[Git][ghc/ghc][wip/T25375] Fix CRLF in multiline strings (#25375)

[Brandon Chinn (@brandonchinn178)]

Brandon Chinn pushed to branch wip/T25375 at Glasgow Haskell Compiler / GHC


Commits:
db2a1f4a by Brandon Chinn at 2024-11-03T09:37:04-08:00
Fix CRLF in multiline strings (#25375)

- - - - -


6 changed files:

- .gitattributes
- compiler/GHC/Parser/String.hs
- docs/users_guide/exts/multiline_strings.rst
- + testsuite/tests/parser/should_run/T25375.hs
- + testsuite/tests/parser/should_run/T25375.stdout
- testsuite/tests/parser/should_run/all.T


Changes:

=====================================
.gitattributes
=====================================
@@ -2,3 +2,4 @@
 # don't convert anything on checkout
 * text=auto eol=lf
 mk/win32-tarballs.md5sum text=auto eol=LF
+testsuite/tests/parser/should_run/T25375.hs text=auto eol=crlf


=====================================
compiler/GHC/Parser/String.hs
=====================================
@@ -261,6 +261,7 @@ lexMultilineString = lexStringWith processChars processChars
     processChars :: HasChar c => [c] -> Either (c, LexErr) [c]
     processChars =
           collapseGaps             -- Step 1
+      >>> normalizeEOL
       >>> expandLeadingTabs        -- Step 3
       >>> rmCommonWhitespacePrefix -- Step 4
       >>> collapseOnlyWsLines      -- Step 5
@@ -268,6 +269,19 @@ lexMultilineString = lexStringWith processChars processChars
       >>> rmLastNewline            -- Step 7b
       >>> resolveEscapes           -- Step 8
 
+    -- Normalize line endings to LF. The spec dictates that lines should be
+    -- split on newline characters and rejoined with ``\n``. But because we
+    -- aren't actually splitting/rejoining, we'll manually normalize here
+    normalizeEOL :: HasChar c => [c] -> [c]
+    normalizeEOL =
+      let go = \case
+            Char '\r' : c@(Char '\n') : cs -> c : go cs
+            c@(Char '\r') : cs -> setChar '\n' c : go cs
+            c@(Char '\f') : cs -> setChar '\n' c : go cs
+            c : cs -> c : go cs
+            [] -> []
+       in go
+
     -- expands all tabs, since the lexer will verify that tabs can only appear
     -- as leading indentation
     expandLeadingTabs :: HasChar c => [c] -> [c]


=====================================
docs/users_guide/exts/multiline_strings.rst
=====================================
@@ -14,7 +14,9 @@ With this extension, GHC now recognizes multiline string literals with ``"""`` d
 
 Normal string literals are lexed, then string gaps are collapsed, then escape characters are resolved. Multiline string literals add the following post-processing steps between collapsing string gaps and resolving escape characters:
 
-#. Split the string by newlines
+#. Split the string by newline characters
+
+      * Includes ``\r\n``, ``\r``, ``\n``, ``\f``
 
 #. Replace leading tabs with spaces up to the next tab stop
 
@@ -24,7 +26,9 @@ Normal string literals are lexed, then string gaps are collapsed, then escape ch
 
 #. Join the string back with ``\n`` delimiters
 
-#. If the first character of the string is a newline, remove it
+#. If the first character of the string is ``\n``, remove it
+
+#. If the last character of the string is ``\n``, remove it
 
 Examples
 ~~~~~~~~


=====================================
testsuite/tests/parser/should_run/T25375.hs
=====================================
@@ -0,0 +1,38 @@
+{-# LANGUAGE MultilineStrings #-}
+
+str1 = unlines
+  [ "aaa"
+  , "bbb"
+  , "ccc"
+  ]
+
+str2 = "aaa\n\
+       \bbb\n\
+       \ccc\n"
+
+str3 = """
+       aaa
+       bbb
+       ccc
+       """
+
+str4 = """
+
+       aaa
+       bbb
+       ccc
+
+       """
+
+str5 = """
+       aaa
+       bbb
+       ccc\n
+       """
+
+main = do
+  print str1
+  print str2
+  print str3
+  print str4
+  print str5


=====================================
testsuite/tests/parser/should_run/T25375.stdout
=====================================
@@ -0,0 +1,5 @@
+"aaa\nbbb\nccc\n"
+"aaa\nbbb\nccc\n"
+"aaa\nbbb\nccc"
+"\naaa\nbbb\nccc\n"
+"aaa\nbbb\nccc\n"


=====================================
testsuite/tests/parser/should_run/all.T
=====================================
@@ -23,3 +23,4 @@ test('RecordDotSyntax5', normal, compile_and_run, [''])
 test('ListTuplePunsConstraints', extra_files(['ListTuplePunsConstraints.hs']), ghci_script, ['ListTuplePunsConstraints.script'])
 test('MultilineStrings', normal, compile_and_run, [''])
 test('MultilineStringsOverloaded', normal, compile_and_run, [''])
+test('T25375', normal, compile_and_run, [''])



View it on GitLab: https://gitlab.haskell.org/ghc/ghc/-/commit/db2a1f4afe9939b4e14114f0ba4bc3145b67c015

-- 
View it on GitLab: https://gitlab.haskell.org/ghc/ghc/-/commit/db2a1f4afe9939b4e14114f0ba4bc3145b67c015
You're receiving this email because of your account on gitlab.haskell.org.


-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mail.haskell.org/pipermail/ghc-commits/attachments/20241103/24699101/attachment-0001.html>