From 6b2dfad98cb2793f604840454dfdc00ce9484207 Mon Sep 17 00:00:00 2001
From: Simon Michael <simon@joyful.com>
Date: Sat, 9 May 2020 15:43:44 -0700
Subject: [PATCH] ;csv: clarify that whitespace is not stripped when matching

---
 hledger-lib/Hledger/Read/CsvReader.hs | 14 +++++++++-----
 hledger-lib/hledger_csv.m4.md         |  9 ++++++---
 2 files changed, 15 insertions(+), 8 deletions(-)

diff --git a/hledger-lib/Hledger/Read/CsvReader.hs b/hledger-lib/Hledger/Read/CsvReader.hs
index a346f2582..5d3c5cf0e 100644
--- a/hledger-lib/Hledger/Read/CsvReader.hs
+++ b/hledger-lib/Hledger/Read/CsvReader.hs
@@ -1075,12 +1075,16 @@ getEffectiveAssignment rules record f = lastMay $ map snd $ assignments
               where
                 -- does this individual matcher match the current csv record ?
                 matcherMatches :: Matcher -> Bool
-                matcherMatches (RecordMatcher pat) = regexMatchesCI pat wholecsvline
+                matcherMatches (RecordMatcher pat) = regexMatchesCI pat' wholecsvline
                   where
-                    -- a synthetic whole CSV record to match against; note, it has
-                    -- no quotes enclosing fields, and is always comma-separated,
-                    -- so may differ from the actual record, and may not be valid CSV.
-                    wholecsvline = dbg3 "wholecsvline" $ intercalate "," record
+                    pat' = dbg3 "regex" pat
+                    -- A synthetic whole CSV record to match against. Note, this can be
+                    -- different from the original CSV data:
+                    -- - any whitespace surrounding field values is preserved
+                    -- - any quotes enclosing field values are removed
+                    -- - and the field separator is always comma
+                    -- which means that a field containing a comma will look like two fields.
+                    wholecsvline = dbg3 "wholecsvline" $ intercalate "," record  -- $ map strip record  ?
                 matcherMatches (FieldMatcher csvfieldref pat) = regexMatchesCI pat csvfieldvalue
                   where
                     -- the value of the referenced CSV field to match against.
diff --git a/hledger-lib/hledger_csv.m4.md b/hledger-lib/hledger_csv.m4.md
index 11ee7ebb9..ad0153c24 100644
--- a/hledger-lib/hledger_csv.m4.md
+++ b/hledger-lib/hledger_csv.m4.md
@@ -545,9 +545,12 @@ REGEX
 REGEX is a case-insensitive regular expression which tries to match anywhere within the CSV record.
 It is a POSIX extended regular expressions with some additions (see 
 [Regular expressions](https://hledger.org/hledger.html#regular-expressions) in the hledger manual).
-Note: the "CSV record" it is matched against is not the original record, but a synthetic one,
-with enclosing double quotes or whitespace removed, and always comma-separated.
-(Eg, an SSV record `2020-01-01; "Acme, Inc."; 1,000` appears to REGEX as `2020-01-01,Acme, Inc.,1,000`).
+
+Important note: the record that is matched is not the original record, but a synthetic one,
+with any enclosing double quotes (but not enclosing whitespace) removed, and always comma-separated
+(which means that a field containing a comma will appear like two fields).
+Eg, if the original record is `2020-01-01; "Acme, Inc.";  1,000`,
+the REGEX will actually see   `2020-01-01,Acme, Inc.,  1,000`).
 
 Or, MATCHER can be a field matcher, like this:
 ```rules