From 022dcfed314b7794139a0041d2eae01318d1b88e Mon Sep 17 00:00:00 2001
From: Matthias Urlichs <matthias@urlichs.de>
Date: Thu, 4 Jan 2024 18:47:41 +0100
Subject: [PATCH] Fix PEG parsers' "comment" rule

The problem with the previous version was that if there is no text after
the '//', regular whitespace processing kicked in and the regexp was
applied to the next non-empty line.

The effect of this was that the next line gets commented off
unconditionally, which is kindof not what you want.
---
 CHANGELOG.md                      | 2 ++
 arpeggio/cleanpeg.py              | 2 +-
 arpeggio/peg.py                   | 4 ++--
 arpeggio/tests/test_peg_parser.py | 1 +
 4 files changed, 6 insertions(+), 3 deletions(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 7b91cb3..6e5f4a2 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -66,6 +66,8 @@ please take a look at related PRs and issues and see if the change affects you.
 - fix: #98 suppressed match in zero-or-more [#98]. Thanks @vpavlu for reporting
   the issue.
 
+- fix: empty comments in .peg files hid the next line, commented or not.
+
 [#101]: https://github.com/textX/Arpeggio/issues/101
 [#98]: https://github.com/textX/Arpeggio/issues/98
 [#96]: https://github.com/textX/Arpeggio/issues/96
diff --git a/arpeggio/cleanpeg.py b/arpeggio/cleanpeg.py
index b503428..af5c602 100644
--- a/arpeggio/cleanpeg.py
+++ b/arpeggio/cleanpeg.py
@@ -58,7 +58,7 @@ def rule_name():        return _(r"[a-zA-Z_]([a-zA-Z_]|[0-9])*")
 def rule_crossref():    return rule_name
 def str_match():        return _(r'''(?s)('[^'\\]*(?:\\.[^'\\]*)*')|'''
                                  r'''("[^"\\]*(?:\\.[^"\\]*)*")''')
-def comment():          return "//", _(".*\n")
+def comment():          return _("//.*\n", multiline=False)
 
 
 class ParserPEG(ParserPEGOrig):
diff --git a/arpeggio/peg.py b/arpeggio/peg.py
index bbc8717..e6f6ec9 100644
--- a/arpeggio/peg.py
+++ b/arpeggio/peg.py
@@ -67,8 +67,8 @@ def regex():            return [("r'", _(r'''[^'\\]*(?:\\.[^'\\]*)*'''), "'"),
 def rule_name():        return _(r"[a-zA-Z_]([a-zA-Z_]|[0-9])*")
 def rule_crossref():    return rule_name
 def str_match():        return _(r'''(?s)('[^'\\]*(?:\\.[^'\\]*)*')|'''
-                                 r'''("[^"\\]*(?:\\.[^"\\]*)*")''')
-def comment():          return "//", _(".*\n")
+                                     r'''("[^"\\]*(?:\\.[^"\\]*)*")''')
+def comment():          return _("//.*\n", multiline=False)
 
 
 # Escape sequences supported in PEG literal string matches
diff --git a/arpeggio/tests/test_peg_parser.py b/arpeggio/tests/test_peg_parser.py
index 22e45a5..c796898 100644
--- a/arpeggio/tests/test_peg_parser.py
+++ b/arpeggio/tests/test_peg_parser.py
@@ -16,6 +16,7 @@
     factor <- ("+" / "-")?
               (number / "(" expression ")");
     // This is another comment
+    //
     term <- factor (( "*" / "/") factor)*;
     expression <- term (("+" / "-") term)*;
     calc <- expression+ EOF;