2010-11-14 16:35:05 +00:00
|
|
|
{- git-annex command
|
|
|
|
-
|
2018-12-09 18:10:37 +00:00
|
|
|
- Copyright 2010-2018 Joey Hess <id@joeyh.name>
|
2010-11-14 16:35:05 +00:00
|
|
|
-
|
2019-03-13 19:48:14 +00:00
|
|
|
- Licensed under the GNU AGPL version 3 or higher.
|
2010-11-14 16:35:05 +00:00
|
|
|
-}
|
|
|
|
|
|
|
|
module Command.Find where
|
|
|
|
|
2015-01-28 19:55:17 +00:00
|
|
|
import Data.Default
|
2011-12-22 22:31:44 +00:00
|
|
|
import qualified Data.Map as M
|
|
|
|
|
2010-11-14 16:35:05 +00:00
|
|
|
import Command
|
2011-10-04 04:40:47 +00:00
|
|
|
import Annex.Content
|
2011-09-19 00:41:51 +00:00
|
|
|
import Limit
|
2017-02-24 19:16:56 +00:00
|
|
|
import Types.Key
|
2018-12-09 18:10:37 +00:00
|
|
|
import Git.FilePath
|
2011-12-22 22:31:44 +00:00
|
|
|
import qualified Utility.Format
|
|
|
|
import Utility.DataUnits
|
2010-11-14 16:35:05 +00:00
|
|
|
|
2015-07-08 16:33:27 +00:00
|
|
|
cmd :: Command
|
2018-10-16 14:44:09 +00:00
|
|
|
cmd = notBareRepo $ withGlobalOptions [annexedMatchingOptions] $ mkCommand $
|
2015-07-08 19:08:02 +00:00
|
|
|
command "find" SectionQuery "lists available files"
|
2015-07-10 16:47:35 +00:00
|
|
|
paramPaths (seek <$$> optParser)
|
2014-04-17 22:41:24 +00:00
|
|
|
|
|
|
|
mkCommand :: Command -> Command
|
2018-02-19 18:28:17 +00:00
|
|
|
mkCommand = noCommit . noMessages . withGlobalOptions [jsonOptions]
|
2015-07-10 16:47:35 +00:00
|
|
|
|
|
|
|
data FindOptions = FindOptions
|
|
|
|
{ findThese :: CmdParams
|
|
|
|
, formatOption :: Maybe Utility.Format.Format
|
2018-12-09 18:10:37 +00:00
|
|
|
, keyOptions :: Maybe KeyOptions
|
2016-01-20 17:04:07 +00:00
|
|
|
, batchOption :: BatchMode
|
2015-07-10 16:47:35 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
optParser :: CmdParamsDesc -> Parser FindOptions
|
|
|
|
optParser desc = FindOptions
|
|
|
|
<$> cmdParams desc
|
|
|
|
<*> optional parseFormatOption
|
2018-12-09 18:10:37 +00:00
|
|
|
<*> optional parseBranchKeysOption
|
2016-01-20 17:04:07 +00:00
|
|
|
<*> parseBatchOption
|
2015-07-10 16:47:35 +00:00
|
|
|
|
|
|
|
parseFormatOption :: Parser Utility.Format.Format
|
|
|
|
parseFormatOption =
|
|
|
|
option (Utility.Format.gen <$> str)
|
|
|
|
( long "format" <> metavar paramFormat
|
|
|
|
<> help "control format of output"
|
|
|
|
)
|
|
|
|
<|> flag' (Utility.Format.gen "${file}\0")
|
|
|
|
( long "print0"
|
|
|
|
<> help "output filenames terminated with nulls"
|
|
|
|
)
|
|
|
|
|
|
|
|
seek :: FindOptions -> CommandSeek
|
2016-01-20 17:04:07 +00:00
|
|
|
seek o = case batchOption o of
|
2018-12-09 18:10:37 +00:00
|
|
|
NoBatch -> withKeyOptions (keyOptions o) False
|
|
|
|
(commandAction . startKeys o)
|
|
|
|
(withFilesInGit (commandAction . go))
|
2018-10-01 18:12:06 +00:00
|
|
|
=<< workTreeItems (findThese o)
|
added -z
Added -z option to git-annex commands that use --batch, useful for
supporting filenames containing newlines.
