diff options
| -rw-r--r-- | toys/other/ascii.c | 79 | ||||
| -rw-r--r-- | toys/pending/unicode.c | 65 |
2 files changed, 62 insertions, 82 deletions
diff --git a/toys/other/ascii.c b/toys/other/ascii.c index 42f73260..c9448a75 100644 --- a/toys/other/ascii.c +++ b/toys/other/ascii.c @@ -4,8 +4,15 @@ * * Technically 7-bit ASCII is ANSI X3.4-1986, a standard available as * INCITS 4-1986[R2012] on ansi.org, but they charge for it. + * + * unicode.c - convert between Unicode and UTF-8 + * + * Copyright 2020 The Android Open Source Project. + * + * Loosely based on the Plan9/Inferno unicode(1). -USE_ASCII(NEWTOY(ascii, 0, TOYFLAG_USR|TOYFLAG_BIN)) +USE_ASCII(NEWTOY(ascii, 0, TOYFLAG_USR|TOYFLAG_BIN|TOYFLAG_LINEBUF)) +USE_UNICODE(NEWTOY(unicode, "<1", TOYFLAG_USR|TOYFLAG_BIN)) config ASCII bool "ascii" @@ -14,27 +21,65 @@ config ASCII usage: ascii Display ascii character set. + +config UNICODE + bool "unicode" + default y + help + usage: unicode CODE[-END]... + + Convert between Unicode code points and UTF-8, in both directions. + CODE can be one or more characters (show U+XXXX), hex numbers + (show character), or dash separated range. */ +#define FOR_unicode #include "toys.h" +static char *low="NULSOHSTXETXEOTENQACKBELBS HT LF VT FF CR SO SI DLEDC1DC2" + "DC3DC4NAKSYNETBCANEM SUBESCFS GS RS US "; + +static void codepoint(unsigned wc) +{ + char *s = toybuf + sprintf(toybuf, "U+%04X : ", wc), *ss; + unsigned n, i; + + if (wc>31 && wc!=127) { + s += n = wctoutf8(ss = s, wc); + if (n>1) for (i = 0; i<n; i++) s += sprintf(s, " : %#02x"+2*!!i, *ss++); + } else s = memcpy(s, (wc==127) ? "DEL" : low+wc*3, 3)+3; + *s++ = '\n'; + writeall(1, toybuf, s-toybuf); +} + +void unicode_main(void) +{ + int from, to, n; + char next, **args, *s; + wchar_t wc; + + // Loop through args, handling range, hex code, or character(s) + for (args = toys.optargs; *args; args++) { + if (sscanf(*args, "%x-%x%c", &from, &to, &next) == 2) + while (from <= to) codepoint(from++); + else if (sscanf(*args, "%x%c", &from, &next) == 1) codepoint(from); + else for (s = *args; (n = utf8towc(&wc, s, 4)) > 0; s += n) codepoint(wc); + } +} + void ascii_main(void) { - char *low="NULSOHSTXETXEOTENQACKBELBS HT LF VT FF CR SO SI DLEDC1DC2DC3DC4" - "NAKSYNETBCANEM SUBESCFS GS RS US "; - int x, y; - - for (x = 0; x<8; x++) printf("Dec Hex%*c", 2+2*(x<2)+(x>4), ' '); - xputc('\n'); - for (y=0; y<=15; y++) { - for (x=0; x<8; x++) { - int i = x*16+y; - - if (i>95 && i<100) putchar(' '); - printf("% 3d %02X ", i, i); - if (i<32 || i==127) printf("%.3s ", (i==127) ? "DEL" : low+3*i); - else printf("%c ", i); - } - xputc('\n'); + char *s = toybuf; + int i, x, y; + + for (y = -1; y<16; y++) for (x = 0; x<8; x++) { + if (y>=0) { + i = (x<<4)+y; + s += sprintf(s, "% *d %02X ", 3+(x>5), i, i); + if (i<32 || i==127) s += sprintf(s, "%.3s", (i<32) ? low+3*i : "DEL"); + else *s++ = i; + } else s += sprintf(s, "Dec Hex%*c", 1+2*(x<2)+(x>4), ' '); + *s++ = (x>6) ? '\n' : ' '; } + writeall(1, toybuf, s-toybuf); } diff --git a/toys/pending/unicode.c b/toys/pending/unicode.c deleted file mode 100644 index 0a9eb24a..00000000 --- a/toys/pending/unicode.c +++ /dev/null @@ -1,65 +0,0 @@ -/* unicode.c - convert between Unicode and UTF-8 - * - * Copyright 2020 The Android Open Source Project. - * - * Loosely based on the Plan9/Inferno unicode(1). - -USE_UNICODE(NEWTOY(unicode, "<1", TOYFLAG_USR|TOYFLAG_BIN)) - -config UNICODE - bool "unicode" - default n - help - usage: unicode [[min]-max] - - Convert between Unicode code points and UTF-8, in both directions. -*/ - -#define FOR_unicode -#include "toys.h" - -static void codepoint(unsigned wc) { - char *low="NULSOHSTXETXEOTENQACKBELBS HT LF VT FF CR SO SI DLEDC1DC2DC3DC4" - "NAKSYNETBCANEM SUBESCFS GS RS US "; - unsigned n, i; - - printf("U+%04X : ", wc); - if (wc < ' ') printf("%.3s", low+(wc*3)); - else if (wc == 0x7f) printf("DEL"); - else { - toybuf[n = wctoutf8(toybuf, wc)] = 0; - printf("%s%s", toybuf, n>1 ? " :":""); - if (n>1) for (i = 0; i < n; i++) printf(" %#02x", toybuf[i]); - } - xputc('\n'); -} - -void unicode_main(void) -{ - unsigned from, to; - char next, **args; - - for (args = toys.optargs; *args; args++) { - // unicode 660-666 => table of `U+0600 : ٠ : 0xd9 0xa0` etc. - if (sscanf(*args, "%x-%x%c", &from, &to, &next) == 2) { - while (from <= to) codepoint(from++); - - // unicode 666 => just `U+0666 : ٦ : 0xd9 0xa6`. - } else if (sscanf(*args, "%x%c", &from, &next) == 1) { - codepoint(from); - - // unicode hello => table showing every character in the string. - } else { - char *s = *args; - size_t l = strlen(s); - wchar_t wc; - int n; - - while ((n = utf8towc(&wc, s, l)) > 0) { - codepoint(wc); - s += n; - l -= n; - } - } - } -} |