wordchoice 0.1.0.0 → 0.1.0.1

raw patch · 8 files changed

+63/−97 lines, 8 filesdep +criteriondep ~basenew-component:exe:wrd

Dependencies added: criterion

Dependency ranges changed: base

Files

• README.md +10/−16
• bench/Bench.hs +12/−0
• default.nix +1/−0
• src/Data/Text/WordCount.hs +6/−3
• src/Data/Text/WordCount/Exec.hs +1/−1
• src/Data/Text/WordCount/FileRead.hs +18/−15
• stack.yaml +0/−60
• wordchoice.cabal +15/−2

@@ -3,8 +3,7 @@  ## Usage -The following will print the 10 most used words *and* output a bar graph-showing the distribution of those 10 words.+The following will print the 10 most used words.  ```bash  $ wordchoice test/ulysses.txt -n10 -o distribution.html@@ -20,6 +19,13 @@  2391: with ``` +To print the 10 most used words *and* write a bar graph:++```bash+ $ wordchoice test/ulysses.txt -n10 -o distribution.html+```++ ## Installation  ### Manual@@ -33,7 +39,7 @@ Install [nix](https://nixos.org/nix/), then type:  ```bash-nix-env -i+nix-env -i wordchoice ```  to download the package for Mac or Linux.@@ -51,16 +57,4 @@  ### Build -To build this repo, simply type:--```bash- $ stack install-```--or--```bash- $ cabal new-build-```--in the `wordchoice/` directory.+This repo should build with cabal, stack, and nix-build.

@@ -0,0 +1,12 @@+module Main where++import Criterion.Main+import Data.Text.WordCount++main = do+    defaultMain [ env setupEnv $ \file ->+                  bgroup "ulysses all"+                      [ bench "226" $ whnf (fun 10000000) file ] ]+    where fun      = topN+          setupEnv = processFile "test/ulysses.txt"+

@@ -14,5 +14,6 @@   executableHaskellDepends = [ base ];   testHaskellDepends = [ base ];   homepage = "https://github.com/githubuser/wordchoice#readme";+  description = "Get word counts and distributions";   license = stdenv.lib.licenses.bsd3; }

@@ -6,6 +6,8 @@     -- * For making graphs     , makeFile     , makeDistribution+    -- * File processing with pandoc+    , processFile     -- * Low level-ish     , buildFreq     ) where@@ -13,7 +15,7 @@ import qualified Data.Map.Lazy as M import Data.Map.Lens import Control.Lens hiding (argument)-import qualified Data.Text.Lazy as TL+import qualified Data.Text as TL -- .Lazy as TL import Data.Tuple import Data.Monoid import Data.List@@ -21,6 +23,7 @@ import Graphics.Rendering.Chart.Easy hiding (argument) import Graphics.Rendering.Chart.Backend.Diagrams import Data.Char+import Data.Text.WordCount.FileRead  -- | Return top n words and their frequencies --@@ -66,5 +69,5 @@     layout_y_axis . laxis_override .= axisGridHide     layout_left_axis_visibility . axis_show_ticks .= False     plot $ fmap plotBars $ liftEC $ do-        plot_bars_values .= [ (x,[y]) | (x,y) <- values ]-        plot_bars_item_styles .= [ (fillStyle, Nothing) ]+        plot_bars_values .= fmap (over _2 pure) values+        plot_bars_item_styles .= pure (fillStyle, Nothing)

@@ -1,7 +1,7 @@ module Data.Text.WordCount.Exec where      import Data.Monoid-import qualified Data.Text.Lazy.IO as TLIO+import qualified Data.Text.IO as TLIO -- .Lazy.IO as TLIO import Paths_wordchoice import Options.Applicative import Data.Maybe

