsopts -with-rtsopts=-N -O3