It only controls input to --batch, the output will still be line delimited
unless --json or etc is used to get some other output. While git often
makes -z affect both input and output, I don't like trying them together,
and making it affect output would have been a significant complication,
and also git-annex output is generally not intended to be machine parsed,
unless using --json or a format option.
Commands that take pairs like "file key" still separate them with a space
in --batch mode. All such commands take care to support filenames with
spaces when parsing that, so there was no need to change it, and it would
have needed significant changes to the batch machinery to separate tose
with a null.
To make fromkey and registerurl support -z, I had to give them a --batch
option. The implicit batch mode they enter when not provided with input
parameters does not support -z as that would have complicated option
parsing. Seemed better to move these toward using the same --batch as
everything else, though the implicit batch mode can still be used.
This commit was sponsored by Ole-Morten Duesund on Patreon.
2018-09-20 20:09:21 +00:00
|
|
|
Batch fmt -> batchFilesMatching fmt go
|
2016-01-20 17:04:07 +00:00
|
|
|
where
|
|
|
|
go = whenAnnexed $ start o
|
2010-11-14 16:35:05 +00:00
|
|
|
|
2016-01-20 17:04:07 +00:00
|
|
|
-- only files inAnnex are shown, unless the user has requested
|
|
|
|
-- others via a limit
|
2015-07-11 00:38:11 +00:00
|
|
|
start :: FindOptions -> FilePath -> Key -> CommandStart
|
make CommandStart return a StartMessage
The goal is to be able to run CommandStart in the main thread when -J is
used, rather than unncessarily passing it off to a worker thread, which
incurs overhead that is signficant when the CommandStart is going to
quickly decide to stop.
To do that, the message it displays needs to be displayed in the worker
thread, after the CommandStart has run.
Also, the change will mean that CommandStart will no longer necessarily
run with the same Annex state as CommandPerform. While its docs already
said it should avoid modifying Annex state, I audited all the
CommandStart code as part of the conversion. (Note that CommandSeek
already sometimes runs with a different Annex state, and that has not been
a source of any problems, so I am not too worried that this change will
lead to breakage going forward.)
The only modification of Annex state I found was it calling
allowMessages in some Commands that default to noMessages. Dealt with
that by adding a startCustomOutput and a startingUsualMessages.
This lets a command start with noMessages and then select the output it
wants for each CommandStart.
One bit of breakage: onlyActionOn has been removed from commands that used it.
The plan is that, since a StartMessage contains an ActionItem,
when a Key can be extracted from that, the parallel job runner can
run onlyActionOn' automatically. Then commands won't need to worry about
this detail. Future work.
Otherwise, this was a fairly straightforward process of making each
CommandStart compile again. Hopefully other behavior changes were mostly
avoided.
In a few cases, a command had a CommandStart that called a CommandPerform
that then called showStart multiple times. I have collapsed those
down to a single start action. The main command to perhaps suffer from it
is Command.Direct, which used to show a start for each file, and no
longer does.
Another minor behavior change is that some commands used showStart
before, but had an associated file and a Key available, so were changed
to ShowStart with an ActionItemAssociatedFile. That will not change the
normal output or behavior, but --json output will now include the key.
This should not break it for anyone using a real json parser.
2019-06-06 19:42:30 +00:00
|
|
|
start o file key =
|
|
|
|
stopUnless (limited <||> inAnnex key) $
|
finish CommandStart transition
The hoped for optimisation of CommandStart with -J did not materialize.
In fact, not runnign CommandStart in parallel is slower than -J3.
So, CommandStart are still run in parallel.
(The actual bad performance I've been seeing with -J in my big repo
has to do with building the remoteList.)
But, this is still progress toward making -J faster, because it gets rid
of the onlyActionOn roadblock in the way of making CommandCleanup jobs
run separate from CommandPerform jobs.
Added OnlyActionOn constructor for ActionItem which fixes the
onlyActionOn breakage in the last commit.
Made CustomOutput include an ActionItem, so even things using it can
specify OnlyActionOn.
In Command.Move and Command.Sync, there were CommandStarts that used
includeCommandAction, so output messages, which is no longer allowed.
Fixed by using startingCustomOutput, but that's still not quite right,
since it prevents message display for the includeCommandAction run
inside it too.
