From e8392b282c2eaa28725241a9612804fb55113da4 Mon Sep 17 00:00:00 2001 From: "Avi Halachmi (:avih)" Date: Thu, 14 May 2020 18:18:07 +0300 Subject: support REP (repeat) escape sequence The sequence \e[Nb prints the last printed char N (more) times if it's printable, and it's ignored after newline or other control chars. This is Ecma-048/ANSI-X3.6 sequence and not DEC VT. It's supported by xterm, and ncurses uses it when possible, e.g. when TERM is xterm* (and with this commit also st*). xterm supports only codepoints<=255, possibly due to internal limits. We support any value/codepoint which was placed in a cell. To test: - tput rep 65 4 -> prints 'AAAA' - printf "\342\225\246\033[4b" -> prints U+2566 1+4 times. --- st.c | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'st.c') diff --git a/st.c b/st.c index 0d35613..54af098 100644 --- a/st.c +++ b/st.c @@ -129,6 +129,7 @@ typedef struct { int charset; /* current charset */ int icharset; /* selected charset for sequence */ int *tabs; + Rune lastc; /* last printed char outside of sequence, 0 if control */ } Term; /* CSI Escape sequence structs */ @@ -1648,6 +1649,12 @@ csihandle(void) if (csiescseq.arg[0] == 0) ttywrite(vtiden, strlen(vtiden), 0); break; + case 'b': /* REP -- if last char is printable print it more times */ + DEFAULT(csiescseq.arg[0], 1); + if (term.lastc) + while (csiescseq.arg[0]-- > 0) + tputc(term.lastc); + break; case 'C': /* CUF -- Cursor Forward */ case 'a': /* HPR -- Cursor Forward */ DEFAULT(csiescseq.arg[0], 1); @@ -2373,6 +2380,8 @@ check_control_code: /* * control codes are not shown ever */ + if (!term.esc) + term.lastc = 0; return; } else if (term.esc & ESC_START) { if (term.esc & ESC_CSI) { @@ -2422,6 +2431,7 @@ check_control_code: } tsetchar(u, &term.c.attr, term.c.x, term.c.y); + term.lastc = u; if (width == 2) { gp->mode |= ATTR_WIDE; -- cgit From 475a0a36cb4fda1da30f014da65988e99b222876 Mon Sep 17 00:00:00 2001 From: Hiltjo Posthuma Date: Sat, 16 May 2020 18:06:42 +0200 Subject: Revert "support REP (repeat) escape sequence" This reverts commit e8392b282c2eaa28725241a9612804fb55113da4. There is currently a bug in older ncurses versions (like on OpenBSD) where a fix for a bug with REP is not backported yet. Most likely in tty/tty_update.c: Noticed while using lynx (which uses ncurses/curses). To reproduce using lynx: echo "Z0000000" | lynx -stdin or using the program: int main(void) { WINDOW *win; win = initscr(); printw("Z0000000"); refresh(); sleep(5); return 0; } This prints "ZZZZZZZ" (incorrectly). --- st.c | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'st.c') diff --git a/st.c b/st.c index 54af098..0d35613 100644 --- a/st.c +++ b/st.c @@ -129,7 +129,6 @@ typedef struct { int charset; /* current charset */ int icharset; /* selected charset for sequence */ int *tabs; - Rune lastc; /* last printed char outside of sequence, 0 if control */ } Term; /* CSI Escape sequence structs */ @@ -1649,12 +1648,6 @@ csihandle(void) if (csiescseq.arg[0] == 0) ttywrite(vtiden, strlen(vtiden), 0); break; - case 'b': /* REP -- if last char is printable print it more times */ - DEFAULT(csiescseq.arg[0], 1); - if (term.lastc) - while (csiescseq.arg[0]-- > 0) - tputc(term.lastc); - break; case 'C': /* CUF -- Cursor Forward */ case 'a': /* HPR -- Cursor Forward */ DEFAULT(csiescseq.arg[0], 1); @@ -2380,8 +2373,6 @@ check_control_code: /* * control codes are not shown ever */ - if (!term.esc) - term.lastc = 0; return; } else if (term.esc & ESC_START) { if (term.esc & ESC_CSI) { @@ -2431,7 +2422,6 @@ check_control_code: } tsetchar(u, &term.c.attr, term.c.x, term.c.y); - term.lastc = u; if (width == 2) { gp->mode |= ATTR_WIDE; -- cgit From 94b8ec002101a5e8f52a342e53431eea71aa0631 Mon Sep 17 00:00:00 2001 From: Hiltjo Posthuma Date: Sat, 30 May 2020 21:34:57 +0200 Subject: Partially add back in "support REP (repeat) escape sequence" Add the functionality back in for xterm compatibility, but do not expose the capability in st.info (yet). Some notes: It was reverted because it caused some issues with ncurses in some configurations, namely when using BSD padding (--enable-bsdpad, BSD_TPUTS) in ncurses it caused issues with repeating digits. A fix has been upstreamed in ncurses since snapshot 20200523. The fix is also backported to OpenBSD -current. --- st.c | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'st.c') diff --git a/st.c b/st.c index 0d35613..54af098 100644 --- a/st.c +++ b/st.c @@ -129,6 +129,7 @@ typedef struct { int charset; /* current charset */ int icharset; /* selected charset for sequence */ int *tabs; + Rune lastc; /* last printed char outside of sequence, 0 if control */ } Term; /* CSI Escape sequence structs */ @@ -1648,6 +1649,12 @@ csihandle(void) if (csiescseq.arg[0] == 0) ttywrite(vtiden, strlen(vtiden), 0); break; + case 'b': /* REP -- if last char is printable print it more times */ + DEFAULT(csiescseq.arg[0], 1); + if (term.lastc) + while (csiescseq.arg[0]-- > 0) + tputc(term.lastc); + break; case 'C': /* CUF -- Cursor Forward */ case 'a': /* HPR -- Cursor Forward */ DEFAULT(csiescseq.arg[0], 1); @@ -2373,6 +2380,8 @@ check_control_code: /* * control codes are not shown ever */ + if (!term.esc) + term.lastc = 0; return; } else if (term.esc & ESC_START) { if (term.esc & ESC_CSI) { @@ -2422,6 +2431,7 @@ check_control_code: } tsetchar(u, &term.c.attr, term.c.x, term.c.y); + term.lastc = u; if (width == 2) { gp->mode |= ATTR_WIDE; -- cgit From e6e2c6199f102f1459b53717050eee27832f4f87 Mon Sep 17 00:00:00 2001 From: Hiltjo Posthuma Date: Sat, 30 May 2020 21:39:49 +0200 Subject: tiny style fix --- st.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'st.c') diff --git a/st.c b/st.c index 54af098..2d901ab 100644 --- a/st.c +++ b/st.c @@ -843,7 +843,6 @@ ttyread(void) if (buflen > 0) memmove(buf, buf + written, buflen); return ret; - } } @@ -1778,7 +1777,7 @@ csihandle(void) break; case 'n': /* DSR – Device Status Report (cursor position) */ if (csiescseq.arg[0] == 6) { - len = snprintf(buf, sizeof(buf),"\033[%i;%iR", + len = snprintf(buf, sizeof(buf), "\033[%i;%iR", term.c.y+1, term.c.x+1); ttywrite(buf, len, 0); } -- cgit From a2a704492b9f4d2408d180f7aeeacf4c789a1d67 Mon Sep 17 00:00:00 2001 From: Hiltjo Posthuma Date: Sat, 30 May 2020 21:56:18 +0200 Subject: config.def.h: add an option allowwindowops, by default off (secure) Similar to the xterm AllowWindowOps option, this is an option to allow or disallow certain (non-interactive) operations that can be insecure or exploited. NOTE: xsettitle() is not guarded by this because st does not support printing the window title. Else this could be exploitable (arbitrary code execution). Similar problems have been found in the past in other terminal emulators. The sequence for base64-encoded clipboard copy is now guarded because it allows a sequence written to the terminal to manipulate the clipboard of the running user non-interactively, for example: printf '\x1b]52;0;ZWNobyBoaQ0=\a' --- st.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'st.c') diff --git a/st.c b/st.c index 2d901ab..ef8abd5 100644 --- a/st.c +++ b/st.c @@ -1861,7 +1861,7 @@ strhandle(void) xsettitle(strescseq.args[1]); return; case 52: - if (narg > 2) { + if (narg > 2 && allowwindowops) { dec = base64dec(strescseq.args[2]); if (dec) { xsetsel(dec); -- cgit From 818ec746f4caae453d09368b101c3e841cf39870 Mon Sep 17 00:00:00 2001 From: Hiltjo Posthuma Date: Wed, 17 Jun 2020 21:35:39 +0200 Subject: fix unicode glitch in DCS strings, patch by Tim Allen MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Reported on the mailinglist: " I discovered recently that if an application running inside st tries to send a DCS string, subsequent Unicode characters get messed up. For example, consider the following test-case: printf '\303\277\033P\033\\\303\277' ...where: - \303\277 is the UTF-8 encoding of U+00FF LATIN SMALL LETTER Y WITH DIAERESIS (ÿ). - \033P is ESC P, the token that begins a DCS string. - \033\\ is ESC \, a token that ends a DCS string. - \303\277 is the same ÿ character again. If I run the above command in a VTE-based terminal, or xterm, or QTerminal, or pterm (PuTTY), I get the output: ÿÿ ...which is to say, the empty DCS string is