Merge branch 'busybox' into merge

4 files changed, 259 insertions, 53 deletions

diff --git a/libbb/Config.src b/libbb/Config.src
index 6ba256290..00804e31e 100644
--- a/libbb/Config.src
+++ b/libbb/Config.src
@@ -7,6 +7,30 @@ menu "Busybox Library Tuning"
 
 INSERT
 
+choice
+        prompt "Buffer allocation policy"
+        default FEATURE_BUFFERS_USE_MALLOC
+        help
+          There are 3 ways BusyBox can handle buffer allocations:
+          - Use malloc. This costs code size for the call to xmalloc.
+          - Put them on stack. For some very small machines with limited stack
+            space, this can be deadly. For most folks, this works just fine.
+          - Put them in BSS. This works beautifully for computers with a real
+            MMU (and OS support), but wastes runtime RAM for uCLinux. This
+            behavior was the only one available for BusyBox versions 0.48 and
+            earlier.
+
+config FEATURE_BUFFERS_USE_MALLOC
+        bool "Allocate with Malloc"
+
+config FEATURE_BUFFERS_GO_ON_STACK
+        bool "Allocate on the Stack"
+
+config FEATURE_BUFFERS_GO_IN_BSS
+        bool "Allocate in the .bss section"
+
+endchoice
+
 config PASSWORD_MINLEN
         int "Minimum password length"
         default 6
@@ -153,6 +177,131 @@ config FEATURE_EDITING_ASK_TERMINAL
           correctly, or want to save on code size (about 400 bytes),
           then do not turn this option on.
 