@@ -3,26 +3,29 @@  import Text.Pandoc import Filesystem.Path.CurrentOS as F-import qualified Data.Text.Lazy as TL-import qualified Data.Text.Lazy.IO as TLIO+import qualified Data.Text as T+import qualified Data.Text.IO as TIO import qualified Data.ByteString.Lazy as BSL  eitherError = either (error . show) id  -- | Process a file given its filename. Return text only, discarding superflouous material.-processFile :: String -> IO TL.Text-processFile filepath = case (extension . decodeString $ filepath) of-    (Just "md") -> TL.pack . writePlain def . filterCode . eitherError . readMarkdown def . TL.unpack <$> TLIO.readFile filepath-    (Just "dbk") -> TL.pack . writePlain def . filterCode . eitherError . readDocBook def . TL.unpack <$> TLIO.readFile filepath-    (Just "docx") -> TL.pack . writePlain def . filterCode . fst . eitherError . readDocx def <$> BSL.readFile filepath-    (Just "epub") -> TL.pack . writePlain def . filterCode . fst . eitherError . readEPUB def <$> BSL.readFile filepath-    (Just "html") -> TL.pack . writePlain def . filterCode . eitherError . readHtml def . TL.unpack <$> TLIO.readFile filepath-    (Just "tex") -> TL.pack . writePlain def . filterCode . eitherError . readLaTeX def . TL.unpack <$> TLIO.readFile filepath-    (Just "xml") -> TL.pack . writePlain def . filterCode . eitherError . readOPML def . TL.unpack <$> TLIO.readFile filepath-    (Just "odt") -> TL.pack . writePlain def . filterCode . fst . eitherError . readOdt def <$> BSL.readFile filepath-    (Just "rst") -> TL.pack . writePlain def . filterCode . eitherError . readRST def . TL.unpack <$> TLIO.readFile filepath-    (Just "textile") -> TL.pack . writePlain def . filterCode . eitherError . readTextile def . TL.unpack <$> TLIO.readFile filepath-    _ -> TLIO.readFile filepath+processFile :: String -> IO T.Text+processFile filepath = T.filter goodChar <$> case (extension . decodeString $ filepath) of+    (Just "md") -> T.pack . writePlain def . filterCode . eitherError . readMarkdown def . T.unpack <$> TIO.readFile filepath+    (Just "dbk") -> T.pack . writePlain def . filterCode . eitherError . readDocBook def . T.unpack <$> TIO.readFile filepath+    (Just "docx") -> T.pack . writePlain def . filterCode . fst . eitherError . readDocx def <$> BSL.readFile filepath+    (Just "epub") -> T.pack . writePlain def . filterCode . fst . eitherError . readEPUB def <$> BSL.readFile filepath+    (Just "html") -> T.pack . writePlain def . filterCode . eitherError . readHtml def . T.unpack <$> TIO.readFile filepath+    (Just "tex") -> T.pack . writePlain def . filterCode . eitherError . readLaTeX def . T.unpack <$> TIO.readFile filepath+    (Just "xml") -> T.pack . writePlain def . filterCode . eitherError . readOPML def . T.unpack <$> TIO.readFile filepath+    (Just "odt") -> T.pack . writePlain def . filterCode . fst . eitherError . readOdt def <$> BSL.readFile filepath+    (Just "rst") -> T.pack . writePlain def . filterCode . eitherError . readRST def . T.unpack <$> TIO.readFile filepath+    (Just "textile") -> T.pack . writePlain def . filterCode . eitherError . readTextile def . T.unpack <$> TIO.readFile filepath+    _ -> TIO.readFile filepath++goodChar :: Char -> Bool+goodChar = not . flip any (".,?_()![]{}*&$#" :: String) . (==)  -- | Filter out code and tables from the document filterCode :: Pandoc -> Pandoc

@@ -1,66 +1,6 @@-# 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-8.12--# 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

@@ -1,5 +1,5 @@ name:                wordchoice-version:             0.1.0.0+version:             0.1.0.1 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@@ -35,7 +35,7 @@   default-language:    Haskell2010   default-extensions:  OverloadedStrings -executable wordchoice+executable wrd   hs-source-dirs:      app   main-is:             Main.hs   ghc-options:         -threaded -rtsopts -with-rtsopts=-N@@ -51,6 +51,19 @@                      , wordchoice   ghc-options:         -threaded -rtsopts -with-rtsopts=-N   default-language:    Haskell2010++benchmark wordchoice-bench+  type:             exitcode-stdio-1.0+  hs-source-dirs:   bench+  main-is:          Bench.hs+  build-depends:    base+                  , criterion+                  , wordchoice+  if flag(llvm-fast)+    ghc-options:       -threaded -rtsopts -with-rtsopts=-N -fllvm -optlo-O3 -O3+  else+    ghc-options:       -threaded -rtsopts -with-rtsopts=-N -O3+  default-language: Haskell2010  source-repository head   type:     git