Utilities: Replace fgrep with grep --fixed-strings

Author: https://github.com/petelliott
Commit: https://github.com/SerenityOS/serenity/commit/d50de8e4ef
Pull-request: https://github.com/SerenityOS/serenity/pull/16134
Reviewed-by: https://github.com/alimpfard
Reviewed-by: https://github.com/gmta
Reviewed-by: https://github.com/linusg
Reviewed-by: https://github.com/timschumi ✅

Base/usr/share/man/man1/grep.md

@@ -5,13 +5,14 @@ grep
 ## Synopsis
 
 ```sh
-$ grep [--recursive] [--extended-regexp] [--regexp Pattern] [-i] [--line-numbers] [--invert-match] [--quiet] [--no-messages] [--binary-mode ] [--text] [-I] [--color WHEN] [--count] [file...]
+$ grep [--recursive] [--extended-regexp] [--fixed-strings] [--regexp Pattern] [-i] [--line-numbers] [--invert-match] [--quiet] [--no-messages] [--binary-mode ] [--text] [-I] [--color WHEN] [--count] [file...]
 ```
 
 ## Options:
 
 * `-r`, `--recursive`: Recursively scan files
 * `-E`, `--extended-regexp`: Extended regular expressions
+* `-F`, `--fixed-strings`: Treat pattern as a string, not a regexp
 * `-e Pattern`, `--regexp Pattern`: Pattern
 * `-i`: Make matches case-insensitive
 * `-n`, `--line-numbers`: Output line-numbers

Userland/Utilities/CMakeLists.txt

@@ -1,7 +1,7 @@
 file(GLOB CMD_SOURCES  CONFIGURE_DEPENDS "*.cpp")
 list(APPEND SPECIAL_TARGETS test install)
 list(APPEND REQUIRED_TARGETS
-    arp base64 basename cat chmod chown clear comm cp cut date dd df diff dirname dmesg du echo env expr false fgrep
+    arp base64 basename cat chmod chown clear comm cp cut date dd df diff dirname dmesg du echo env expr false
     file find grep groups head host hostname id ifconfig kill killall ln logout ls mkdir mount mv nproc
     pgrep pidof ping pkill pmap ps readlink realpath reboot rm rmdir route seq shutdown sleep sort stat stty su tail test
     touch tr true umount uname uniq uptime w wc which whoami xargs yes
@@ -65,6 +65,7 @@ if (ENABLE_JAKT)
 endif()
 
 install(CODE "file(CREATE_LINK grep ${CMAKE_INSTALL_PREFIX}/bin/egrep SYMBOLIC)")
+install(CODE "file(CREATE_LINK grep ${CMAKE_INSTALL_PREFIX}/bin/fgrep SYMBOLIC)")
 install(CODE "file(CREATE_LINK grep ${CMAKE_INSTALL_PREFIX}/bin/rgrep SYMBOLIC)")
 
 target_link_libraries(abench PRIVATE LibAudio)

Userland/Utilities/fgrep.cpp

@@ -1,30 +0,0 @@
-/*
- * Copyright (c) 2018-2020, Andreas Kling <kling@serenityos.org>
- *
- * SPDX-License-Identifier: BSD-2-Clause
- */
-
-#include <AK/Assertions.h>
-#include <AK/DeprecatedString.h>
-#include <AK/Format.h>
-#include <LibCore/System.h>
-#include <LibMain/Main.h>
-#include <stdio.h>
-
-ErrorOr<int> serenity_main(Main::Arguments arguments)
-{
-    if (arguments.strings.size() < 2) {
-        warnln("usage: fgrep <str>");
-        return 1;
-    }
-    for (;;) {
-        char buffer[4096];
-        fgets(buffer, sizeof(buffer), stdin);
-        auto str = StringView { buffer, strlen(buffer) };
-        if (str.contains(arguments.strings[1]))
-            TRY(Core::System::write(1, str.bytes()));
-        if (feof(stdin))
-            return 0;
-        VERIFY(str.to_deprecated_string().characters());
-    }
-}

Userland/Utilities/grep.cpp

@@ -8,6 +8,7 @@
 #include <AK/DeprecatedString.h>
 #include <AK/LexicalPath.h>
 #include <AK/ScopeGuard.h>
+#include <AK/StringBuilder.h>
 #include <AK/Vector.h>
 #include <LibCore/ArgsParser.h>
 #include <LibCore/DirIterator.h>
@@ -33,6 +34,21 @@ void fail(StringView format, Ts... args)
     abort();
 }
 
+constexpr StringView ere_special_characters = ".^$*+?()[{\\|"sv;
+constexpr StringView basic_special_characters = ".^$*[\\"sv;
+
+static DeprecatedString escape_characters(StringView string, StringView characters)
+{
+    StringBuilder builder;
+    for (auto ch : string) {
+        if (characters.contains(ch))
+            builder.append('\\');
+
+        builder.append(ch);
+    }
+    return builder.to_deprecated_string();
+}
+
 ErrorOr<int> serenity_main(Main::Arguments args)
 {
     TRY(Core::System::pledge("stdio rpath"));
@@ -43,6 +59,7 @@ ErrorOr<int> serenity_main(Main::Arguments args)
 
     bool recursive = (program_name == "rgrep"sv);
     bool use_ere = (program_name == "egrep"sv);
+    bool fixed_strings = (program_name == "fgrep"sv);
     Vector<DeprecatedString> patterns;
     BinaryFileMode binary_mode { BinaryFileMode::Binary };
     bool case_insensitive = false;
@@ -58,6 +75,7 @@ ErrorOr<int> serenity_main(Main::Arguments args)
     Core::ArgsParser args_parser;
     args_parser.add_option(recursive, "Recursively scan files", "recursive", 'r');
     args_parser.add_option(use_ere, "Extended regular expressions", "extended-regexp", 'E');
+    args_parser.add_option(fixed_strings, "Treat pattern as a string, not a regexp", "fixed-strings", 'F');
     args_parser.add_option(Core::ArgsParser::Option {
         .argument_mode = Core::ArgsParser::OptionArgumentMode::Required,
         .help_string = "Pattern",
@@ -144,6 +162,7 @@ ErrorOr<int> serenity_main(Main::Arguments args)
     auto grep_logic = [&](auto&& regular_expressions) {
         for (auto& re : regular_expressions) {
             if (re.parser_result.error != regex::Error::NoError) {
+                warnln("regex parse error: {}", regex::get_error_string(re.parser_result.error));
                 return 1;
             }
         }
@@ -296,14 +315,17 @@ ErrorOr<int> serenity_main(Main::Arguments args)
     if (use_ere) {
         Vector<Regex<PosixExtended>> regular_expressions;
         for (auto pattern : patterns) {
-            regular_expressions.append(Regex<PosixExtended>(pattern, options));
+            auto escaped_pattern = (fixed_strings) ? escape_characters(pattern, ere_special_characters) : pattern;
+            regular_expressions.append(Regex<PosixExtended>(escaped_pattern, options));
         }
         return grep_logic(regular_expressions);
     }
 
     Vector<Regex<PosixBasic>> regular_expressions;
     for (auto pattern : patterns) {
-        regular_expressions.append(Regex<PosixBasic>(pattern, options));
+        auto escaped_pattern = (fixed_strings) ? escape_characters(pattern, basic_special_characters) : pattern;
+        dbgln("'{}'", escaped_pattern);
+        regular_expressions.append(Regex<PosixBasic>(escaped_pattern, options));
     }
     return grep_logic(regular_expressions);
 }