Re: Help establishing wctype character classes

[Rich Felker <dalias@aerifal.cx>]

[-- Attachment #1: Type: text/plain, Size: 341 bytes --]

And here's a quick implementation of the iswalnum set generator. At
this point it just generates a dumb lookup table without doing any
multi-level table optimizations or compression, and dumps the table to
stdout in a visual form. I need to run some analysis on the table to
determine the best way to get it down to a reasonable size.

Rich

[-- Attachment #2: gen_ctype_alpha.c --]
[-- Type: text/plain, Size: 1046 bytes --]

#include <stdio.h>

int main()
{
	char *set = calloc(0x110000,1);
	char buf[128], dummy;
	int a, b;
	FILE *f;

	/* Alphabetic property */
	f = fopen("DerivedCoreProperties.txt", "rb");
	while (fgets(buf, sizeof buf, f)) {
		if (sscanf(buf, "%x..%x ; Alphabetic%c", &a, &b, &dummy)==3)
			for (; a<=b; a++) set[a]=1;
		else if (sscanf(buf, "%x ; Alphabetic%c", &a, &dummy)==2)
			set[a] = 1;
	}
	fclose(f);

	/* Plus Nd category */
	f = fopen("UnicodeData.txt", "rb");
	while (fgets(buf, sizeof buf, f)) {
		if (sscanf(buf, "%x;%*[^;];Nd%c", &a, &dummy)==2)
			set[a] = 1;
	}
	fclose(f);

	/* Fix misclassified Thai characters */
	set[0xe2f] = set[0xe46] = 0;

	/* Fill in elided CJK ranges */
	for (a=0x3400; a<=0x4db5; a++) set[a]=1;
	for (a=0x4e00; a<=0x9fcc; a++) set[a]=1;
	for (a=0xac00; a<=0xd7a3; a++) set[a]=1;
	for (a=0x20000; a<=0x2a6d6; a++) set[a]=1;
	for (a=0x2a700; a<=0x2b734; a++) set[a]=1;
	for (a=0x2b740; a<=0x2b81d; a++) set[a]=1;

	for (a=0; a<0x110000; a++) {
		putchar(set[a]?'*':'.');
		if (!(a+1&63)) putchar('\n');
	}
}