From 97f083fc2c231ec5927fed67bca3f704531e7333 Mon Sep 17 00:00:00 2001
From: Joshua Clayton <joshua.clayton@gmail.com>
Date: Sat, 14 May 2016 08:04:35 -0400
Subject: [PATCH] Use regex in ag for simple words

Why?
====

ag supports using regular expressions for searches; however, the -Q
flag, which was previously always used, resulted in literal search
results.

By searching literal matches, it would potentially return too many
results. For example, with a `me` method in a controller, it'd match
words like `awesome` or `method`.

This introduces a check where, if the token being searched is only
composed of word characters (`[A-Za-z0-9_]`), it'll switch over to use
regular expressions with ag and surround the token with non-word matches
on either end. The goal here is to reduce false-positives in matches.
---
 src/Unused/TermSearch.hs               |  3 ++-
 src/Unused/TermSearch/Internal.hs      | 15 +++++++++++++++
 test/Unused/TermSearch/InternalSpec.hs | 22 ++++++++++++++++++++++
 unused.cabal                           |  2 ++
 4 files changed, 41 insertions(+), 1 deletion(-)
 create mode 100644 src/Unused/TermSearch/Internal.hs
 create mode 100644 test/Unused/TermSearch/InternalSpec.hs

diff --git a/src/Unused/TermSearch.hs b/src/Unused/TermSearch.hs
index 2e85119..a5a5b79 100644
--- a/src/Unused/TermSearch.hs
+++ b/src/Unused/TermSearch.hs
@@ -3,6 +3,7 @@ module Unused.TermSearch
     ) where
 
 import System.Process
+import Unused.TermSearch.Internal (commandLineOptions)
 
 search :: String -> IO [String]
 search t = do
@@ -19,5 +20,5 @@ linesMap f =
 
 ag :: String -> IO String
 ag t = do
-  (_, results, _) <- readProcessWithExitCode "ag" [t, ".", "-c", "-Q", "--ackmate"] ""
+  (_, results, _) <- readProcessWithExitCode "ag" (commandLineOptions t) ""
   return results
diff --git a/src/Unused/TermSearch/Internal.hs b/src/Unused/TermSearch/Internal.hs
new file mode 100644
index 0000000..60a5844
--- /dev/null
+++ b/src/Unused/TermSearch/Internal.hs
@@ -0,0 +1,15 @@
+module Unused.TermSearch.Internal
+    ( commandLineOptions
+    ) where
+
+import Unused.Regex
+
+commandLineOptions :: String -> [String]
+commandLineOptions t =
+    case regexSafeTerm t of
+        True -> ["\\W" ++ t ++ "\\W", ".", "-c", "--ackmate"]
+        False -> [t, ".", "-c", "-Q", "--ackmate"]
+
+regexSafeTerm :: String -> Bool
+regexSafeTerm =
+    matchRegex "^[[:word:]]+$"
diff --git a/test/Unused/TermSearch/InternalSpec.hs b/test/Unused/TermSearch/InternalSpec.hs
new file mode 100644
index 0000000..83ffb8a
--- /dev/null
+++ b/test/Unused/TermSearch/InternalSpec.hs
@@ -0,0 +1,22 @@
+module Unused.TermSearch.InternalSpec
+    ( main
+    , spec
+    ) where
+
+import Test.Hspec
+import Unused.TermSearch.Internal
+
+main :: IO ()
+main = hspec spec
+
+spec :: Spec
+spec = parallel $
+    describe "commandLineOptions" $ do
+        it "does not use regular expressions when the term contains non-word characters" $ do
+            commandLineOptions "can_do_things?" `shouldBe` ["can_do_things?", ".", "-c", "-Q", "--ackmate"]
+            commandLineOptions "no_way!" `shouldBe` ["no_way!", ".", "-c", "-Q", "--ackmate"]
+            commandLineOptions "[]=" `shouldBe` ["[]=", ".", "-c", "-Q", "--ackmate"]
+            commandLineOptions "window.globalOverride" `shouldBe` ["window.globalOverride", ".", "-c", "-Q", "--ackmate"]
+
+        it "uses regular expression match with surrounding non-word matches for accuracy" $
+            commandLineOptions "awesome_method" `shouldBe` ["\\Wawesome_method\\W", ".", "-c", "--ackmate"]
diff --git a/unused.cabal b/unused.cabal
index 02e33b5..64c6b85 100644
--- a/unused.cabal
+++ b/unused.cabal
@@ -16,6 +16,7 @@ cabal-version:       >=1.10
 library
   hs-source-dirs:      src
   exposed-modules:     Unused.TermSearch
+                     , Unused.TermSearch.Internal
                      , Unused.Parser
                      , Unused.Parser.Internal
                      , Unused.Types
@@ -71,6 +72,7 @@ test-suite unused-test
                      , Unused.TypesSpec
                      , Unused.LikelihoodCalculatorSpec
                      , Unused.Grouping.InternalSpec
+                     , Unused.TermSearch.InternalSpec
   ghc-options:         -threaded -rtsopts -with-rtsopts=-N -Wall -Werror
   default-language:    Haskell2010