+config LOCALE_SUPPORT
+        bool "Enable locale support (system needs locale for this to work)"
+        default n
+        help
+          Enable this if your system has locale support and you would like
+          busybox to support locale settings.
+
+config UNICODE_SUPPORT
+        bool "Support Unicode"
+        default y
+        help
+          This makes various applets aware that one byte is not
+          one character on screen.
+
+          Busybox aims to eventually work correctly with Unicode displays.
+          Any older encodings are not guaranteed to work.
+          Probably by the time when busybox will be fully Unicode-clean,
+          other encodings will be mainly of historic interest.
+
+config UNICODE_USING_LOCALE
+        bool "Use libc routines for Unicode (else uses internal ones)"
+        default n
+        depends on UNICODE_SUPPORT && LOCALE_SUPPORT
+        help
+          With this option on, Unicode support is implemented using libc
+          routines. Otherwise, internal implementation is used.
+          Internal implementation is smaller.
+
+config FEATURE_CHECK_UNICODE_IN_ENV
+        bool "Check $LC_ALL, $LC_CTYPE and $LANG environment variables"
+        default n
+        depends on UNICODE_SUPPORT && !UNICODE_USING_LOCALE
+        help
+          With this option on, Unicode support is activated
+          only if locale-related variables have the value of the form
+          "xxxx.utf8"
+
+          Otherwise, Unicode support will be always enabled and active.
+
+config SUBST_WCHAR
+        int "Character code to substitute unprintable characters with"
+        depends on UNICODE_SUPPORT
+        default 63
+        help
+          Typical values are 63 for '?' (works with any output device),
+          30 for ASCII substitute control code,
+          65533 (0xfffd) for Unicode replacement character.
+
+config LAST_SUPPORTED_WCHAR
+        int "Range of supported Unicode characters"
+        depends on UNICODE_SUPPORT
+        default 767
+        help
+          Any character with Unicode value bigger than this is assumed
+          to be non-printable on output device. Many applets replace
+          such characters with substitution character.
+
+          The idea is that many valid printable Unicode chars
+          nevertheless are not displayed correctly. Think about
+          combining charachers, double-wide hieroglyphs, obscure
+          characters in dozens of ancient scripts...
+          Many terminals, terminal emulators, xterms etc will fail
+          to handle them correctly. Choose the smallest value
+          which suits your needs.
+
+          Typical values are:
+          126 - ASCII only
+          767 (0x2ff) - there are no combining chars in [0..767] range
+                        (the range includes Latin 1, Latin Ext. A and B),
+                        code is ~700 bytes smaller for this case.
+          4351 (0x10ff) - there are no double-wide chars in [0..4351] range,
+                        code is ~300 bytes smaller for this case.
+          12799 (0x31ff) - nearly all non-ideographic characters are
+                        available in [0..12799] range, including
+                        East Asian scripts like katakana, hiragana, hangul,
+                        bopomofo...
+          0 - off, any valid printable Unicode character will be printed.
+
+config UNICODE_COMBINING_WCHARS
+        bool "Allow zero-width Unicode characters on output"
+        default n
+        depends on UNICODE_SUPPORT
+        help
+          With this option off, any Unicode char with width of 0
+          is substituted on output.
+
+config UNICODE_WIDE_WCHARS
+        bool "Allow wide Unicode characters on output"
+        default n
+        depends on UNICODE_SUPPORT
+        help
+          With this option off, any Unicode char with width > 1
+          is substituted on output.
+
+config UNICODE_BIDI_SUPPORT
+        bool "Bidirectional character-aware line input"
+        default n
+        depends on UNICODE_SUPPORT && !UNICODE_USING_LOCALE
+        help
+          With this option on, right-to-left Unicode characters
+          are treated differently on input (e.g. cursor movement).
+
+config UNICODE_NEUTRAL_TABLE
+        bool "In bidi input, support non-ASCII neutral chars too"
+        default n
+        depends on UNICODE_BIDI_SUPPORT
+        help
+          In most cases it's enough to treat only ASCII non-letters
+          (i.e. punctuation, numbers and space) as characters
+          with neutral directionality.
+          With this option on, more extensive (and bigger) table
+          of neutral chars will be used.
+
+config UNICODE_PRESERVE_BROKEN
+        bool "Make it possible to enter sequences of chars which are not Unicode"
+        default n
+        depends on UNICODE_SUPPORT
+        help
+          With this option on, on line-editing input (such as used by shells)
+          invalid UTF-8 bytes are not substituted with the selected
+          substitution character.
+          For example, this means that entering 'l', 's', ' ', 0xff, [Enter]
+          at shell prompt will list file named 0xff (single char name
+          with char value 255), not file named '?'.
+
 config FEATURE_NON_POSIX_CP
         bool "Non-POSIX, but safer, copying to special nodes"
         default y
@@ -177,6 +326,19 @@ config FEATURE_VERBOSE_CP_MESSAGE
             cp: cannot stat '/vmlinuz/file': Not a directory
           This will cost you ~60 bytes.
 
+config FEATURE_USE_SENDFILE
+        bool "Use sendfile system call"
+        default y
+        select PLATFORM_LINUX
+        help
+          When enabled, busybox will use the kernel sendfile() function
+          instead of read/write loops to copy data between file descriptors
+          (for example, cp command does this a lot).
+          If sendfile() doesn't work, copying code falls back to read/write
+          loop. sendfile() was originally implemented for faster I/O
+          from files to sockets, but since Linux 2.6.33 it was extended
+          to work for many more file types.
+
 config FEATURE_COPYBUF_KB
         int "Copy buffer size, in kilobytes"
         range 1 1024
diff --git a/libbb/appletlib.c b/libbb/appletlib.c
index 4aa40454f..1fe0eb44f 100644
--- a/libbb/appletlib.c
+++ b/libbb/appletlib.c
@@ -821,7 +821,7 @@ static int busybox_main(char **argv)
                         col += len2;
                         a += len2 - 1;
                 }
-                full_write2_str("\n\n");
+                full_write2_str("\n");
                 return 0;
         }
 
@@ -936,20 +936,21 @@ void FAST_FUNC run_applet_no_and_exit(int applet_no, char **argv)
 }
 # endif /* NUM_APPLETS > 0 */
 
