From e7634a8c0cbb1e1f6df16536646683db6d224426 Mon Sep 17 00:00:00 2001
From: "copilot-swe-agent[bot]" <198982749+Copilot@users.noreply.github.com>
Date: Mon, 6 Apr 2026 13:01:45 +0000
Subject: [PATCH 1/3] feat: add snort data syntax support for pm operator

Agent-Logs-Url: https://github.com/corazawaf/coraza/sessions/2ebb487b-5f51-4c42-b857-602201c80801

Co-authored-by: fzipi <3012076+fzipi@users.noreply.github.com>
---
 internal/operators/pm.go            | 93 +++++++++++++++++++++++++++--
 internal/operators/testdata/pm.json | 35 +++++++++++
 2 files changed, 122 insertions(+), 6 deletions(-)

diff --git a/internal/operators/pm.go b/internal/operators/pm.go
index 35e5b3244..717fc919e 100644
--- a/internal/operators/pm.go
+++ b/internal/operators/pm.go
@@ -6,6 +6,8 @@
 package operators
 
 import (
+	"fmt"
+	"strconv"
 	"strings"
 
 	ahocorasick "github.com/petar-dambovaliev/aho-corasick"
@@ -18,8 +20,9 @@ import (
 // multi-pattern searching. Matches space-separated keywords or patterns provided as arguments.
 //
 // Arguments:
-// Space-separated keywords or patterns to match. Supports Snort data syntax like "A|42|C|44|F"
-// for hex notation. All patterns are converted to lowercase for case-insensitive matching.
+// Space-separated keywords or patterns to match. Supports Snort data syntax where raw bytes
+// can be embedded using pipe-delimited hex notation, e.g. "A|42|C" or "|0d 0a|".
+// All patterns are converted to lowercase for case-insensitive matching.
 //
 // Returns:
 // true if any of the patterns are found in the input, false otherwise
@@ -31,6 +34,9 @@ import (
 //
 // # Match multiple attack patterns
 // SecRule ARGS "@pm <script> javascript: onerror=" "id:171,deny"
+//
+// # Match using snort data syntax with hex bytes: A + 0x42('B') + C + 0x44('D') + F = "ABCDF"
+// SecRule ARGS "@pm A|42|C|44|F" "id:172,deny"
 // ```
 type pm struct {
 	matcher ahocorasick.AhoCorasick
@@ -41,8 +47,11 @@ var _ plugintypes.Operator = (*pm)(nil)
 func newPM(options plugintypes.OperatorOptions) (plugintypes.Operator, error) {
 	data := options.Arguments
 
-	data = strings.ToLower(data)
-	dict := strings.Split(data, " ")
+	dict, err := parsePMArgs(data)
+	if err != nil {
+		return nil, err
+	}
+
 	builder := ahocorasick.NewAhoCorasickBuilder(ahocorasick.Opts{
 		AsciiCaseInsensitive: true,
 		MatchOnlyWholeWords:  false,
@@ -50,11 +59,83 @@ func newPM(options plugintypes.OperatorOptions) (plugintypes.Operator, error) {
 		DFA:                  true,
 	})
 
-	m, _ := memoizeDo(options.Memoizer, data, func() (any, error) { return builder.Build(dict), nil })
-	// TODO this operator is supposed to support snort data syntax: "@pm A|42|C|44|F"
+	m, _ := memoizeDo(options.Memoizer, strings.ToLower(data), func() (any, error) { return builder.Build(dict), nil })
 	return &pm{matcher: m.(ahocorasick.AhoCorasick)}, nil
 }
 
