From 3ddc9d74320d09492cf7fd117ac8858b6f4f01f8 Mon Sep 17 00:00:00 2001
From: Simon Michael <simon@joyful.com>
Date: Wed, 16 Nov 2016 13:25:33 -0800
Subject: [PATCH] lib: clarify file format detectors

---
 hledger-lib/Hledger/Read/CsvReader.hs       | 10 ++++++----
 hledger-lib/Hledger/Read/JournalReader.hs   | 14 +++++++++-----
 hledger-lib/Hledger/Read/LedgerReader.hs    | 11 ++++++-----
 hledger-lib/Hledger/Read/TimeclockReader.hs | 10 ++++++----
 hledger-lib/Hledger/Read/TimedotReader.hs   | 10 ++++++----
 5 files changed, 33 insertions(+), 22 deletions(-)

diff --git a/hledger-lib/Hledger/Read/CsvReader.hs b/hledger-lib/Hledger/Read/CsvReader.hs
index fe1165fdd..209df6ccb 100644
--- a/hledger-lib/Hledger/Read/CsvReader.hs
+++ b/hledger-lib/Hledger/Read/CsvReader.hs
@@ -69,11 +69,13 @@ reader = Reader format detect parse
 format :: String
 format = "csv"
 
--- | Does the given file path and data look like it might be CSV ?
+-- | Does the given file path and data look like something this reader can handle ?
 detect :: FilePath -> Text -> Bool
-detect f t
-  | f /= "-"  = takeExtension f == '.':format  -- from a file: yes if the extension is .csv
-  | otherwise = T.length (T.filter (==',') t) >= 2 -- from stdin: yes if there are two or more commas
+detect f excerpt
+  -- file name known: try this reader if it has any of these extensions
+  | f /= "-"  = takeExtension f `elem` ['.':format]
+  -- file name unknown: try this reader if excerpt contains two or more commas
+  | otherwise = T.length (T.filter (==',') excerpt) >= 2
 
 -- | Parse and post-process a "Journal" from CSV data, or give an error.
 -- XXX currently ignores the string and reads from the file path
diff --git a/hledger-lib/Hledger/Read/JournalReader.hs b/hledger-lib/Hledger/Read/JournalReader.hs
index 422edc40b..4733ee28a 100644
--- a/hledger-lib/Hledger/Read/JournalReader.hs
+++ b/hledger-lib/Hledger/Read/JournalReader.hs
@@ -111,12 +111,16 @@ reader = Reader format detect parse
 format :: String
 format = "journal"
 
--- | Does the given file path and data look like it might be hledger's journal format ?
+-- | Does the given file path and data look like something this reader can handle ?
 detect :: FilePath -> Text -> Bool
-detect f _t
-  | f /= "-"  = takeExtension f `elem` ['.':format, ".j", ".hledger"] -- from a known file name: yes if the extension is .hledger or .journal or .j
-  | otherwise = True                                      -- from stdin: yes, always attempt to parse stdin as hledger journal data
-  -- otherwise = regexMatches "(^|\n)[0-9]+.*\n[ \t]+" $ T.unpack t   -- from stdin: yes if we can see something that looks like a journal entry (digits in column 0 with the next line indented)
+detect f _
+  -- file name known: try this reader if it has any of these extensions
+  | f /= "-"  = takeExtension f `elem` ['.':format, ".j", ".hledger", ".ledger", ".l"]
+  -- file name unknown: always try this reader
+  | otherwise = True
+  -- file name unknown: try this reader if we can see something like a journal entry
+  -- (digits in column 0 with the next line indented)
+  -- otherwise = regexMatches "(^|\n)[0-9]+.*\n[ \t]+" $ T.unpack excerpt
 
 -- | Parse and post-process a "Journal" from hledger's journal file
 -- format, or give an error.
diff --git a/hledger-lib/Hledger/Read/LedgerReader.hs b/hledger-lib/Hledger/Read/LedgerReader.hs
index 0560f73f9..6df15cf47 100644
--- a/hledger-lib/Hledger/Read/LedgerReader.hs
+++ b/hledger-lib/Hledger/Read/LedgerReader.hs
@@ -56,12 +56,13 @@ reader = Reader format detect parse
 format :: String
 format = "ledger"
 