+# if ENABLE_BUSYBOX || NUM_APPLETS > 0
 static NORETURN void run_applet_and_exit(const char *name, char **argv)
 {
-# if ENABLE_BUSYBOX
+#  if ENABLE_BUSYBOX
         if (is_prefixed_with(name, "busybox"))
                 exit(busybox_main(argv));
-# endif
-# if NUM_APPLETS > 0
+#  endif
+#  if NUM_APPLETS > 0
         /* find_applet_by_name() search is more expensive, so goes second */
         {
                 int applet = find_applet_by_name(name);
                 if (applet >= 0)
                         run_applet_no_and_exit(applet, argv);
         }
-# endif
+#  endif
 
         /*bb_error_msg_and_die("applet not found"); - links in printf */
         full_write2_str(applet_name);
@@ -957,11 +958,11 @@ static NORETURN void run_applet_and_exit(const char *name, char **argv)
         /* POSIX: "If a command is not found, the exit status shall be 127" */
         exit(127);
 }
+# endif
 
 #endif /* !defined(SINGLE_APPLET_MAIN) */
 
 
-
 #if ENABLE_BUILD_LIBBUSYBOX
 int lbb_main(char **argv)
 #else
@@ -1025,6 +1026,7 @@ int main(int argc UNUSED_PARAM, char **argv)
 #endif
 
 #if defined(SINGLE_APPLET_MAIN)
+
         /* Only one applet is selected in .config */
         if (argv[1] && is_prefixed_with(argv[0], "busybox")) {
                 /* "busybox <applet> <params>" should still work as expected */
@@ -1033,9 +1035,16 @@ int main(int argc UNUSED_PARAM, char **argv)
         /* applet_names in this case is just "applet\0\0" */
         lbb_prepare(applet_names IF_FEATURE_INDIVIDUAL(, argv));
         return SINGLE_APPLET_MAIN(argc, argv);
+
+#elif !ENABLE_BUSYBOX && NUM_APPLETS == 0
+
+        full_write2_str(bb_basename(argv[0]));
+        full_write2_str(": no applets enabled\n");
+        exit(127);
+
 #else
-        lbb_prepare("busybox" IF_FEATURE_INDIVIDUAL(, argv));
 
+        lbb_prepare("busybox" IF_FEATURE_INDIVIDUAL(, argv));
 # if !ENABLE_BUSYBOX
         if (argv[1] && is_prefixed_with(bb_basename(argv[0]), "busybox"))
                 argv++;
@@ -1067,9 +1076,8 @@ int main(int argc UNUSED_PARAM, char **argv)
                 }
         }
         applet_name = bb_basename(applet_name);
-
         parse_config_file(); /* ...maybe, if FEATURE_SUID_CONFIG */
-
         run_applet_and_exit(applet_name, argv);
+
 #endif
 }
diff --git a/libbb/lineedit.c b/libbb/lineedit.c
index 06f708b62..5d9080131 100644
--- a/libbb/lineedit.c
+++ b/libbb/lineedit.c
@@ -13,7 +13,6 @@
  *
  * This code is 'as is' with no warranty.
  */
-
 /*
  * Usage and known bugs:
  * Terminal key codes are not extensive, more needs to be added.
@@ -23,9 +22,6 @@
  * Ctrl-E also works as End.
  *
  * The following readline-like commands are not implemented:
- * ESC-b -- Move back one word
- * ESC-f -- Move forward one word
- * ESC-d -- Delete forward one word
  * CTL-t -- Transpose two characters
  *
  * lineedit does not know that the terminal escape sequences do not
@@ -133,8 +129,7 @@ static const char null_str[] ALIGN1 = "";
 struct lineedit_statics {
         line_input_t *state;
 