+// parsePMArgs parses the pm operator arguments, supporting Snort data syntax where raw bytes
+// can be embedded using pipe-delimited hex notation. For example, "A|42|C" is parsed as the
+// three-byte string "ABC" (since 0x42 = 'B'). Multiple hex bytes can be specified inside the
+// pipes separated by spaces, e.g. "|0d 0a|" becomes a CRLF sequence.
+//
+// Patterns are separated by spaces that appear outside of pipe blocks.
+func parsePMArgs(data string) ([]string, error) {
+	var patterns []string
+	var current strings.Builder
+	var hexBuf strings.Builder
+	inPipe := false
+
+	for i := 0; i < len(data); i++ {
+		c := data[i]
+		switch {
+		case c == '|':
+			if inPipe {
+				// End of pipe block – flush any remaining hex token.
+				if hexBuf.Len() > 0 {
+					b, err := parseHexByte(hexBuf.String())
+					if err != nil {
+						return nil, err
+					}
+					current.WriteByte(b)
+					hexBuf.Reset()
+				}
+				inPipe = false
+			} else {
+				inPipe = true
+			}
+		case inPipe && c == ' ':
+			// Space inside a pipe block is a hex-byte separator.
+			if hexBuf.Len() > 0 {
+				b, err := parseHexByte(hexBuf.String())
+				if err != nil {
+					return nil, err
+				}
+				current.WriteByte(b)
+				hexBuf.Reset()
+			}
+		case inPipe:
+			hexBuf.WriteByte(c)
+		case c == ' ':
+			// Space outside a pipe block is a pattern separator.
+			if current.Len() > 0 {
+				patterns = append(patterns, strings.ToLower(current.String()))
+				current.Reset()
+			}
+		default:
+			current.WriteByte(c)
+		}
+	}
+
+	if inPipe {
+		return nil, fmt.Errorf("unclosed pipe in snort data syntax")
+	}
+
+	if current.Len() > 0 {
+		patterns = append(patterns, strings.ToLower(current.String()))
+	}
+
+	return patterns, nil
+}
+
+// parseHexByte parses a one- or two-digit hexadecimal string into a byte.
+func parseHexByte(s string) (byte, error) {
+	b, err := strconv.ParseUint(strings.TrimSpace(s), 16, 8)
+	if err != nil {
+		return 0, fmt.Errorf("invalid hex value %q in snort data syntax: %w", s, err)
+	}
+	return byte(b), nil
+}
+
 func (o *pm) Evaluate(tx plugintypes.TransactionState, value string) bool {
 	return pmEvaluate(o.matcher, tx, value)
 }
diff --git a/internal/operators/testdata/pm.json b/internal/operators/testdata/pm.json
index 2c6aeff04..4d4702484 100644
--- a/internal/operators/testdata/pm.json
+++ b/internal/operators/testdata/pm.json
@@ -97,6 +97,41 @@
       "input" : "xxxyyyghi",
       "param" : "abc def ghi"
    },
+   {
+      "type" : "op",
+      "ret" : 1,
+      "name" : "pm",
+      "input" : "ABCDF",
+      "param" : "A|42|C|44|F"
+   },
+   {
+      "type" : "op",
+      "ret" : 1,
+      "name" : "pm",
+      "input" : "test\r\ndata",
+      "param" : "|0d 0a|"
+   },
+   {
+      "type" : "op",
+      "ret" : 0,
+      "name" : "pm",
+      "input" : "AXYF",
+      "param" : "A|42|C|44|F"
+   },
+   {
+      "type" : "op",
+      "ret" : 1,
+      "name" : "pm",
+      "input" : "hello\x01world",
+      "param" : "hello|01|world"
+   },
+   {
+      "type" : "op",
+      "ret" : 1,
+      "name" : "pm",
+      "input" : "abcdf",
+      "param" : "A|42|C|44|F"
+   },
    {
       "param" : "000 001 002 003 004 005 006 007 008 009 010 011 012 013 014 015 016 017 018 019 020 021 022 023 024 025 026 027 028 029 030 031 032 033 034 035 036 037 038 039 040 041 042 043 044 045 046 047 048 049 050 051 052 053 054 055 056 057 058 059 060 061 062 063 064 065 066 067 068 069 070 071 072 073 074 075 076 077 078 079 080 081 082 083 084 085 086 087 088 089 090 091 092 093 094 095 096 097 098 099 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999",
       "input" : "xxxyyy999",