--- | Does the given file path and data look like it might be ledger's journal format ?
+-- | Does the given file path and data look like something this reader can handle ?
 detect :: FilePath -> Text -> Bool
-detect f _t
-  | f /= "-"  = takeExtension f `elem` ['.':format, ".l"] -- from a known file name: yes if the extension is .ledger or .l
-  | otherwise = False                                      -- from stdin: yes, always attempt to parse stdin as a ledger journal
-  -- otherwise = regexMatches "(^|\n)[0-9]+.*\n[ \t]+" $ T.unpack t   -- from stdin: yes if we can see something that looks like a journal entry (digits in column 0 with the next line indented)
+detect f _
+  -- file name known: try this reader if it has any of these extensions
+  | f /= "-"  = takeExtension f `elem` ['.':format, ".l"]
+  -- file name unknown: don't try this reader
+  | otherwise = False
 
 -- | Parse and post-process a "Journal" from ledger's journal format, or give an error.
 parse :: Maybe FilePath -> Bool -> FilePath -> Text -> ExceptT String IO Journal
diff --git a/hledger-lib/Hledger/Read/TimeclockReader.hs b/hledger-lib/Hledger/Read/TimeclockReader.hs
index 9ec7701f7..3503decd7 100644
--- a/hledger-lib/Hledger/Read/TimeclockReader.hs
+++ b/hledger-lib/Hledger/Read/TimeclockReader.hs
@@ -75,11 +75,13 @@ reader = Reader format detect parse
 format :: String
 format = "timeclock"
 
--- | Does the given file path and data look like it might be timeclock.el's timeclock format ?
+-- | Does the given file path and data look like something this reader can handle ?
 detect :: FilePath -> Text -> Bool
-detect f t
-  | f /= "-"  = takeExtension f == '.':format -- from a known file name: yes if the extension is this format's name
-  | otherwise = regexMatches "(^|\n)[io] " $ T.unpack t  -- from stdin: yes if any line starts with "i " or "o "
+detect f excerpt
+  -- file name known: try this reader if it has any of these extensions
+  | f /= "-"  = takeExtension f `elem` ['.':format]
+  -- file name unknown: try this reader if a line starts with "i " or "o " in excerpt
+  | otherwise = regexMatches "(^|\n)[io] " $ T.unpack excerpt
 
 -- | Parse and post-process a "Journal" from timeclock.el's timeclock
 -- format, saving the provided file path and the current time, or give an
diff --git a/hledger-lib/Hledger/Read/TimedotReader.hs b/hledger-lib/Hledger/Read/TimedotReader.hs
index eb49312ce..de31e9a1d 100644
--- a/hledger-lib/Hledger/Read/TimedotReader.hs
+++ b/hledger-lib/Hledger/Read/TimedotReader.hs
@@ -61,11 +61,13 @@ reader = Reader format detect parse
 format :: String
 format = "timedot"
 
--- | Does the given file path and data look like it might contain this format ?
+-- | Does the given file path and data look like something this reader can handle ?
 detect :: FilePath -> Text -> Bool
-detect f t
-  | f /= "-"  = takeExtension f == '.':format -- from a file: yes if the extension matches the format name
-  | otherwise = regexMatches "(^|\n)[0-9]" $ T.unpack t  -- from stdin: yes if we can see a possible timedot day entry (digits in column 0)
+detect f excerpt
+  -- file name known: try this reader if it has any of these extensions
+  | f /= "-"  = takeExtension f `elem` ['.':format]
+  -- file name unknown: try this reader if a line starts with a number in excerpt
+  | otherwise = regexMatches "(^|\n)[0-9]" $ T.unpack excerpt
 
 -- | Parse and post-process a "Journal" from the timedot format, or give an error.
 parse :: Maybe FilePath -> Bool -> FilePath -> Text -> ExceptT String IO Journal