2019-06-12 13:23:26 +00:00
|
|
|
startingCustomOutput key $ do
|
make CommandStart return a StartMessage
The goal is to be able to run CommandStart in the main thread when -J is
used, rather than unncessarily passing it off to a worker thread, which
incurs overhead that is signficant when the CommandStart is going to
quickly decide to stop.
To do that, the message it displays needs to be displayed in the worker
thread, after the CommandStart has run.
Also, the change will mean that CommandStart will no longer necessarily
run with the same Annex state as CommandPerform. While its docs already
said it should avoid modifying Annex state, I audited all the
CommandStart code as part of the conversion. (Note that CommandSeek
already sometimes runs with a different Annex state, and that has not been
a source of any problems, so I am not too worried that this change will
lead to breakage going forward.)
The only modification of Annex state I found was it calling
allowMessages in some Commands that default to noMessages. Dealt with
that by adding a startCustomOutput and a startingUsualMessages.
This lets a command start with noMessages and then select the output it
wants for each CommandStart.
One bit of breakage: onlyActionOn has been removed from commands that used it.
The plan is that, since a StartMessage contains an ActionItem,
when a Key can be extracted from that, the parallel job runner can
run onlyActionOn' automatically. Then commands won't need to worry about
this detail. Future work.
Otherwise, this was a fairly straightforward process of making each
CommandStart compile again. Hopefully other behavior changes were mostly
avoided.
In a few cases, a command had a CommandStart that called a CommandPerform
that then called showStart multiple times. I have collapsed those
down to a single start action. The main command to perhaps suffer from it
is Command.Direct, which used to show a start for each file, and no
longer does.
Another minor behavior change is that some commands used showStart
before, but had an associated file and a Key available, so were changed
to ShowStart with an ActionItemAssociatedFile. That will not change the
normal output or behavior, but --json output will now include the key.
This should not break it for anyone using a real json parser.
2019-06-06 19:42:30 +00:00
|
|
|
showFormatted (formatOption o) file $ ("file", file) : keyVars key
|
|
|
|
next $ return True
|
2013-12-15 18:46:29 +00:00
|
|
|
|
2018-12-09 18:10:37 +00:00
|
|
|
startKeys :: FindOptions -> (Key, ActionItem) -> CommandStart
|
2019-06-06 16:53:24 +00:00
|
|
|
startKeys o (key, ActionItemBranchFilePath (BranchFilePath _ topf) _) =
|
2018-12-09 18:10:37 +00:00
|
|
|
start o (getTopFilePath topf) key
|
|
|
|
startKeys _ _ = stop
|
|
|
|
|
2013-12-15 18:46:29 +00:00
|
|
|
showFormatted :: Maybe Utility.Format.Format -> String -> [(String, String)] -> Annex ()
|
|
|
|
showFormatted format unformatted vars =
|
2016-07-26 23:15:34 +00:00
|
|
|
unlessM (showFullJSON $ JSONChunk vars) $
|
2013-12-15 18:46:29 +00:00
|
|
|
case format of
|
|
|
|
Nothing -> liftIO $ putStrLn unformatted
|
|
|
|
Just formatter -> liftIO $ putStr $
|
|
|
|
Utility.Format.format formatter $
|
|
|
|
M.fromList vars
|
|
|
|
|
|
|
|
keyVars :: Key -> [(String, String)]
|
|
|
|
keyVars key =
|
2019-01-14 17:03:35 +00:00
|
|
|
[ ("key", serializeKey key)
|
2019-01-11 20:34:04 +00:00
|
|
|
, ("backend", decodeBS $ formatKeyVariety $ keyVariety key)
|
2013-12-15 18:46:29 +00:00
|
|
|
, ("bytesize", size show)
|
|
|
|
, ("humansize", size $ roughSize storageUnits True)
|
2019-01-11 20:34:04 +00:00
|
|
|
, ("keyname", decodeBS $ keyName key)
|
2015-01-28 19:55:17 +00:00
|
|
|
, ("hashdirlower", hashDirLower def key)
|
|
|
|
, ("hashdirmixed", hashDirMixed def key)
|
2013-12-15 18:46:29 +00:00
|
|
|
, ("mtime", whenavail show $ keyMtime key)
|
|
|
|
]
|
2012-11-12 05:05:04 +00:00
|
|
|
where
|
2013-12-15 18:46:29 +00:00
|
|
|
size c = whenavail c $ keySize key
|
|
|
|
whenavail = maybe "unknown"
|