From a4eea165bbab6d13f89b59707e835d58b7014a66 Mon Sep 17 00:00:00 2001 From: Stephen Dolan Date: Tue, 18 Sep 2012 17:44:43 +0100 Subject: Move everything around - delete old Haskell code, clean up build. --- jv_unicode.c | 64 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 64 insertions(+) create mode 100644 jv_unicode.c (limited to 'jv_unicode.c') diff --git a/jv_unicode.c b/jv_unicode.c new file mode 100644 index 00000000..b1417a2a --- /dev/null +++ b/jv_unicode.c @@ -0,0 +1,64 @@ +#include +#include +#include "jv_unicode.h" +#include "jv_utf8_tables.gen.h" + +const char* jvp_utf8_next(const char* in, const char* end, int* codepoint) { + if (in == end) { + codepoint = 0; + return 0; + } + unsigned char first = (unsigned char)in[0]; + int length = utf8_coding_length[first]; + if (length == 0 || length == UTF8_CONTINUATION_BYTE || in + length > end) { + *codepoint = -1; + return 0; + } + *codepoint = ((unsigned)in[0]) & utf8_coding_bits[first]; + for (int i=1; i= 0 && codepoint <= 0x10FFFF); + char* start = out; + if (codepoint <= 0x7F) { + *out++ = codepoint; + } else if (codepoint <= 0x7FF) { + *out++ = 0xC0 + ((codepoint & 0x7C0) >> 6); + *out++ = 0x80 + ((codepoint & 0x03F)); + } else if(codepoint <= 0xFFFF) { + *out++ = 0xE0 + ((codepoint & 0xF000) >> 12); + *out++ = 0x80 + ((codepoint & 0x0FC0) >> 6); + *out++ = 0x80 + ((codepoint & 0x003F)); + } else { + *out++ = 0xF0 + ((codepoint & 0x1C0000) >> 18); + *out++ = 0x80 + ((codepoint & 0x03F000) >> 12); + *out++ = 0x80 + ((codepoint & 0x000FC0) >> 6); + *out++ = 0x80 + ((codepoint & 0x00003F)); + } + assert(out - start == jvp_utf8_encode_length(codepoint)); + return out - start; +} -- cgit v1.2.3