Support --metadata field<number, --metadata field>number etc to match ranges of numeric values.

Similarly (well, for free), support preferred content expressions like
metadata=field<number and metadata=field>number

Annex/MetaData.hs

@@ -1,6 +1,6 @@
 {- git-annex metadata
  -
- - Copyright 2014 Joey Hess <id@joeyh.name>
+ - Copyright 2014-2016 Joey Hess <id@joeyh.name>
  -
  - Licensed under the GNU GPL version 3 or higher.
  -}
@@ -8,6 +8,8 @@
 module Annex.MetaData (
 	genMetaData,
 	dateMetaData,
+	parseModMeta,
+	parseMetaDataMatcher,
 	module X
 ) where
 
@@ -17,6 +19,7 @@ import Types.MetaData as X
 import Annex.MetaData.StandardFields as X
 import Logs.MetaData
 import Annex.CatFile
+import Utility.Glob
 
 import qualified Data.Set as S
 import qualified Data.Map as M
@@ -53,3 +56,37 @@ dateMetaData mtime old = MetaData $ M.fromList $ filter isnew
   where
 	isnew (f, _) = S.null (currentMetaDataValues f old)
 	(y, m, _d) = toGregorian $ utctDay mtime
+
+{- Parses field=value, field+=value, field-=value, field?=value -}
+parseModMeta :: String -> Either String ModMeta
+parseModMeta p = case lastMaybe f of
+	Just '+' -> AddMeta <$> mkMetaField f' <*> v
+	Just '-' -> DelMeta <$> mkMetaField f' <*> v
+	Just '?' -> MaybeSetMeta <$> mkMetaField f' <*> v
+	_ -> SetMeta <$> mkMetaField f <*> v
+  where
+	(f, sv) = separate (== '=') p
+	f' = beginning f
+	v = pure (toMetaValue sv)
+
+{- Parses field=value, field<value, field<=value, field>value, field>=value -}
+parseMetaDataMatcher :: String -> Either String (MetaField, MetaValue -> Bool)
+parseMetaDataMatcher p = (,)
+	<$> mkMetaField f
+	<*> pure matcher
+  where
+	(f, op_v) = break (`elem` "=<>") p
+	matcher = case op_v of
+		('=':v) -> checkglob v
+		('<':'=':v) -> checkcmp (<=) v
+		('<':v) -> checkcmp (<) v
+		('>':'=':v) -> checkcmp (>=) v
+		('>':v) -> checkcmp (>) v
+		_ -> checkglob ""
+	checkglob v =
+		let cglob = compileGlob v CaseInsensative
+		in matchGlob cglob . fromMetaValue
+	checkcmp cmp v v' = case (doubleval v, doubleval (fromMetaValue v')) of
+		(Just d, Just d') -> d' `cmp` d
+		_ -> False
+	doubleval v = readish v :: Maybe Double

Backend/Hash.hs

@@ -5,7 +5,7 @@
  - Licensed under the GNU GPL version 3 or higher.
  -}
 
-{-# LANGUAGE CPP, BangPatterns #-}
+{-# LANGUAGE CPP #-}
 
 module Backend.Hash (
 	backends,

Limit.hs

@@ -23,6 +23,7 @@ import Types.TrustLevel
 import Types.Group
 import Types.FileMatcher
 import Types.MetaData
+import Annex.MetaData
 import Logs.MetaData
 import Logs.Group
 import Logs.Unused
@@ -278,14 +279,12 @@ addMetaData :: String -> Annex ()
 addMetaData = addLimit . limitMetaData
 
 limitMetaData :: MkLimit Annex
-limitMetaData s = case parseMetaData s of
+limitMetaData s = case parseMetaDataMatcher s of
 	Left e -> Left e
-	Right (f, v) ->
-		let cglob = compileGlob (fromMetaValue v) CaseInsensative
-		in Right $ const $ checkKey (check f cglob)
+	Right (f, matching) -> Right $ const $ checkKey (check f matching)
   where
-	check f cglob k = not . S.null 
-		. S.filter (matchGlob cglob . fromMetaValue) 
+	check f matching k = not . S.null 
+		. S.filter matching
 		. metaDataValues f <$> getCurrentMetaData k
 
 addTimeLimit :: String -> Annex ()

