Re-implement cat builtin with full flag support

interp/builtins/cat/builtin_cat_pentest_test.go

@@ -0,0 +1,299 @@
+// Unless explicitly stated otherwise all files in this repository are licensed
+// under the Apache License Version 2.0.
+// This product includes software developed at Datadog (https://www.datadoghq.com/).
+// Copyright 2026-present Datadog, Inc.
+
+package cat_test
+
+import (
+	"context"
+	"math"
+	"os"
+	"path/filepath"
+	"strings"
+	"testing"
+	"time"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+
+	"github.com/DataDog/rshell/interp"
+	"github.com/DataDog/rshell/interp/builtins/cat"
+	"github.com/DataDog/rshell/interp/builtins/testutil"
+)
+
+const pentestTimeout = 10 * time.Second
+
+func catRun(t *testing.T, script, dir string, extraPaths ...string) (string, string, int) {
+	t.Helper()
+	paths := append([]string{dir}, extraPaths...)
+	return testutil.RunScript(t, script, dir, interp.AllowedPaths(paths))
+}
+
+func catRunCtx(ctx context.Context, t *testing.T, script, dir string) (string, string, int) {
+	t.Helper()
+	return testutil.RunScriptCtx(ctx, t, script, dir, interp.AllowedPaths([]string{dir}))
+}
+
+func mustNotHang(t *testing.T, fn func()) {
+	t.Helper()
+	done := make(chan struct{})
+	go func() {
+		fn()
+		close(done)
+	}()
+	select {
+	case <-done:
+	case <-time.After(pentestTimeout):
+		t.Fatal("operation did not complete within timeout")
+	}
+}
+
+// --- Flag and argument injection ---
+
+func TestCatPentestUnknownLongFlag(t *testing.T) {
+	dir := t.TempDir()
+	_, stderr, code := catRun(t, "cat --no-such-flag file.txt", dir)
+	assert.Equal(t, 1, code)
+	assert.Contains(t, stderr, "cat:")
+}
+
+func TestCatPentestUnknownShortFlag(t *testing.T) {
+	dir := t.TempDir()
+	_, stderr, code := catRun(t, "cat -f file.txt", dir)
+	assert.Equal(t, 1, code)
+	assert.Contains(t, stderr, "cat:")
+}
+
+func TestCatPentestFlagViaExpansion(t *testing.T) {
+	dir := t.TempDir()
+	writeFile(t, dir, "file.txt", "ok\n")
+	_, stderr, code := catRun(t, `for flag in -f; do cat $flag file.txt; done`, dir)
+	assert.Equal(t, 1, code)
+	assert.Contains(t, stderr, "cat:")
+}
+
+func TestCatPentestDoubleDashThenFlagLikeFile(t *testing.T) {
+	dir := t.TempDir()
+	writeFile(t, dir, "-n", "content\n")
+	stdout, _, code := catRun(t, "cat -- -n", dir)
+	assert.Equal(t, 0, code)
+	assert.Equal(t, "content\n", stdout)
+}
+
+func TestCatPentestMultipleStdinDash(t *testing.T) {
+	dir := t.TempDir()
+	writeFile(t, dir, "src.txt", "hello\n")
+	stdout, _, code := catRun(t, "cat - - < src.txt", dir)
+	assert.Equal(t, 0, code)
+	assert.Equal(t, "hello\n", stdout)
+}
+
+// --- Path and filename edge cases ---
+
+func TestCatPentestNonexistentFile(t *testing.T) {
+	dir := t.TempDir()
+	_, stderr, code := catRun(t, "cat does_not_exist", dir)
+	assert.Equal(t, 1, code)
+	assert.Contains(t, stderr, "cat:")
+}
+
+func TestCatPentestDirectoryAsFile(t *testing.T) {
+	dir := t.TempDir()
+	require.NoError(t, os.Mkdir(filepath.Join(dir, "subdir"), 0755))
+	_, stderr, code := catRun(t, "cat subdir", dir)
+	assert.Equal(t, 1, code)
+	assert.Contains(t, stderr, "cat:")
+}
+