-        volatile unsigned cmdedit_termw; /* = 80; */ /* actual terminal width */
-        sighandler_t previous_SIGWINCH_handler;
+        unsigned cmdedit_termw; /* = 80; */ /* actual terminal width */
 
         unsigned cmdedit_x;        /* real x (col) terminal position */
         unsigned cmdedit_y;        /* pseudoreal y (row) terminal position */
@@ -159,15 +154,22 @@ struct lineedit_statics {
         unsigned num_matches;
 #endif
 
+        unsigned SIGWINCH_saved;
+        volatile unsigned SIGWINCH_count;
+        volatile smallint ok_to_redraw;
+
 #if ENABLE_FEATURE_EDITING_VI
 # define DELBUFSIZ 128
-        CHAR_T *delptr;
         smallint newdelflag;     /* whether delbuf should be reused yet */
+        CHAR_T *delptr;
         CHAR_T delbuf[DELBUFSIZ];  /* a place to store deleted characters */
 #endif
 #if ENABLE_FEATURE_EDITING_ASK_TERMINAL
         smallint sent_ESC_br6n;
 #endif
+
+        /* Largish struct, keeping it last results in smaller code */
+        struct sigaction SIGWINCH_handler;
 };
 
 /* See lineedit_ptr_hack.c */
@@ -176,7 +178,6 @@ extern struct lineedit_statics *const lineedit_ptr_to_statics;
 #define S (*lineedit_ptr_to_statics)
 #define state            (S.state           )
 #define cmdedit_termw    (S.cmdedit_termw   )
-#define previous_SIGWINCH_handler (S.previous_SIGWINCH_handler)
 #define cmdedit_x        (S.cmdedit_x       )
 #define cmdedit_y        (S.cmdedit_y       )
 #define cmdedit_prmt_len (S.cmdedit_prmt_len)
@@ -474,14 +475,10 @@ static void beep(void)
 
 static void put_prompt(void)
 {
-        unsigned w;
-
         fputs(cmdedit_prompt, stdout);
-        fflush_all();
         cursor = 0;
-        w = cmdedit_termw; /* read volatile var once */
-        cmdedit_y = cmdedit_prmt_len / w; /* new quasireal y */
-        cmdedit_x = cmdedit_prmt_len % w;
+        cmdedit_y = cmdedit_prmt_len / cmdedit_termw; /* new quasireal y */
+        cmdedit_x = cmdedit_prmt_len % cmdedit_termw;
 }
 
 /* Move back one character */
@@ -555,13 +552,11 @@ static void input_backward(unsigned num)
                         put_cur_glyph_and_inc_cursor();
         } else {
                 int lines_up;
-                unsigned width;
                 /* num = chars to go back from the beginning of current line: */
                 num -= cmdedit_x;
-                width = cmdedit_termw; /* read volatile var once */
                 /* num=1...w: one line up, w+1...2w: two, etc: */
-                lines_up = 1 + (num - 1) / width;
-                cmdedit_x = (width * cmdedit_y - num) % width;
+                lines_up = 1 + (num - 1) / cmdedit_termw;
+                cmdedit_x = (cmdedit_termw * cmdedit_y - num) % cmdedit_termw;
                 cmdedit_y -= lines_up;
                 /* go to 1st column; go up */
                 printf("\r" ESC"[%uA", lines_up);
@@ -2052,28 +2047,29 @@ static void parse_and_put_prompt(const char *prmt_ptr)
 }
 #endif
 
-static void cmdedit_setwidth(unsigned w, int redraw_flg)
+static void cmdedit_setwidth(void)
 {
-        cmdedit_termw = w;
-        if (redraw_flg) {
-                /* new y for current cursor */
-                int new_y = (cursor + cmdedit_prmt_len) / w;
-                /* redraw */
-                redraw((new_y >= cmdedit_y ? new_y : cmdedit_y), command_len - cursor);
-                fflush_all();
-        }
+        int new_y;
+
+        cmdedit_termw = get_terminal_width(STDIN_FILENO);
+        /* new y for current cursor */
+        new_y = (cursor + cmdedit_prmt_len) / cmdedit_termw;
+        /* redraw */
+        redraw((new_y >= cmdedit_y ? new_y : cmdedit_y), command_len - cursor);
 }
 
