diff options
author | Elliott Hughes <enh@google.com> | 2020-12-05 17:41:39 -0800 |
---|---|---|
committer | Rob Landley <rob@landley.net> | 2020-12-06 02:24:12 -0600 |
commit | ed3d5eb0eaf74e6686bc2576b2c4d5a5343dfd57 (patch) | |
tree | e0116710fb056cee84f021d8b2c230806679b65b /toys | |
parent | 49c02dbe435681015a88c636749d144044fc5e4a (diff) | |
download | toybox-ed3d5eb0eaf74e6686bc2576b2c4d5a5343dfd57.tar.gz |
unicode: new toy.
Based loosely on the Plan9/Inferno utility, and a convenient way to go back
and forth between code points and utf8 sequences.
This patch also fixes a couple of bugs in wctoutf8 (and the tests for this
toy effectively serve as unit tests for wctoutf8/utf8towc).
Diffstat (limited to 'toys')
-rw-r--r-- | toys/pending/unicode.c | 65 |
1 files changed, 65 insertions, 0 deletions
diff --git a/toys/pending/unicode.c b/toys/pending/unicode.c new file mode 100644 index 00000000..0a9eb24a --- /dev/null +++ b/toys/pending/unicode.c @@ -0,0 +1,65 @@ +/* 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; + } + } + } +} |