mirror of
https://github.com/jart/cosmopolitan.git
synced 2025-06-30 16:28:30 +00:00
Improve Python and Linenoise
This change reinvents all the GNU Readline features I discovered that I couldn't live without, e.g. UTF-8, CTRL-R search and CTRL-Y yanking. It now feels just as good in terms of user interface from the subconscious workflow perspective. It's real nice to finally have an embeddable line reader that's actually good with a 30 kb footprint and a bsd-2 license. This change adds a directory to the examples folder, explaining how the new Python compiler may be used. Some of the bugs with Python binaries have been addressed but overall it's still a work in progress.
This commit is contained in:
Justine Tunney
parent
ad52387b74
commit
51904e2687
35 changed files with 3541 additions and 8587 deletions
|
|
@ -31,9 +31,16 @@
|
|||
*
|
||||
* "a" ALFA
|
||||
* "\316\261" ALPHA
|
||||
* "\033[A" CURSOR UP
|
||||
* "\033[38;5;202m" ORANGERED
|
||||
* "\e[38;5;202m" ORANGERED
|
||||
* "\e[A" UP
|
||||
* "\e\e[A" ALT-UP
|
||||
* "\001" CTRL-ALFA
|
||||
* "\e\001" ALT-CTRL-ALFA
|
||||
* "\eOP" PF1
|
||||
* "\000" NUL
|
||||
* "\e]rm -rf /\e\\" OSC
|
||||
* "\302\233A" UP
|
||||
* "\300\200" NUL
|
||||
*
|
||||
* This routine generalizes to ascii, utf-8, chorded modifier keys,
|
||||
* function keys, color codes, c0/c1 control codes, cursor movement,
|
||||
|
|
@ -44,15 +51,7 @@
|
|||
* can cause the stream to go out of sync. This function recovers such
|
||||
* events by ignoring continuation bytes at the beginning of each read.
|
||||
*
|
||||
* String control sequences, e.g. "\e_hello\e\\" currently are not
|
||||
* tokenized as a single read. Lastly note, this function has limited
|
||||
* support for UNICODE representations of C0/C1 control codes, e.g.
|
||||
*
|
||||
* "\000" NUL
|
||||
* "\300\200" NUL
|
||||
* "\302\233A" CURSOR UP
|
||||
*
|
||||
* @param buf is guaranteed to receive a NUL terminator if size>0
|
||||
* @param p is guaranteed to receive a NUL terminator if n>0
|
||||
* @return number of bytes read (helps differentiate "\0" vs. "")
|
||||
* @see examples/ttyinfo.c
|
||||
* @see ANSI X3.64-1979
|
||||
|
|
@ -60,81 +59,198 @@
|
|||
* @see FIPS-86
|
||||
* @see ECMA-48
|
||||
*/
|
||||
ssize_t readansi(int fd, char *buf, size_t size) {
|
||||
ssize_t readansi(int fd, char *p, size_t n) {
|
||||
wint_t x;
|
||||
uint8_t c;
|
||||
int i, j, rc;
|
||||
enum { kAscii, kUtf8, kEsc, kCsi, kSs } t;
|
||||
if (size) buf[0] = 0;
|
||||
for (j = i = 0, t = kAscii;;) {
|
||||
if (i + 2 >= size) return enomem();
|
||||
if ((rc = read(fd, &c, 1)) != 1) return rc;
|
||||
buf[i++] = c;
|
||||
buf[i] = 0;
|
||||
ssize_t rc;
|
||||
int e, i, j;
|
||||
unsigned char c;
|
||||
enum { kAscii, kUtf8, kEsc, kCsi1, kCsi2, kSs, kNf, kStr, kStr2, kDone } t;
|
||||
e = errno;
|
||||
t = kAscii;
|
||||
x = i = j = 0;
|
||||
if (n) p[0] = 0;
|
||||
do {
|
||||
for (;;) {
|
||||
if (n) {
|
||||
rc = read(fd, &c, 1);
|
||||
} else {
|
||||
rc = read(fd, 0, 0);
|
||||
}
|
||||
if (rc == -1 && errno == EINTR) {
|
||||
if (!i) {
|
||||
return -1;
|
||||
}
|
||||
} else if (rc == -1) {
|
||||
return -1;
|
||||
} else if (!rc) {
|
||||
if (!i) {
|
||||
errno = e;
|
||||
return 0;
|
||||
} else {
|
||||
return eilseq();
|
||||
}
|
||||
} else {
|
||||
break;
|
||||
}
|
||||
}
|
||||
if (i + 1 < n) {
|
||||
p[i] = c;
|
||||
p[i + 1] = 0;
|
||||
} else if (i < n) {
|
||||
p[i] = 0;
|
||||
}
|
||||
++i;
|
||||
switch (t) {
|
||||
Whoopsie:
|
||||
if (n) p[0] = c;
|
||||
t = kAscii;
|
||||
i = 1;
|
||||
/* fallthrough */
|
||||
case kAscii:
|
||||
if (c < 0200) {
|
||||
if (c == '\e') {
|
||||
t = kEsc;
|
||||
} else {
|
||||
return i;
|
||||
t = kDone;
|
||||
}
|
||||
} else if (c >= 0300) {
|
||||
t = kUtf8;
|
||||
x = ThomPikeByte(c);
|
||||
j = ThomPikeLen(c) - 1;
|
||||
} else {
|
||||
/* ignore overlong sequences */
|
||||
}
|
||||
break;
|