Types/MetaData.hs

@@ -36,8 +36,6 @@ module Types.MetaData (
 	metaDataValues,
 	ModMeta(..),
 	modMeta,
-	parseModMeta,
-	parseMetaData,
 	prop_metadata_sane,
 	prop_metadata_serialize
 ) where
@@ -239,26 +237,6 @@ modMeta m (MaybeSetMeta f v)
 	| S.null (currentMetaDataValues f m) = updateMetaData f v emptyMetaData
 	| otherwise = emptyMetaData
 
-{- Parses field=value, field+=value, field-=value, field?=value -}
-parseModMeta :: String -> Either String ModMeta
-parseModMeta p = case lastMaybe f of
-	Just '+' -> AddMeta <$> mkMetaField f' <*> v
-	Just '-' -> DelMeta <$> mkMetaField f' <*> v
-	Just '?' -> MaybeSetMeta <$> mkMetaField f' <*> v
-	_ -> SetMeta <$> mkMetaField f <*> v
-  where
-	(f, sv) = separate (== '=') p
-	f' = beginning f
-	v = pure (toMetaValue sv)
-
-{- Parses field=value -}
-parseMetaData :: String -> Either String (MetaField, MetaValue)
-parseMetaData p = (,)
-	<$> mkMetaField f
-	<*> pure (toMetaValue v)
-  where
-	(f, v) = separate (== '=') p
-
 {- Avoid putting too many fields in the map; extremely large maps make
  - the seriaization test slow due to the sheer amount of data.
  - It's unlikely that more than 100 fields of metadata will be used. -}

debian/changelog

@@ -15,6 +15,10 @@ git-annex (6.20160218) UNRELEASED; urgency=medium
   * Fix memory leak when hashing files, which triggered during fsck
     when an external hash program was not used.
     (This leak was introduced in version 6.20160114.)
+  * Support --metadata field<number, --metadata field>number etc
+    to match ranges of numeric values.
+  * Similarly, support preferred content expressions like
+    metadata=field<number and metadata=field>number
 
  -- Joey Hess <id@joeyh.name>  Thu, 18 Feb 2016 13:09:21 -0400
 

doc/git-annex-matching-options.mdwn

@@ -115,6 +115,15 @@ file contents are present at either of two repositories.
   matches the glob. The values of metadata fields are matched case
   insensitively.
 
+* `--metadata field<number` / `--metadata field>number`
+* `--metadata field<=number` / `--metadata field>=number`
+
+  Matches only files that have a metadata field attached with a value that
+  is a number and is less than or greater than the specified number.
+
+  (Note that you will need to quote the second parameter to avoid
+  the shell doing redirection.)
+
 * `--want-get`
 
   Matches files that the preferred content settings for the repository

doc/git-annex-preferred-content.mdwn

@@ -119,6 +119,15 @@ elsewhere to allow removing it).
 
   To match author metadata, use `metadata=author=*Smith`
 
+* `metadata=field<number` / `metadata=field>number` 
+* `metadata=field<=number` / `metadata=field>=number`
+
+  Matches only files that have a metadata field attached with a value that
+  is a number and is less than or greater than the specified number.
+
+  To match PDFs with between 100 and 200 pages (assuming something has set
+  that metadata), use `metadata=pagecount>=100 and metadata=pagecount<=200`
+
 * `present`
 
   Makes content be wanted if it's present, but not otherwise.

doc/preferred_content.mdwn

@@ -67,3 +67,4 @@ they were added in.
 * "metadata=" 5.20140221
 * "lackingcopies=", "approxlackingcopies=", "unused=" 5.20140127
 * "inpreferreddir=" 4.20130501
+* "metadata=field<number" etc 6.20160227