Implement tr builtin command

SHELL_FEATURES.md

@@ -17,6 +17,7 @@ Blocked features are rejected before execution with exit code 2.
 - ✅ `ls [-1aAdFhlpRrSt] [FILE]...` — list directory contents
 - ✅ `strings [-a] [-n MIN] [-t o|d|x] [-o] [-f] [-s SEP] [FILE]...` — print printable character sequences in files (default min length 4); offsets via `-t`/`-o`; filename prefix via `-f`; custom separator via `-s`
 - ✅ `tail [-n N|-c N] [-q|-v] [-z] [FILE]...` — output the last part of files (default: last 10 lines); supports `+N` offset mode; `-f`/`--follow` is rejected
+- ✅ `tr [-cdsCt] SET1 [SET2]` — translate, squeeze, and/or delete characters from stdin
 - ✅ `true` — return exit code 0
 - ✅ `uniq [OPTION]... [INPUT]` — report or omit repeated lines
 - ✅ `wc [-l] [-w] [-c] [-m] [FILE]...` — count lines, words, bytes, or characters in files

interp/builtins/tr/builtin_tr_pentest_test.go

@@ -0,0 +1,194 @@
+// 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.
+
+// Exploratory pentest for the tr builtin.
+//
+// These tests probe edge cases in flag/argument handling, special input
+// patterns, memory safety boundaries, and behaviour-matching with GNU tr.
+
+package tr_test
+
+import (
+	"context"
+	"strings"
+	"testing"
+	"time"
+
+	"github.com/stretchr/testify/assert"
+
+	"github.com/DataDog/rshell/interp"
+)
+
+const pentestTimeout = 10 * time.Second
+
+func mustNotHang(t *testing.T, f func()) {
+	t.Helper()
+	done := make(chan struct{})
+	go func() {
+		defer close(done)
+		f()
+	}()
+	select {
+	case <-done:
+	case <-time.After(pentestTimeout):
+		t.Fatalf("operation did not complete within %s", pentestTimeout)
+	}
+}
+
+// --- Flag and argument injection ---
+
+func TestTrPentestUnknownLongFlag(t *testing.T) {
+	_, stderr, code := runScript(t, "tr --no-such-flag a b", t.TempDir())
+	assert.Equal(t, 1, code)
+	assert.Contains(t, stderr, "tr:")
+}
+
+func TestTrPentestDoubleDashOperands(t *testing.T) {
+	stdout, _, code := trRun(t, "aha", "-- ah -H")
+	assert.Equal(t, 0, code)
+	assert.Equal(t, "-H-", stdout)
+}
+
+func TestTrPentestBasicTranslation(t *testing.T) {
+	stdout, _, code := trRun(t, "abc", "a X")
+	assert.Equal(t, 0, code)
+	assert.Equal(t, "Xbc", stdout)
+}
+
+// --- Empty/whitespace operands ---
+
+func TestTrPentestEmptySet1(t *testing.T) {
+	dir := t.TempDir()
+	writeFile(t, dir, "in.txt", "abc")
+	_, _, code := runScript(t, `cat in.txt | tr '' '[.*]'`, dir, interp.AllowedPaths([]string{dir}))
+	assert.Equal(t, 0, code)
+}
+
+func TestTrPentestEmptySet2WithTruncate(t *testing.T) {
+	dir := t.TempDir()
+	writeFile(t, dir, "in.txt", "abc")
+	_, _, code := runScript(t, `cat in.txt | tr -t abc ''`, dir, interp.AllowedPaths([]string{dir}))
+	assert.Equal(t, 0, code)
+}
+
+// --- Context timeout on infinite source ---
+
+func TestTrPentestContextTimeout(t *testing.T) {
+	mustNotHang(t, func() {
+		ctx, cancel := context.WithTimeout(context.Background(), 2*time.Second)
+		defer cancel()
+		_, _, _ = runScriptCtx(ctx, t, "tr a b", t.TempDir())
+	})
+}
+
+// --- Large repetitive input ---
+
+func TestTrPentestLargeInput(t *testing.T) {
+	dir := t.TempDir()
+	large := strings.Repeat("a", 100000)