-static void win_changed(int nsig)
+static void win_changed(int nsig UNUSED_PARAM)
 {
-        int sv_errno = errno;
-        unsigned width;
-
-        get_terminal_width_height(0, &width, NULL);
-//FIXME: cmdedit_setwidth() -> redraw() -> printf() -> KABOOM! (we are in signal handler!)
-        cmdedit_setwidth(width, /*redraw_flg:*/ nsig);
-
-        errno = sv_errno;
+        if (S.ok_to_redraw) {
+                /* We are in read_key(), safe to redraw immediately */
+                int sv_errno = errno;
+                cmdedit_setwidth();
+                fflush_all();
+                errno = sv_errno;
+        } else {
+                /* Signal main loop that redraw is necessary */
+                S.SIGWINCH_count++;
+        }
 }
 
 static int lineedit_read_key(char *read_key_buffer, int timeout)
@@ -2084,6 +2080,7 @@ static int lineedit_read_key(char *read_key_buffer, int timeout)
         int unicode_idx = 0;
 #endif
 
+        fflush_all();
         while (1) {
                 /* Wait for input. TIMEOUT = -1 makes read_key wait even
                  * on nonblocking stdin, TIMEOUT = 50 makes sure we won't
@@ -2092,7 +2089,9 @@ static int lineedit_read_key(char *read_key_buffer, int timeout)
                  *
                  * Note: read_key sets errno to 0 on success.
                  */
+                S.ok_to_redraw = 1;
                 ic = read_key(STDIN_FILENO, read_key_buffer, timeout);
+                S.ok_to_redraw = 0;
                 if (errno) {
 #if ENABLE_UNICODE_SUPPORT
                         if (errno == EAGAIN && unicode_idx != 0)
@@ -2223,7 +2222,6 @@ static int32_t reverse_i_search(void)
                 int h;
                 unsigned match_buf_len = strlen(match_buf);
 
-                fflush_all();
 //FIXME: correct timeout?
                 ic = lineedit_read_key(read_key_buffer, -1);
 
@@ -2325,6 +2323,7 @@ static int32_t reverse_i_search(void)
  * Returns:
  * -1 on read errors or EOF, or on bare Ctrl-D,
  * 0  on ctrl-C (the line entered is still returned in 'command'),
+ * (in both cases the cursor remains on the input line, '\n' is not printed)
  * >0 length of input string, including terminating '\n'
  */
 int FAST_FUNC read_line_input(line_input_t *st, const char *prompt, char *command, int maxsize, int timeout)
@@ -2359,7 +2358,7 @@ int FAST_FUNC read_line_input(line_input_t *st, const char *prompt, char *comman
                  * tty is still in "raw mode").
                  */
                 parse_and_put_prompt(prompt);
-                /* fflush_all(); - done by parse_and_put_prompt */
+                fflush_all();
                 if (fgets(command, maxsize, stdin) == NULL)
                         len = -1; /* EOF or error */
                 else
@@ -2435,9 +2434,11 @@ int FAST_FUNC read_line_input(line_input_t *st, const char *prompt, char *comman
         ask_terminal();
 
         /* Install window resize handler (NB: after *all* init is complete) */
-//FIXME: save entire sigaction!
-        previous_SIGWINCH_handler = signal(SIGWINCH, win_changed);
-        win_changed(0); /* get initial window size */
+        S.SIGWINCH_handler.sa_handler = win_changed;
+        S.SIGWINCH_handler.sa_flags = SA_RESTART;
+        sigaction(SIGWINCH, &S.SIGWINCH_handler, &S.SIGWINCH_handler);
+
+        cmdedit_termw = get_terminal_width(STDIN_FILENO);
 
         read_key_buffer[0] = 0;
         while (1) {
@@ -2450,8 +2451,14 @@ int FAST_FUNC read_line_input(line_input_t *st, const char *prompt, char *comman
                  * in one place.
                  */
                 int32_t ic, ic_raw;
+                unsigned count;
+
+                count = S.SIGWINCH_count;
+                if (S.SIGWINCH_saved != count) {
+                        S.SIGWINCH_saved = count;
+                        cmdedit_setwidth();
+                }
 
