From 00e9e844ac591de396a0884a87f4a28392556be5 Mon Sep 17 00:00:00 2001
From: Simon Michael <simon@joyful.com>
Date: Tue, 2 Jun 2020 17:13:07 -0700
Subject: [PATCH] journal: the include directive now accepts a file format
 prefix

This works with glob patterns too, applying the prefix to each path.
This can be useful when included files don't have the standard file
extension, eg:

include timedot:2020*.md
---
 hledger-lib/Hledger/Read/JournalReader.hs | 27 ++++++++++++++---------
 hledger-lib/hledger_journal.m4.md         | 18 +++++++++------
 2 files changed, 27 insertions(+), 18 deletions(-)

diff --git a/hledger-lib/Hledger/Read/JournalReader.hs b/hledger-lib/Hledger/Read/JournalReader.hs
index 9810ea9aa..0557b7893 100644
--- a/hledger-lib/Hledger/Read/JournalReader.hs
+++ b/hledger-lib/Hledger/Read/JournalReader.hs
@@ -240,19 +240,23 @@ directivep = (do
    ]
   ) <?> "directive"
 
+-- | Parse an include directive. include's argument is an optionally
+-- file-format-prefixed file path or glob pattern. In the latter case,
+-- the prefix is applied to each matched path. Examples:
+-- foo.j, foo/bar.j, timedot:foo/2020*.md
 includedirectivep :: MonadIO m => ErroringJournalParser m ()
 includedirectivep = do
   string "include"
   lift (skipSome spacenonewline)
-  filename <- T.unpack <$> takeWhileP Nothing (/= '\n') -- don't consume newline yet
-
+  prefixedglob <- T.unpack <$> takeWhileP Nothing (/= '\n') -- don't consume newline yet
   parentoff <- getOffset
   parentpos <- getSourcePos
-
-  filepaths <- getFilePaths parentoff parentpos filename
-
-  forM_ filepaths $ parseChild parentpos
-
+  let (mprefix,glob) = splitReaderPrefix prefixedglob
+  paths <- getFilePaths parentoff parentpos glob
+  let prefixedpaths = case mprefix of
+        Nothing  -> paths
+        Just fmt -> map ((fmt++":")++) paths
+  forM_ prefixedpaths $ parseChild parentpos
   void newline
 
   where
@@ -275,10 +279,11 @@ includedirectivep = do
             else customFailure $ parseErrorAt parseroff $
                    "No existing files match pattern: " ++ filename
 
-    parseChild :: MonadIO m => SourcePos -> FilePath -> ErroringJournalParser m ()
-    parseChild parentpos filepath = do
-      parentj <- get
+    parseChild :: MonadIO m => SourcePos -> PrefixedFilePath -> ErroringJournalParser m ()
+    parseChild parentpos prefixedpath = do
+      let (_mprefix,filepath) = splitReaderPrefix prefixedpath
 
+      parentj <- get
       let parentfilestack = jincludefilestack parentj
       when (filepath `elem` parentfilestack) $
         Fail.fail ("Cyclic include: " ++ filepath)
@@ -289,7 +294,7 @@ includedirectivep = do
 
       -- Choose a reader/format based on the file path, or fall back
       -- on journal. Duplicating readJournal a bit here.
-      let r = fromMaybe reader $ findReader Nothing (Just filepath)
+      let r = fromMaybe reader $ findReader Nothing (Just prefixedpath)
           parser = rParser r
       dbg1IO "trying reader" (rFormat r)
       updatedChildj <- journalAddFile (filepath, childInput) <$>
diff --git a/hledger-lib/hledger_journal.m4.md b/hledger-lib/hledger_journal.m4.md
index 668409456..714604309 100644
--- a/hledger-lib/hledger_journal.m4.md
+++ b/hledger-lib/hledger_journal.m4.md
@@ -878,16 +878,20 @@ See also [comments](#comments).
 You can pull in the content of additional files by writing an include directive, like this:
 
 ```journal
-include path/to/file.journal
+include FILEPATH
 ```
 
-If the path does not begin with a slash, it is relative to the current file.
-The include file path may contain
-[common glob patterns](https://hackage.haskell.org/package/Glob-0.9.2/docs/System-FilePath-Glob.html#v:compile)
-(e.g. `*`).
+Only journal files can include, and only journal, timeclock or timedot files can be included (not CSV files, currently).
 
-The `include` directive can only be used in journal files.
-It can include journal, timeclock or timedot files, but not CSV files.
+If the file path does not begin with a slash, it is relative to the current file's folder. 
+
+It may contain [glob patterns] to match multiple files, eg: `include *.journal`.
+
+Or a tilde, meaning home directory: `include ~/main.journal`.
+
+It may also be prefixed to force a specific file format, overriding the file extension (as described in [hledger.1 -> Input files](hledger.html#input-files)): `include timedot:~/notes/2020*.md`.
+
+[glob patterns]: https://hackage.haskell.org/package/Glob-0.9.2/docs/System-FilePath-Glob.html#v:compile
 
 ### Default year