+func TestCatPentestEmptyStringFilename(t *testing.T) {
+	dir := t.TempDir()
+	_, stderr, code := catRun(t, `cat ""`, dir)
+	assert.Equal(t, 1, code)
+	assert.Contains(t, stderr, "cat:")
+}
+
+func TestCatPentestPathTraversal(t *testing.T) {
+	dir := t.TempDir()
+	outer := t.TempDir()
+	require.NoError(t, os.WriteFile(filepath.Join(outer, "secret.txt"), []byte("secret"), 0644))
+	outerPath := strings.ReplaceAll(filepath.Join(outer, "secret.txt"), `\`, `/`)
+	_, stderr, code := catRun(t, "cat "+outerPath, dir)
+	assert.Equal(t, 1, code)
+	assert.Contains(t, stderr, "cat:")
+}
+
+// --- Long lines ---
+
+func TestCatPentestLineAtCapMinus1(t *testing.T) {
+	dir := t.TempDir()
+	content := make([]byte, cat.MaxLineBytes-1)
+	for i := range content {
+		content[i] = 'a'
+	}
+	content = append(content, '\n')
+	require.NoError(t, os.WriteFile(filepath.Join(dir, "file.txt"), content, 0644))
+	stdout, _, code := catRun(t, "cat -n file.txt", dir)
+	assert.Equal(t, 0, code)
+	assert.Contains(t, stdout, "     1\t")
+}
+
+func TestCatPentestLineAtCapExact(t *testing.T) {
+	dir := t.TempDir()
+	content := make([]byte, cat.MaxLineBytes)
+	for i := range content {
+		content[i] = 'a'
+	}
+	require.NoError(t, os.WriteFile(filepath.Join(dir, "file.txt"), content, 0644))
+	_, _, code := catRun(t, "cat -n file.txt", dir)
+	assert.Equal(t, 1, code)
+}
+
+func TestCatPentestLineAtCapPlus1(t *testing.T) {
+	dir := t.TempDir()
+	content := make([]byte, cat.MaxLineBytes+1)
+	for i := range content {
+		content[i] = 'a'
+	}
+	require.NoError(t, os.WriteFile(filepath.Join(dir, "file.txt"), content, 0644))
+	_, stderr, code := catRun(t, "cat -n file.txt", dir)
+	assert.Equal(t, 1, code)
+	assert.Contains(t, stderr, "cat:")
+}
+
+// --- Memory / resource exhaustion ---
+
+func TestCatPentestSmallFileRawMode(t *testing.T) {
+	dir := t.TempDir()
+	writeFile(t, dir, "tiny.txt", "small\n")
+	mustNotHang(t, func() {
+		stdout, _, code := catRun(t, "cat tiny.txt", dir)
+		assert.Equal(t, 0, code)
+		assert.Equal(t, "small\n", stdout)
+	})
+}
+
+func TestCatPentestManyFiles(t *testing.T) {
+	dir := t.TempDir()
+	var args []string
+	for i := 0; i < 200; i++ {
+		name := "f" + strings.Repeat("0", 3-len(string(rune('0'+i/100)))) + string(rune('0'+i/100)) + string(rune('0'+i%100/10)) + string(rune('0'+i%10)) + ".txt"
+		writeFile(t, dir, name, "line\n")
+		args = append(args, name)
+	}
+	mustNotHang(t, func() {
+		_, _, code := catRun(t, "cat "+strings.Join(args, " "), dir)
+		assert.Equal(t, 0, code)
+	})
+}
+
+func TestCatPentestLargeFileNumbered(t *testing.T) {
+	dir := t.TempDir()
+	var sb strings.Builder
+	for i := 0; i < 10000; i++ {
+		sb.WriteString("line\n")
+	}
+	writeFile(t, dir, "big.txt", sb.String())
+	mustNotHang(t, func() {
+		stdout, _, code := catRun(t, "cat -n big.txt", dir)
+		assert.Equal(t, 0, code)
+		assert.Contains(t, stdout, " 10000\t")
+	})
+}
+
+// --- Special files / infinite sources ---
+
+func TestCatPentestDevNull(t *testing.T) {
+	if os.DevNull == "NUL" {
+		// Windows reserved device names (NUL, CON, etc.) are blocked by the
+		// sandbox to prevent hangs — same as head's TestHeadWindowsReservedName.
