Merge branch 'release/0.1.4'

.bin/build

@@ -1,4 +1,4 @@
-resolver="lts-13.2"
+resolver="lts-13.6"
 ghcv="8.6.3"
 
 branch=$(git rev-parse --abbrev-ref HEAD)

README.md

@@ -12,6 +12,16 @@ Currently only supports `http://` and `https://` prefixed URLs
 
 [Binaries for Mac and Linux are available](https://github.com/smallhadroncollider/brok/releases). Add the binary to a directory in your path (such as `/usr/local/bin`).
 
+### Cabal
+
+If you have `cabal` installed:
+
+```bash
+cabal install brok
+```
+
+Make sure you run `cabal update` if you haven't run it recently.
+
 ### Building
 
 **Requirements**: [Stack](https://docs.haskellstack.org/en/stable/README/)

package.yaml

@@ -1,5 +1,5 @@
 name:                brok
-version:             0.1.3.0
+version:             0.1.4.0
 github:              "smallhadroncollider/brok"
 license:             BSD3
 author:              "Small Hadron Collider"
@@ -12,7 +12,7 @@ extra-source-files:
 
 # Metadata used when publishing your package
 synopsis:            Finds broken links in text files
-# category:            Web
+category:            Command Line Tools
 
 # To avoid duplicated efforts in documentation and dealing with the
 # complications of embedding Haddock markup inside cabal files, it is

src/Brok/Parser/Attoparsec.hs

@@ -8,19 +8,22 @@ import ClassyPrelude
 import Data.Attoparsec.Text
 
 lexeme :: Parser a -> Parser a
-lexeme p = many' space *> p <* many' space
+lexeme p = skipSpace *> p <* skipSpace
 
 tchar :: Char -> Parser Text
 tchar ch = singleton <$> char ch
 
 chopt :: Char -> Parser Text
 chopt ch = option "" (tchar ch)
 
+manyChars :: Parser Char -> Parser Text
+manyChars p = pack <$> many1 p
+
 concat3 :: (Monoid a) => a -> a -> a -> a
 concat3 t1 t2 t3 = concat [t1, t2, t3]
 
-concat4 :: (Monoid a) => a -> a -> a -> a -> a
-concat4 t1 t2 t3 t4 = concat [t1, t2, t3, t4]
+concat5 :: (Monoid a) => a -> a -> a -> a -> a -> a
+concat5 t1 t2 t3 t4 t5 = concat [t1, t2, t3, t4, t5]
 
 surround :: Char -> Char -> Parser Text -> Parser Text
 surround open close parser = concat3 <$> tchar open <*> parser <*> tchar close

src/Brok/Parser/DB.hs

@@ -10,17 +10,10 @@ import ClassyPrelude
 import Data.Attoparsec.Text
 
 import Brok.Parser.Links (url)
-import Brok.Types.Link
+import Brok.Types.Link   (URL)
 
 line :: Parser (URL, Integer)
-line = do
-    lnk <- url
-    _ <- char ' '
-    int <- many1 digit
-    _ <- char '\n'
-    case readMay int :: Maybe Integer of
-        Just i  -> return (lnk, i)
-        Nothing -> fail "Unable to parse timestamp"
+line = (,) <$> (url <* char ' ') <*> (decimal <* endOfLine)
 
 entries :: Parser [(URL, Integer)]
 entries = many1 line

src/Brok/Parser/Links.hs

@@ -16,19 +16,30 @@ import Brok.Types.Link        (URL)
 
 type Token = Maybe URL
 
+preQueryChars :: String
+preQueryChars = "-._~:/#%@"
+
+queryBodyChars :: String
+queryBodyChars = "-._~:/#%@!$&*+,;="
+
+chars :: String -> Parser Char
+chars chrs = digit <|> letter <|> choice (char <$> chrs)
+
 -- parentheses
 parens :: Parser Text -> Parser Text
 parens parser = surround '(' ')' parser <|> surround '[' ']' parser
 
 -- urls
-urlChar :: Parser Char
-urlChar = digit <|> letter <|> choice (char <$> "-._~:/?#%@!$&*+,;=")
+part :: String -> Parser Text
+part str = concat <$> many' (parens (part str) <|> manyChars (chars str))
 