||||
case kUtf8:
|
||||
x = ThomPikeMerge(x, c);
|
||||
if (!--j) {
|
||||
switch (x) {
|
||||
case '\e':
|
||||
t = kEsc;
|
||||
break;
|
||||
case 0x9b:
|
||||
t = kCsi;
|
||||
break;
|
||||
default:
|
||||
return i;
|
||||
if ((c & 0300) == 0200) {
|
||||
x = ThomPikeMerge(x, c);
|
||||
if (!--j) {
|
||||
switch (x) {
|
||||
case '\e':
|
||||
t = kEsc; /* parsed but not canonicalized */
|
||||
break;
|
||||
case 0x9b:
|
||||
t = kCsi1; /* unusual but legal */
|
||||
break;
|
||||
case 0x8e:
|
||||
case 0x8f:
|
||||
t = kSs; /* unusual but legal */
|
||||
break;
|
||||
case 0x90: /* DCS (Device Control String) */
|
||||
case 0x98: /* SOS (Start of String) */
|
||||
case 0x9d: /* OSC (Operating System Command) */
|
||||
case 0x9e: /* PM (Privacy Message) */
|
||||
case 0x9f: /* APC (Application Program Command) */
|
||||
t = kStr;
|
||||
break;
|
||||
default:
|
||||
t = kDone;
|
||||
break;
|
||||
}
|
||||
}
|
||||
} else {
|
||||
goto Whoopsie; /* ignore underlong sequences if not eof */
|
||||
}
|
||||
break;
|
||||
case kEsc:
|
||||
switch (c) {
|
||||
case '[':
|
||||
t = kCsi;
|
||||
break;
|
||||
case 'N':
|
||||
case 'O':
|
||||
t = kSs;
|
||||
break;
|
||||
case '\e':
|
||||
case 0x20 ... 0x2F:
|
||||
break;
|
||||
default:
|
||||
return i;
|
||||
}
|
||||
break;
|
||||
case kCsi:
|
||||
switch (c) {
|
||||
case '[':
|
||||
case ':':
|
||||
case ';':
|
||||
case '<':
|
||||
case '=':
|
||||
case '>':
|
||||
case '?':
|
||||
case '0' ... '9':
|
||||
break;
|
||||
default:
|
||||
return i;
|
||||
if (0x20 <= c && c <= 0x2f) {
|
||||
t = kNf;
|
||||
} else if (0x30 <= c && c <= 0x3f) { /* Fp */
|
||||
t = kDone;
|
||||
} else if (0x20 <= c && c <= 0x5F) { /* Fe */
|
||||
switch (c) {
|
||||
case '[':
|
||||
t = kCsi1;
|
||||
break;
|
||||
case 'N': /* SS2 */
|
||||
case 'O': /* SS3 */
|
||||
t = kSs;
|
||||
break;
|
||||
case 'P': /* DCS (Device Control String) */
|
||||
case 'X': /* SOS (Start of String) */
|
||||
case ']': /* DCS (Operating System Command) */
|
||||
case '^': /* PM (Privacy Message) */
|
||||
case '_': /* DCS (Application Program Command) */
|
||||
t = kStr;
|
||||
break;
|
||||
case '\\':
|
||||
goto Whoopsie;
|
||||
default:
|
||||
t = kDone;
|
||||
break;
|
||||
}
|
||||
} else if (0x60 <= c && c <= 0x7e) { /* Fs */
|
||||
t = kDone;
|
||||
} else if (c == '\e') {
|
||||
if (i < 3) {
|
||||
t = kEsc; /* alt chording */
|
||||
} else {
|
||||
t = kDone; /* esc mashing */
|
||||
i = 1;
|
||||
}
|
||||
} else {
|
||||
t = kDone;
|
||||
}
|
||||
break;
|
||||
case kSs:
|
||||
return i;
|
||||
t = kDone;
|
||||
break;
|
||||
case kNf:
|
||||
if (0x30 <= c && c <= 0x7e) {
|
||||
t = kDone;
|
||||
} else if (!(0x20 <= c && c <= 0x2f)) {
|
||||
goto Whoopsie;
|
||||
}
|
||||
break;
|
||||
case kCsi1:
|
||||
if (0x20 <= c && c <= 0x2f) {
|
||||
t = kCsi2;
|
||||
} else if (c == '[' && i == 3) {
|
||||
/* linux function keys */
|
||||
} else if (0x40 <= c && c <= 0x7e) {
|
||||
t = kDone;
|
||||
} else if (!(0x30 <= c && c <= 0x3f)) {
|
||||
goto Whoopsie;
|
||||
}
|
||||
break;
|
||||
case kCsi2:
|
||||
if (0x40 <= c && c <= 0x7e) {
|
||||
t = kDone;
|
||||
} else if (!(0x20 <= c && c <= 0x2f)) {
|
||||
goto Whoopsie;
|
||||
}
|
||||
break;
|
||||
case kStr:
|
||||
switch (c) {
|
||||
case '\a':
|
||||
t = kDone;
|
||||
break;
|
||||
case '\e': /* ESC */
|
||||
case 0302: /* C1 (UTF-8) */
|
||||
t = kStr2;
|
||||
break;
|
||||
default:
|
||||
break;
|
||||
}
|
||||
break;
|
||||
case kStr2:
|
||||
switch (c) {
|
||||
case '\a':
|
||||
t = kDone;
|
||||
break;
|
||||
case '\\': /* ST (ASCII) */
|
||||
case 0234: /* ST (UTF-8) */
|
||||
t = kDone;
|
||||
break;
|
||||
default:
|
||||
t = kStr;
|
||||
break;
|
||||
}
|
||||
break;
|
||||
default:
|
||||
unreachable;
|
||||
}
|
||||
}
|
||||
} while (t != kDone);
|
||||
errno = e;
|
||||
return i;
|
||||
}
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue