From 33cd1ffbfe200188a4fc61fd5715e7aa29556d7f Mon Sep 17 00:00:00 2001
From: Joey Hess <joey@kitenet.net>
Date: Sun, 18 Sep 2011 20:41:51 -0400
Subject: [PATCH] make find show files meeting limits, even when not present

find: Rather than only showing files whose contents are present, when used
with --exclude --copies or --in, displays all files that match the
specified conditions.

Note that this is a behavior change for find --exclude! Old behavior
can be gotten with find --in . --exclude=...
---
 Command/Find.hs    |  9 ++++++---
 Limit.hs           |  5 +++++
 Utility/Matcher.hs | 10 +++++++++-
 debian/changelog   |  5 +++++
 doc/git-annex.mdwn |  5 ++++-
 5 files changed, 29 insertions(+), 5 deletions(-)

diff --git a/Command/Find.hs b/Command/Find.hs
index 51849f6b85..effb331840 100644
--- a/Command/Find.hs
+++ b/Command/Find.hs
@@ -7,11 +7,12 @@
 
 module Command.Find where
 
-import Control.Monad.State (liftIO)
+import Control.Monad.State
 
 import Command
 import Content
 import Utility.Conditional
+import Limit
 
 command :: [Command]
 command = [repoCommand "find" paramPaths seek "lists available files"]
@@ -19,8 +20,10 @@ command = [repoCommand "find" paramPaths seek "lists available files"]
 seek :: [CommandSeek]
 seek = [withFilesInGit start]
 
-{- Output a list of files. -}
 start :: FilePath -> CommandStart
 start file = isAnnexed file $ \(key, _) -> do
-	whenM (inAnnex key) $ liftIO $ putStrLn file
+	-- only files inAnnex are shown, unless the user has requested
+	-- others via a limit
+	whenM (liftM2 (||) (inAnnex key) limited) $
+		liftIO $ putStrLn file
 	stop
diff --git a/Limit.hs b/Limit.hs
index 4aeb8bafb4..51f3fc9505 100644
--- a/Limit.hs
+++ b/Limit.hs
@@ -10,6 +10,7 @@ module Limit where
 import Text.Regex.PCRE.Light.Char8
 import System.Path.WildMatch
 import Control.Monad (filterM)
+import Control.Applicative
 import Data.Maybe
 
 import Annex
@@ -27,6 +28,10 @@ filterFiles l = do
 	matcher <- getMatcher
 	filterM (Utility.Matcher.matchM matcher) l
 
+{- Checks if there are user-specified limits. -}
+limited :: Annex Bool
+limited = (not . Utility.Matcher.matchesAny) <$> getMatcher
+
 {- Gets a matcher for the user-specified limits. The matcher is cached for
  - speed; once it's obtained the user-specified limits can't change. -}
 getMatcher :: Annex (Utility.Matcher.Matcher (FilePath -> Annex Bool))
diff --git a/Utility/Matcher.hs b/Utility/Matcher.hs
index 08534fc304..5cf000b1b6 100644
--- a/Utility/Matcher.hs
+++ b/Utility/Matcher.hs
@@ -20,7 +20,8 @@ module Utility.Matcher (
 	Matcher,
 	generate,
 	match,
-	matchM
+	matchM,
+	matchesAny
 ) where
 
 import Control.Monad
@@ -81,3 +82,10 @@ matchM m v = go m
 		go (Or m1 m2) =  liftM2 (||) (go m1) (go m2)
 		go (Not m1) = liftM not (go m1)
 		go (Op o) = o v
+
+{- Checks is a matcher contains no limits, and so (presumably) matches
+ - anything. Note that this only checks the trivial case; it is possible
+ - to construct matchers that match anything but are more complicated. -}
+matchesAny :: Matcher a -> Bool
+matchesAny Any = True
+matchesAny _ = False
diff --git a/debian/changelog b/debian/changelog
index 638661f735..1f7decc1d8 100644
--- a/debian/changelog
+++ b/debian/changelog
@@ -7,6 +7,11 @@ git-annex (3.20110916) UNRELEASED; urgency=low
     Example: git annex get --exclude '*.mp3' --and --not -( --in usbdrive --or --in archive -)
   * --copies=N can be used to make git-annex only operate on files with
     the specified number of copies. (And --not --copies=N for the inverse.)
+  * find: Rather than only showing files whose contents are present,
+    when used with --exclude --copies or --in, displays all files that
+    match the specified conditions.
+  * Note that this is a behavior change for find --exclude! Old behavior
+    can be gotten with: find --in . --exclude=...
 
  -- Joey Hess <joeyh@debian.org>  Sun, 18 Sep 2011 18:25:51 -0400
 
diff --git a/doc/git-annex.mdwn b/doc/git-annex.mdwn
index 836e782cde..4a8e28a6ee 100644
--- a/doc/git-annex.mdwn
+++ b/doc/git-annex.mdwn
@@ -222,6 +222,8 @@ subdirectories).
 * find [path ...]
 
   Outputs a list of annexed files whose content is currently present.
+  Or, if a file matching option is specified, outputs a list of all
+  matching files, whether or not their content is currently present.
 
   With no parameters, defaults to finding all files in the current directory
   and its subdirectories.
@@ -432,7 +434,8 @@ file contents are present at either of two repositories.
   in a repository.
 
   The repository should be specified using the name of a configured remote,
-  or the UUID or description of a repository.
+  or the UUID or description of a repository. For the current repository,
+  use "--in=."
 
 * --copies=number