From a67642f0070b87b7a9ba442a6f46795580217ae9 Mon Sep 17 00:00:00 2001
From: Aaron Lasseigne <aaron@modeanalytics.com>
Date: Tue, 22 Feb 2022 19:37:44 -0600
Subject: [PATCH] escape troublesome characters in regexp expressions

Found this issue while parsing the ABNF JSON string representation.
These two rules caused parsing issues because of the characters
generated within the regular expressions that they result in:

escape    = %x5C ; \
unescaped = %x20-21 / %x23-5B / %x5D-10FFFF ; [ -!] / [#-[] / []-\u{10FFF}]
---
 lib/ebnf/rule.rb  | 12 +++++++++---
 spec/rule_spec.rb |  6 +++++-
 2 files changed, 14 insertions(+), 4 deletions(-)

diff --git a/lib/ebnf/rule.rb b/lib/ebnf/rule.rb
index 39625e6..37fb189 100644
--- a/lib/ebnf/rule.rb
+++ b/lib/ebnf/rule.rb
@@ -367,11 +367,11 @@ def to_peg
     def to_regexp
       case expr.first
       when :hex
-        Regexp.new(translate_codepoints(expr[1]))
+        Regexp.new(Regexp.escape(translate_codepoints(expr[1])))
       when :istr
         /#{expr.last}/ui
       when :range
-        Regexp.new("[#{translate_codepoints(expr[1])}]")
+        Regexp.new("[#{escape_regexp_character_range(translate_codepoints(expr[1]))}]")
       else
         raise "Can't turn #{expr.inspect} into a regexp"
       end
@@ -770,5 +770,11 @@ def make_sym_id(variation = nil)
       @id_seq += 1
       ["_#{@sym}_#{@id_seq}#{variation}".to_sym, ("#{@id}.#{@id_seq}#{variation}" if @id)]
     end
+
+    # Escape "[", "]", and "\" in ranges so they don't result in a warning or error
+    # about empty character classes.
+    def escape_regexp_character_range(character_range)
+      character_range.gsub(/([\[\]\\])/) {|char| "\\#{char}"}
+    end
   end
-end
\ No newline at end of file
+end
diff --git a/spec/rule_spec.rb b/spec/rule_spec.rb
index bffb777..a11f56a 100644
--- a/spec/rule_spec.rb
+++ b/spec/rule_spec.rb
@@ -481,9 +481,13 @@
   describe "#to_regexp" do
     {
       hex: [:hex, "#x20", / /],
+      hex: [:hex, "#x5c", /\\/],
       range: [:range, "a-b", /[a-b]/],
       range2: [:range, "a-zA-Z", /[a-zA-Z]/],
       range3: [:range, "abc-", /[abc-]/],
+      range4: [:range, "#x23-#x5b", /[#-\[]/],
+      range5: [:range, "#x5d-#x5e", /[\]-^]/],
+      range6: [:range, "#x5c-#x5e", /[\\-^]/],
     }.each do |title, (op, exp, regexp)|
       it title do
         expect(EBNF::Rule.new(title, nil, [op, exp]).to_regexp).to eql regexp
@@ -1055,4 +1059,4 @@
       end
     end
   end
-end
\ No newline at end of file
+end