From e334aa1827b1c8e3acbab692d5a785173b147e09 Mon Sep 17 00:00:00 2001
From: "copilot-swe-agent[bot]" <198982749+Copilot@users.noreply.github.com>
Date: Mon, 6 Apr 2026 13:03:50 +0000
Subject: [PATCH 2/3] feat: add unit tests for pm snort syntax and address code
 review feedback

Agent-Logs-Url: https://github.com/corazawaf/coraza/sessions/2ebb487b-5f51-4c42-b857-602201c80801

Co-authored-by: fzipi <3012076+fzipi@users.noreply.github.com>
---
 internal/operators/pm.go      |   2 +-
 internal/operators/pm_test.go | 150 ++++++++++++++++++++++++++++++++++
 2 files changed, 151 insertions(+), 1 deletion(-)
 create mode 100644 internal/operators/pm_test.go

diff --git a/internal/operators/pm.go b/internal/operators/pm.go
index 717fc919e..a8ceb35ed 100644
--- a/internal/operators/pm.go
+++ b/internal/operators/pm.go
@@ -49,7 +49,7 @@ func newPM(options plugintypes.OperatorOptions) (plugintypes.Operator, error) {
 
 	dict, err := parsePMArgs(data)
 	if err != nil {
-		return nil, err
+		return nil, fmt.Errorf("failed to parse pm operator arguments: %w", err)
 	}
 
 	builder := ahocorasick.NewAhoCorasickBuilder(ahocorasick.Opts{
diff --git a/internal/operators/pm_test.go b/internal/operators/pm_test.go
new file mode 100644
index 000000000..88347f1b5
--- /dev/null
+++ b/internal/operators/pm_test.go
@@ -0,0 +1,150 @@
+// Copyright 2022 Juan Pablo Tosso and the OWASP Coraza contributors
+// SPDX-License-Identifier: Apache-2.0
+
+package operators
+
+import (
+	"testing"
+
+	"github.com/corazawaf/coraza/v3/experimental/plugins/plugintypes"
+	"github.com/corazawaf/coraza/v3/internal/corazawaf"
+)
+
+func TestParsePMArgs(t *testing.T) {
+	tests := []struct {
+		name     string
+		input    string
+		expected []string
+		wantErr  bool
+	}{
+		{
+			name:     "plain patterns",
+			input:    "hello world",
+			expected: []string{"hello", "world"},
+		},
+		{
+			name:     "single pattern",
+			input:    "test",
+			expected: []string{"test"},
+		},
+		{
+			name:     "snort hex inline: A|42|C|44|F",
+			input:    "A|42|C|44|F",
+			expected: []string{"abcdf"},
+		},
+		{
+			name:     "snort hex only: |41|",
+			input:    "|41|",
+			expected: []string{"a"},
+		},
+		{
+			name:     "snort multiple hex bytes in one block: |41 42 43|",
+			input:    "|41 42 43|",
+			expected: []string{"abc"},
+		},
+		{
+			name:     "snort CRLF: |0d 0a|",
+			input:    "|0d 0a|",
+			expected: []string{"\r\n"},
+		},
+		{
+			name:     "snort non-letter byte: |01|",
+			input:    "|01|",
+			expected: []string{"\x01"},
+		},
+		{
+			name:     "uppercase literal normalised to lowercase",
+			input:    "ABC",
+			expected: []string{"abc"},
+		},
+		{
+			name:     "snort hex letter normalised to lowercase: |41|",
+			input:    "|41|",
+			expected: []string{"a"},
+		},
+		{
+			name:    "unclosed pipe",
+			input:   "A|42",
+			wantErr: true,
+		},
+		{
+			name:    "invalid hex value",
+			input:   "|ZZ|",
+			wantErr: true,
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			got, err := parsePMArgs(tt.input)
+			if tt.wantErr {
+				if err == nil {
+					t.Errorf("parsePMArgs(%q) expected error but got nil, result: %v", tt.input, got)
+				}
+				return
+			}
+			if err != nil {
+				t.Errorf("parsePMArgs(%q) unexpected error: %v", tt.input, err)
+				return
+			}
+			if len(got) != len(tt.expected) {
+				t.Errorf("parsePMArgs(%q) = %v (len %d), want %v (len %d)", tt.input, got, len(got), tt.expected, len(tt.expected))
+				return
+			}
+			for i := range got {
+				if got[i] != tt.expected[i] {
+					t.Errorf("parsePMArgs(%q)[%d] = %q, want %q", tt.input, i, got[i], tt.expected[i])
+				}
+			}
+		})
+	}
+}
+
+func TestPMSnortSyntax(t *testing.T) {
+	tests := []struct {
+		name      string
+		param     string
+		input     string
+		wantMatch bool
+	}{
+		{
+			name:      "hex bytes inline: A|42|C|44|F matches ABCDF",
+			param:     "A|42|C|44|F",
+			input:     "ABCDF",
+			wantMatch: true,
+		},
+		{
+			name:      "hex bytes inline: A|42|C|44|F does not match AXYF",
+			param:     "A|42|C|44|F",
+			input:     "AXYF",
+			wantMatch: false,
+		},
+		{
+			name:      "hex CRLF matches CRLF in input",
+			param:     "|0d 0a|",
+			input:     "line1\r\nline2",
+			wantMatch: true,
+		},
+		{
+			name:      "case insensitive: lowercase input matches uppercase pattern encoded as hex",
+			param:     "A|42|C|44|F",
+			input:     "abcdf",
+			wantMatch: true,
+		},
+	}
+
+	waf := corazawaf.NewWAF()
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			op, err := newPM(plugintypes.OperatorOptions{Arguments: tt.param})
+			if err != nil {
+				t.Fatalf("newPM(%q) unexpected error: %v", tt.param, err)
+			}
+			tx := waf.NewTransaction()
+			got := op.Evaluate(tx, tt.input)
+			if got != tt.wantMatch {
+				t.Errorf("pm(%q).Evaluate(%q) = %v, want %v", tt.param, tt.input, got, tt.wantMatch)
+			}
+		})
+	}
+}