-                fflush_all();
                 ic = ic_raw = lineedit_read_key(read_key_buffer, timeout);
 #if ENABLE_PLATFORM_MINGW32
                 /* scroll to cursor position on any keypress */
@@ -2565,6 +2572,24 @@ int FAST_FUNC read_line_input(line_input_t *st, const char *prompt, char *comman
                         while (cursor > 0 && !BB_isspace(command_ps[cursor-1]))
                                 input_backspace();
                         break;
+                case KEYCODE_ALT_D: {
+                        /* Delete word forward */
+                        int nc, sc = cursor;
+                        ctrl_right();
+                        nc = cursor - sc;
+                        input_backward(nc);
+                        while (--nc >= 0)
+                                input_delete(1);
+                        break;
+                }
+                case KEYCODE_ALT_BACKSPACE: {
+                        /* Delete word backward */
+                        int sc = cursor;
+                        ctrl_left();
+                        while (sc-- > cursor)
+                                input_delete(1);
+                        break;
+                }
 #if ENABLE_FEATURE_REVERSE_SEARCH
                 case CTRL('R'):
                         ic = ic_raw = reverse_i_search();
@@ -2792,7 +2817,6 @@ int FAST_FUNC read_line_input(line_input_t *st, const char *prompt, char *comman
                          && ic_raw == initial_settings.c_cc[VINTR]
                         ) {
                                 /* Ctrl-C (usually) - stop gathering input */
-                                goto_new_line();
                                 command_len = 0;
                                 break_out = -1; /* "do not append '\n'" */
                                 break;
@@ -2914,7 +2938,7 @@ int FAST_FUNC read_line_input(line_input_t *st, const char *prompt, char *comman
         /* restore initial_settings */
         tcsetattr_stdin_TCSANOW(&initial_settings);
         /* restore SIGWINCH handler */
-        signal(SIGWINCH, previous_SIGWINCH_handler);
+        sigaction_set(SIGWINCH, &S.SIGWINCH_handler);
         fflush_all();
 
         len = command_len;
diff --git a/libbb/read_key.c b/libbb/read_key.c
index ace23defb..951786869 100644
--- a/libbb/read_key.c
+++ b/libbb/read_key.c
@@ -18,8 +18,20 @@ int64_t FAST_FUNC read_key(int fd, char *buffer, int timeout)
         /* Known escape sequences for cursor and function keys.
          * See "Xterm Control Sequences"
          * http://invisible-island.net/xterm/ctlseqs/ctlseqs.html
+         * Array should be sorted from shortest to longest.
          */
         static const char esccmds[] ALIGN1 = {
+                '\x7f'         |0x80,KEYCODE_ALT_BACKSPACE,
+                '\b'           |0x80,KEYCODE_ALT_BACKSPACE,
+                'd'            |0x80,KEYCODE_ALT_D   ,
+        /* lineedit mimics bash: Alt-f and Alt-b are forward/backward
+         * word jumps. We cheat here and make them return ALT_LEFT/RIGHT
+         * keycodes. This way, lineedit need no special code to handle them.
+         * If we'll need to distinguish them, introduce new ALT_F/B keycodes,
+         * and update lineedit to react to them.
+         */
+                'f'            |0x80,KEYCODE_ALT_RIGHT,
+                'b'            |0x80,KEYCODE_ALT_LEFT,
                 'O','A'        |0x80,KEYCODE_UP      ,
                 'O','B'        |0x80,KEYCODE_DOWN    ,
                 'O','C'        |0x80,KEYCODE_RIGHT   ,