+		dir := t.TempDir()
+		mustNotHang(t, func() {
+			_, stderr, code := catRun(t, "cat NUL", dir)
+			assert.Equal(t, 1, code)
+			assert.Contains(t, stderr, "cat:")
+		})
+		return
+	}
+	dir := t.TempDir()
+	mustNotHang(t, func() {
+		stdout, _, code := catRun(t, "cat "+os.DevNull, dir, filepath.Dir(os.DevNull))
+		assert.Equal(t, 0, code)
+		assert.Equal(t, "", stdout)
+	})
+}
+
+func TestCatPentestContextCancelledDuringRaw(t *testing.T) {
+	dir := t.TempDir()
+	writeFile(t, dir, "file.txt", strings.Repeat("x\n", 10000))
+	ctx, cancel := context.WithTimeout(context.Background(), 2*time.Second)
+	defer cancel()
+	mustNotHang(t, func() {
+		catRunCtx(ctx, t, "cat file.txt", dir)
+	})
+}
+
+func TestCatPentestContextCancelledDuringLines(t *testing.T) {
+	dir := t.TempDir()
+	writeFile(t, dir, "file.txt", strings.Repeat("x\n", 10000))
+	ctx, cancel := context.WithTimeout(context.Background(), 2*time.Second)
+	defer cancel()
+	mustNotHang(t, func() {
+		catRunCtx(ctx, t, "cat -n file.txt", dir)
+	})
+}
+
+// --- Integer edge cases in line numbering ---
+
+func TestCatPentestLineNumberMaxInt(t *testing.T) {
+	dir := t.TempDir()
+	writeFile(t, dir, "file.txt", "hello\n")
+	mustNotHang(t, func() {
+		stdout, _, code := catRun(t, "cat -n file.txt", dir)
+		assert.Equal(t, 0, code)
+		assert.Equal(t, "     1\thello\n", stdout)
+	})
+}
+
+func TestCatPentestLineNumberWidthOverflow(t *testing.T) {
+	_ = math.MaxInt64
+	dir := t.TempDir()
+	writeFile(t, dir, "file.txt", "hello\n")
+	stdout, _, code := catRun(t, "cat -n file.txt", dir)
+	assert.Equal(t, 0, code)
+	assert.Contains(t, stdout, "     1\t")
+}
+
+// --- Behavior matching ---
+
+func TestCatPentestSqueezeOnlyAffectsBlankLines(t *testing.T) {
+	dir := t.TempDir()
+	writeFile(t, dir, "file.txt", "a\n \n \nb\n")
+	stdout, _, code := catRun(t, "cat -s file.txt", dir)
+	assert.Equal(t, 0, code)
+	assert.Equal(t, "a\n \n \nb\n", stdout)
+}
+
+func TestCatPentestCRLFNotBlank(t *testing.T) {
+	dir := t.TempDir()
+	writeFile(t, dir, "file.txt", "a\n\r\n\r\nb\n")
+	stdout, _, code := catRun(t, "cat -s file.txt", dir)
+	assert.Equal(t, 0, code)
+	assert.Equal(t, "a\n\r\n\r\nb\n", stdout)
+}
+
+func TestCatPentestShowEndsCRLFNoV(t *testing.T) {
+	dir := t.TempDir()
+	writeFile(t, dir, "file.txt", "a\rb\r\nc\n\r\nd\r")
+	stdout, _, code := catRun(t, "cat -E file.txt", dir)
+	assert.Equal(t, 0, code)
+	assert.Equal(t, "a\rb^M$\nc$\n^M$\nd\r", stdout)
+}
+
+func TestCatPentestShowEndsCRLFWithV(t *testing.T) {
+	dir := t.TempDir()
+	writeFile(t, dir, "file.txt", "a\r\nb\n")
+	stdout, _, code := catRun(t, "cat -vE file.txt", dir)
+	assert.Equal(t, 0, code)
+	assert.Equal(t, "a^M$\nb$\n", stdout)
+}