From 842d22a4338cf72e46017a3ff8f7008afb2a9a09 Mon Sep 17 00:00:00 2001
From: "copilot-swe-agent[bot]" <198982749+Copilot@users.noreply.github.com>
Date: Mon, 6 Apr 2026 13:49:49 +0000
Subject: [PATCH 3/3] test: add full coverage tests for pm snort syntax
 implementation

Agent-Logs-Url: https://github.com/corazawaf/coraza/sessions/bf792533-4ef4-4be3-8c71-38d5647544f9

Co-authored-by: fzipi <3012076+fzipi@users.noreply.github.com>
---
 internal/operators/pm_test.go | 115 +++++++++++++++++++++++++++++++++-
 1 file changed, 114 insertions(+), 1 deletion(-)

diff --git a/internal/operators/pm_test.go b/internal/operators/pm_test.go
index 88347f1b5..ce67ea781 100644
--- a/internal/operators/pm_test.go
+++ b/internal/operators/pm_test.go
@@ -27,6 +27,16 @@ func TestParsePMArgs(t *testing.T) {
 			input:    "test",
 			expected: []string{"test"},
 		},
+		{
+			name:     "empty string",
+			input:    "",
+			expected: nil,
+		},
+		{
+			name:     "only spaces",
+			input:    "   ",
+			expected: nil,
+		},
 		{
 			name:     "snort hex inline: A|42|C|44|F",
 			input:    "A|42|C|44|F",
@@ -62,16 +72,31 @@ func TestParsePMArgs(t *testing.T) {
 			input:    "|41|",
 			expected: []string{"a"},
 		},
+		{
+			name:     "multiple patterns with snort syntax",
+			input:    "A|42|C |44|F",
+			expected: []string{"abc", "df"},
+		},
+		{
+			name:     "snort syntax mixed with plain pattern",
+			input:    "plain |41 42| mixed",
+			expected: []string{"plain", "ab", "mixed"},
+		},
 		{
 			name:    "unclosed pipe",
 			input:   "A|42",
 			wantErr: true,
 		},
 		{
-			name:    "invalid hex value",
+			name:    "invalid hex value at end of pipe block",
 			input:   "|ZZ|",
 			wantErr: true,
 		},
+		{
+			name:    "invalid hex value before space inside pipe block",
+			input:   "|ZZ FF|",
+			wantErr: true,
+		},
 	}
 