-urlChars :: Parser Text
-urlChars = concat <$> many1 (parens urlChars <|> (pack <$> many1 urlChar))
+query :: Parser Text
+query = (++) <$> string "?" <*> part queryBodyChars
 
 url :: Parser Text
-url = concat4 <$> string "http" <*> chopt 's' <*> string "://" <*> urlChars
+url =
+    concat5 <$> string "http" <*> chopt 's' <*> string "://" <*> part preQueryChars <*>
+    option "" query
 
 noise :: Parser Token
 noise = anyChar >> return Nothing

src/Brok/Parser/Options.hs

@@ -38,7 +38,7 @@ ignoreP :: Parser Option
 ignoreP = lexeme $ Ignore <$> (string "--ignore" *> char '\n' *> many1 urlP)
 
 fileP :: Parser Text
-fileP = lexeme $ pack <$> many1 (notChar '\n')
+fileP = lexeme $ manyChars (notChar '\n')
 
 optsToConfig :: [Option] -> Config
 optsToConfig = foldl' convert defaultConfig

stack.yaml

@@ -1,64 +1,4 @@
-# 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:
-# https://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
-#
-# The location of a snapshot can be provided as a file or url. Stack assumes
-# a snapshot provided as a file might change, whereas a url resource does not.
-#
-# resolver: ./custom-snapshot.yaml
-# resolver: https://example.com/snapshots/2018-01-01.yaml
-resolver: lts-13.2
-
-# 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
-#  subdirs:
-#  - auto-update
-#  - wai
+resolver: lts-13.6
+pvp-bounds: both
 packages:
 - .
-# Dependency packages to be pulled from upstream that are not in the resolver
-# using the same syntax as the packages field.
-# (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: ">=1.9"
-#
-# 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

test/Parser/DBTest.hs

@@ -42,12 +42,15 @@ test_db =
                         ])
                    (db content))
         , testCase
-              "big file"
+              "big file (last)"
               (assertEqual
                    "Gives back final url"
                    (Just
                         "https://developmentarc.gitbooks.io/react-indepth/content/life_cycle/the_life_cycle_recap.html")
                    (fst <$> (lastMay . fromRight [] $ db big)))
+        , testCase
+              "big file (length)"
+              (assertEqual "Gives back length" 142 (length $ fromRight [] (db big)))
         , testCase "invalid .brokdb" (assertEqual "Parse error" True (isLeft $ db invalid))
         , testCase "parses empty" (assertEqual "Gives back empty array" (Right []) (db ""))
         ]

test/Parser/LinksTest.hs

@@ -41,6 +41,15 @@ test_parser =
                          "Gives back google.com"
                          (Right ["https://google.com"])
                          (links "https://google.com"))
+              , testCase
+                    "just long link"
+                    (assertEqual
+                         "Gives back full URL"
+                         (Right
+                              [ "https://developmentarc.gitbooks.io/react-indepth/content/life_cycle/the_life_cycle_recap.html"
+                              ])
+                         (links
+                              "https://developmentarc.gitbooks.io/react-indepth/content/life_cycle/the_life_cycle_recap.html"))
               , testCase
                     "http link with surrounding text"
                     (assertEqual
@@ -61,6 +70,13 @@ test_parser =
                          (links "[A link](http://google.com)"))
               , testCase
                     "link with brackets"
+                    (assertEqual
+                         "Gives back google.com"
+                         (Right ["https://en.wikipedia.org/wiki/Word_(computer_architecture)"])
+                         (links
+                              "[A link](https://en.wikipedia.org/wiki/Word_(computer_architecture))"))
+              , testCase
+                    "link with brackets in query"
                     (assertEqual
                          "Gives back google.com"
                          (Right ["http://google.com?q=(fish)"])
@@ -91,6 +107,12 @@ test_parser =
                          "Gives back google.com"
                          (Right ["http://google.com?q=fish"])
                          (links "'http://google.com?q=fish'"))
+              , testCase
+                    "link with comma on end"
+                    (assertEqual
+                         "Gives back google.com"
+                         (Right ["http://google.com"])
+                         (links "testing http://google.com, here"))
               ]
         , testGroup
               "multiple links"