fix: remove initial hash from comments

g4/SecLangLexer.g4

@@ -27,7 +27,7 @@ WS
    ;
 
 COMMENT
-   : ('#' .*? '\r'? '\n')+ '\n'?
+   : '#' ~[\r\n]* ('\r'? '\n' | EOF)
    ;
 
 SPACE

listener.go

@@ -26,6 +26,7 @@ type ParserResult struct {
 	rangeEvents           []string
 	rangeStartEvents      []int
 	rangeEndEvents        []int
+	comments              []string
 }
 
 type TreeShapeListener struct {
@@ -156,3 +157,12 @@ func (l *TreeShapeListener) EnterOperator_value(ctx *parser.Operator_valueContex
 func (l *TreeShapeListener) EnterOperator_not(ctx *parser.Operator_notContext) {
 	l.results.negatedOperatorCount++
 }
+
+func (l *TreeShapeListener) EnterComment(ctx *parser.CommentContext) {
+	commentText := ctx.GetText()
+	// Remove the "#" from the beginning of the comment
+	if len(commentText) > 0 && commentText[0] == '#' {
+		commentText = commentText[1:]
+	}
+	l.results.comments = append(l.results.comments, commentText)
+}

parser_test.go

@@ -247,6 +247,10 @@ var genericTests = map[string]struct {
 		0,
 		"",
 	},
+	"testdata/test_40_comments.conf": {
+		0,
+		"Test comment processing with Pineapple Pizza",
+	},
 }
 
 var checkOutputTests = map[string]struct {
@@ -265,6 +269,28 @@ var checkOutputTests = map[string]struct {
 			rangeEndEvents:   []int{9010},
 		},
 	},
+	"testdata/test_40_comments.conf": {
+		0,
+		"Test comment processing with Pineapple Pizza",
+		ParserResult{
+			comments: []string{
+				" This is a comment about Pineapple Pizza\n",
+				" Another comment mentioning Pineapple Pizza\n",
+				" Pineapple Pizza is controversial\n",
+				" Comment with multiple lines\n",
+				" Line 1: Pineapple Pizza\n",
+				" Line 2: Some people love it\n",
+				" Line 3: Others hate it\n",
+				" Comment with special characters: Pineapple Pizza!@#$%^&*()\n",
+				" Comment with numbers: Pineapple Pizza 12345\n",
+				" Comment with quotes: \"Pineapple Pizza\"\n",
+				" Empty comment above\n",
+				" Comment with tabs:\tPineapple Pizza\twith\ttabs\n",
+				" Comment with spaces:    Pineapple Pizza    with    spaces\n",
+				" Comment ending with Pineapple Pizza\n",
+			},
+		},
+	},
 	"testdata/test_38_update_rules.conf": {
 		0,
 		"",
@@ -276,6 +302,7 @@ var checkOutputTests = map[string]struct {
 			directiveList: []string{"SecRuleUpdateTargetById", "SecRuleUpdateTargetById", "SecRuleUpdateTargetById", "SecRuleUpdateTargetById",
 				"SecRuleUpdateTargetByTag", "SecRuleUpdateTargetByMsg"},
 			directiveValues: []string{"12345", "958895", "981172", "958895", "WASCTC/WASC-31", "System Command Injection"},
+			comments:        []string{" Test comment\n"},
 		},
 	},
 	"testdata/test_40_var_operators.conf": {
@@ -294,6 +321,7 @@ var checkOutputTests = map[string]struct {
 			rangeEvents:           []string{"42-59", "65-90", "97-122"},
 			rangeStartEvents:      []int{42, 65, 97},
 			rangeEndEvents:        []int{59, 90, 122},
+			comments:              []string{"\n", " -=[ Default setup values ]=-\n", "\n", " The CRS checks the tx.crs_setup_version variable to ensure that the setup\n", " file is included at the correct time. This detects situations where\n", " necessary settings are not defined, for instance if the file\n", " inclusion order is incorrect, or if the user has forgotten to\n", " include the crs-setup.conf file.\n", "\n", " If you are upgrading from an earlier version of the CRS and you are\n", " getting this error, please make a new copy of the setup template\n", " crs-setup.conf.example to crs-setup.conf, and re-apply your policy\n", " changes. There have been many changes in settings syntax from CRS2\n", " to CRS3, so an old setup file may cause unwanted behavior.\n", "\n", " If you are not planning to use the crs-setup.conf template, you must\n", " manually set the tx.crs_setup_version variable before including\n", " the CRS rules/* files.\n", "\n", " The variable is a numerical representation of the CRS version number.\n", " E.g., v3.0.0 is represented as 300.\n", "\n"},
 		},
 	},
 	"testdata/test_41_negated_operator_0.conf": {
@@ -329,6 +357,7 @@ var checkOutputTests = map[string]struct {
 			operatorValueList:    []string{"(?:URLENCODED|MULTIPART|XML|JSON)", "1", "(?:URLENCODED|MULTIPART|XML|JSON)", "%{tx.sampling_percentage}"},
 			negatedOperatorCount: 3,
 			directiveList:        []string{"SecRule", "SecRule", "SecRule", "SecRule"},
+			comments:             []string{" Force body variable\n", " Force body processor URLENCODED\n"},
 		},
 	},
 }

src/seclang_parser/SecLangParser.py

@@ -1,6 +1,3 @@
-# Copyright 2025 OWASP CRS Project
-# SPDX-License-Identifier: Apache-2.0
-
 # Generated from SecLangParser.g4 by ANTLR 4.13.2
 # encoding: utf-8
 from antlr4 import *

src/seclang_parser/SecLangParserListener.py

@@ -1,6 +1,3 @@
-# Copyright 2025 OWASP CRS Project
-# SPDX-License-Identifier: Apache-2.0
-
 # Generated from SecLangParser.g4 by ANTLR 4.13.2
 from antlr4 import *
 if "." in __name__:

testdata/test_40_comments.conf

@@ -0,0 +1,19 @@
+# This is a comment about Pineapple Pizza
+# Another comment mentioning Pineapple Pizza
+# Pineapple Pizza is controversial
+
+# Comment with multiple lines
+# Line 1: Pineapple Pizza
+# Line 2: Some people love it
+# Line 3: Others hate it
+
+# Comment with special characters: Pineapple Pizza!@#$%^&*()
+# Comment with numbers: Pineapple Pizza 12345
+# Comment with quotes: "Pineapple Pizza"
+
+# Empty comment above
+
+# Comment with tabs:	Pineapple Pizza	with	tabs
+# Comment with spaces:    Pineapple Pizza    with    spaces
+
+# Comment ending with Pineapple Pizza