 	for _, tt := range tests {
@@ -131,6 +156,30 @@ func TestPMSnortSyntax(t *testing.T) {
 			input:     "abcdf",
 			wantMatch: true,
 		},
+		{
+			name:      "plain pattern still works",
+			param:     "foo bar",
+			input:     "here is bar",
+			wantMatch: true,
+		},
+		{
+			name:      "plain pattern no match",
+			param:     "foo bar",
+			input:     "nothing here",
+			wantMatch: false,
+		},
+		{
+			name:      "snort hex only pattern matches",
+			param:     "|41 42 43|",
+			input:     "xABCy",
+			wantMatch: true,
+		},
+		{
+			name:      "snort non-printable byte matches",
+			param:     "prefix|01|suffix",
+			input:     "prefix\x01suffix",
+			wantMatch: true,
+		},
 	}
 
 	waf := corazawaf.NewWAF()
@@ -148,3 +197,67 @@ func TestPMSnortSyntax(t *testing.T) {
 		})
 	}
 }
+
+func TestNewPMInvalidArgs(t *testing.T) {
+	invalidCases := []struct {
+		name  string
+		param string
+	}{
+		{name: "unclosed pipe", param: "A|42"},
+		{name: "invalid hex", param: "|ZZ|"},
+		{name: "invalid hex before space in pipe", param: "|ZZ FF|"},
+	}
+
+	for _, tt := range invalidCases {
+		t.Run(tt.name, func(t *testing.T) {
+			_, err := newPM(plugintypes.OperatorOptions{Arguments: tt.param})
+			if err == nil {
+				t.Errorf("newPM(%q) expected error but got nil", tt.param)
+			}
+		})
+	}
+}
+
+func TestPMEvaluateWithCapture(t *testing.T) {
+	waf := corazawaf.NewWAF()
+
+	t.Run("capture mode returns matches", func(t *testing.T) {
+		op, err := newPM(plugintypes.OperatorOptions{Arguments: "foo bar baz"})
+		if err != nil {
+			t.Fatalf("newPM: unexpected error: %v", err)
+		}
+		tx := waf.NewTransaction()
+		tx.Capture = true
+		if !op.Evaluate(tx, "foo and bar") {
+			t.Error("expected match but got none")
+		}
+	})
+
+	t.Run("capture mode no match returns false", func(t *testing.T) {
+		op, err := newPM(plugintypes.OperatorOptions{Arguments: "foo bar"})
+		if err != nil {
+			t.Fatalf("newPM: unexpected error: %v", err)
+		}
+		tx := waf.NewTransaction()
+		tx.Capture = true
+		if op.Evaluate(tx, "nothing to see here") {
+			t.Error("expected no match but got one")
+		}
+	})
+
+	t.Run("capture mode stops after 10 matches", func(t *testing.T) {
+		// Build a pattern that can match many times in one string.
+		// "a" will match every 'a' in the input.
+		op, err := newPM(plugintypes.OperatorOptions{Arguments: "a"})
+		if err != nil {
+			t.Fatalf("newPM: unexpected error: %v", err)
+		}
+		tx := waf.NewTransaction()
+		tx.Capture = true
+		// 15 'a' chars separated by '-' to ensure 15 distinct matches.
+		input := "a-a-a-a-a-a-a-a-a-a-a-a-a-a-a"
+		if !op.Evaluate(tx, input) {
+			t.Error("expected match but got none")
+		}
+	})
+}