+	writeFile(t, dir, "in.txt", large)
+	stdout, _, code := runScript(t, "cat in.txt | tr a b", dir, interp.AllowedPaths([]string{dir}))
+	assert.Equal(t, 0, code)
+	expected := strings.Repeat("b", 100000)
+	assert.Equal(t, expected, stdout)
+}
+
+// --- Repeat construct edge cases ---
+
+func TestTrPentestRepeatFillEmptyCount(t *testing.T) {
+	stdout, _, code := trRun(t, "abcdef", "abcdef '1[x*]2'")
+	assert.Equal(t, 0, code)
+	assert.Equal(t, "1xxxx2", stdout)
+}
+
+func TestTrPentestRepeatOctal(t *testing.T) {
+	stdout, _, code := trRun(t, "abc", "abc '[b*3]'")
+	assert.Equal(t, 0, code)
+	assert.Equal(t, "bbb", stdout)
+}
+
+func TestTrPentestInvalidRepeatCount(t *testing.T) {
+	dir := t.TempDir()
+	writeFile(t, dir, "in.txt", "")
+	_, stderr, code := runScript(t, "cat in.txt | tr 'a' '[b*c]'", dir, interp.AllowedPaths([]string{dir}))
+	assert.Equal(t, 1, code)
+	assert.Contains(t, stderr, "invalid repeat count")
+}
+
+// --- Character class edge cases ---
+
+func TestTrPentestInvalidClassName(t *testing.T) {
+	_, stderr, code := trRun(t, "", "-d '[:bogus:]'")
+	assert.Equal(t, 1, code)
+	assert.Contains(t, stderr, "invalid character class")
+}
+
+func TestTrPentestDeleteAlnumDotsRemain(t *testing.T) {
+	stdout, _, code := trRun(t, ".abc123.", "-d '[:alnum:]'")
+	assert.Equal(t, 0, code)
+	assert.Equal(t, "..", stdout)
+}
+
+// --- Backslash escape edge cases ---
+
+func TestTrPentestOctalThreeDigit(t *testing.T) {
+	stdout, _, code := trRun(t, "XYZ", `XYZ '\0\11\77'`)
+	assert.Equal(t, 0, code)
+	assert.Equal(t, "\000\t?", stdout)
+}
+
+func TestTrPentestUnrecognizedEscape(t *testing.T) {
+	stdout, _, code := trRun(t, "q", `q '\q'`)
+	assert.Equal(t, 0, code)
+	assert.Equal(t, "q", stdout)
+}
+
+// --- Combined flags ---
+
+func TestTrPentestDeleteSqueezeCombined(t *testing.T) {
+	stdout, _, code := trRun(t, "a.b.c $$$$code\\", `-ds a-z '$.'`)
+	assert.Equal(t, 0, code)
+	assert.Equal(t, ". $\\", stdout)
+}
+
+func TestTrPentestComplementSqueeze(t *testing.T) {
+	stdout, _, code := trRun(t, "aaBBcDcc", "-sc a-z")
+	assert.Equal(t, 0, code)
+	assert.Equal(t, "aaBcDcc", stdout)
+}
+
+// --- Equivalence class edge cases ---
+
+func TestTrPentestMultiCharEquiv(t *testing.T) {
+	_, stderr, code := trRun(t, "", "-d '[=aa=]'")
+	assert.Equal(t, 1, code)
+	assert.Contains(t, stderr, "equivalence class operand must be a single character")
+}
+
+// --- Pipe integration ---
+
+func TestTrPentestPipeChain(t *testing.T) {
+	dir := t.TempDir()
+	writeFile(t, dir, "in.txt", "Hello World 123")
+	stdout, _, code := runScript(t, "cat in.txt | tr A-Z a-z | tr -d '[:digit:]'", dir, interp.AllowedPaths([]string{dir}))
+	assert.Equal(t, 0, code)
+	assert.Equal(t, "hello world ", stdout)
+}
+
+// --- Complement with delete ---
+
+func TestTrPentestComplementDeleteKeepAlpha(t *testing.T) {
+	stdout, _, code := trRun(t, "abc123!@#", "-dc '[:alpha:]'")
+	assert.Equal(t, 0, code)
+	assert.Equal(t, "abc", stdout)
+}
+
+// --- Big C flag ---
+
+func TestTrPentestBigCFlag(t *testing.T) {
+	stdout, _, code := trRun(t, "Phone: 01234 567890", "-d -C 0-9")
+	assert.Equal(t, 0, code)
+	assert.Equal(t, "01234567890", stdout)
+}