ignored. However, if I run that command inside st (as of commit 9ba7ecf), I get: ÿÿ ...where those last two characters are \303\277 interpreted as ISO8859-1 characters, instead of UTF-8. I spent some time tracing through the state machines in st.c, and so far as I can tell, this is how it works currently: - ESC P sets the "ESC_DCS" and "ESC_STR" flags, indicating that incoming bytes should be collected into the strescseq buffer, rather than being interpreted. - ESC \ sets the "ESC_STR_END" flag (when ESC is received), and then calls strhandle() (when \ is received) to interpret the collected bytes. - If the collected bytes begin with 'P' (i.e. if this was a DCS string) strhandle() sets the "ESC_DCS" flag again, confusing the state machine. If my understanding is correct, fixing the problem should be as easy as removing the line that sets ESC_DCS from strhandle(): diff --git a/st.c b/st.c index ef8abd5..b5b805a 100644 --- a/st.c +++ b/st.c @@ -1897,7 +1897,6 @@ strhandle(void) xsettitle(strescseq.args[0]); return; case 'P': /* DCS -- Device Control String */ - term.mode |= ESC_DCS; case '_': /* APC -- Application Program Command */ case '^': /* PM -- Privacy Message */ return; I've tried the above patch and it fixes my problem, but I don't know if it introduces any others. " --- st.c | 1 - 1 file changed, 1 deletion(-) (limited to 'st.c') diff --git a/st.c b/st.c index ef8abd5..b5b805a 100644 --- a/st.c +++ b/st.c @@ -1897,7 +1897,6 @@ strhandle(void) xsettitle(strescseq.args[0]); return; case 'P': /* DCS -- Device Control String */ - term.mode |= ESC_DCS; case '_': /* APC -- Application Program Command */ case '^': /* PM -- Privacy Message */ return; -- cgit From f74a9df6e1fc88eebe6d673d888b61fd83cf6fc4 Mon Sep 17 00:00:00 2001 From: Hiltjo Posthuma Date: Wed, 17 Jun 2020 22:05:48 +0200 Subject: remove sixel stub code Remove stub code that was used for an experiment of adding sixel code to st from the commit f7398434. --- st.c | 26 +++++--------------------- 1 file changed, 5 insertions(+), 21 deletions(-) (limited to 'st.c') diff --git a/st.c b/st.c index b5b805a..76b7e0d 100644 --- a/st.c +++ b/st.c @@ -51,7 +51,6 @@ enum term_mode { MODE_ECHO = 1 << 4, MODE_PRINT = 1 << 5, MODE_UTF8 = 1 << 6, - MODE_SIXEL = 1 << 7, }; enum cursor_movement { @@ -78,12 +77,11 @@ enum charset { enum escape_state { ESC_START = 1, ESC_CSI = 2, - ESC_STR = 4, /* OSC, PM, APC */ + ESC_STR = 4, /* DCS, OSC, PM, APC */ ESC_ALTCHARSET = 8, ESC_STR_END = 16, /* a final string was encountered */ ESC_TEST = 32, /* Enter in test mode */ ESC_UTF8 = 64, - ESC_DCS =128, }; typedef struct { @@ -2090,12 +2088,9 @@ tdectest(char c) void tstrsequence(uchar c) { - strreset(); - switch (c) { case 0x90: /* DCS -- Device Control String */ c = 'P'; - term.esc |= ESC_DCS; break; case 0x9f: /* APC -- Application Program Command */ c = '_'; @@ -2107,6 +2102,7 @@ tstrsequence(uchar c) c = ']'; break; } + strreset(); strescseq.type = c; term.esc |= ESC_STR; } @@ -2304,7 +2300,7 @@ tputc(Rune u) Glyph *gp; control = ISCONTROL(u); - if (u < 127 || !IS_SET(MODE_UTF8 | MODE_SIXEL)) { + if (u < 127 || !IS_SET(MODE_UTF8)) { c[0] = u; width = len = 1; } else { @@ -2325,23 +2321,11 @@ tputc(Rune u) if (term.esc & ESC_STR) { if (u == '\a' || u == 030 || u == 032 || u == 033 || ISCONTROLC1(u)) { - term.esc &= ~(ESC_START|ESC_STR|ESC_DCS); - if (IS_SET(MODE_SIXEL)) { - /* TODO: render sixel */; - term.mode &= ~MODE_SIXEL; - return; - } + term.esc &= ~(ESC_START|ESC_STR); term.esc |= ESC_STR_END; goto check_control_code; } - if (IS_SET(MODE_SIXEL)) { - /* TODO: implement sixel mode */ - return; - } - if (term.esc&ESC_DCS && strescseq.len == 0 && u == 'q') - term.mode |= MODE_SIXEL; - if (strescseq.len+len >= strescseq.siz) { /* * Here is a bug in terminals. If the user never sends @@ -2453,7 +2437,7 @@ twrite(const char *buf, int buflen, int show_ctrl) int n; for (n = 0; n < buflen; n += charsize) { - if (IS_SET(MODE_UTF8) && !IS_SET(MODE_SIXEL)) { + if (IS_SET(MODE_UTF8)) { /* process a complete utf8 char */ charsize = utf8decode(buf + n, &u, buflen - n); if (charsize == 0) -- cgit