makeuctb.c

基于rtos开发的浏览器！

	    if (un0 < 0) {
		fprintf(stderr, "Bad input line: %s\n", buffer);
		exit(EX_DATAERR);
		fprintf(stderr,
    "%s: Bad Unicode range corresponding to font position range 0x%x-0x%x\n",
			tblname, fp0, fp1);
		exit(EX_DATAERR);
	    }
	    un1 = un0;
	    while (*p == ' ' || *p == '\t') {
		p++;
	    }
	    if (*p == '-') {
		p++;
		while (*p == ' ' || *p == '\t') {
		    p++;
		}
		un1 = getunicode(&p);
		if (un1 < 0 || un1 < un0) {
		    fprintf(stderr,
			    "%s: Bad Unicode range U+%x-U+%x\n",
			    tblname, un0, un1);
		    fprintf(stderr, "Bad input line: %s\n", buffer);
		    exit(EX_DATAERR);
		}
		while (*p == ' ' || *p == '\t') {
		    p++;
		}
	    }

	    if (*p != ':' && *p != '"') {
		fprintf(stderr, "No ':' or '\"' where expected: %s\n",
			buffer);
		continue;
	    }

	    tbuf = (char *)malloc(4*strlen(p));

	    if (!(p1 = tbuf)) {
		fprintf(stderr, "%s: Out of memory\n", tblname);
		exit(EX_DATAERR);
	    }
	    if (*p == '"') {
		/*
		 *  Handle "<C replace>".
		 *  Copy chars verbatim until first '"' not \-escaped or
		 *  end of buffer.
		 */
		int escaped = 0;
		for (ch = *(++p); (ch = *p) != '\0'; p++) {
		    if (escaped) {
			escaped = 0;
		    } else if (ch == '"') {
			break;
		    } else if (ch == '\\') {
			escaped = 1;
		    }
		    *p1++ = ch;
		}
		if (escaped || ch != '"') {
		    fprintf(stderr, "Warning: String not terminated: %s\n",
			    buffer);
		    if (escaped)
			*p1++ = '\n';
		}
	    } else {
		/*
		 *  We had ':'.
		 */
		for (ch = *(++p); (ch = *p) != '\0'; p++, p1++) {
		    if ((unsigned char)ch < 32 || ch == '\\' || ch == '\"' ||
			(unsigned char)ch >= 127) {
			sprintf(p1, "\\%.3o", (unsigned char)ch); 
#ifdef NOTDEFINED
			fprintf(stderr, "%s\n", tbuf);
#endif /* NOTDEFINED */
			p1 += 3;
		    } else {
			*p1 = ch;
		    }
		}
	    }
	    *p1 = '\0';
	    for (i = un0; i <= un1; i++) {
#ifdef NOTDEFINED
		printf("U+0x%x:%s\n", i, tbuf); */
#endif /* NOTDEFINED */
		addpair_str(tbuf,i);
	    }
	    continue;
	}

	/*
	 *  Input line (after skipping spaces) doesn't start with one
	 *  of the specially recognized characters, so try to interpret
	 *  it as starting with a fontpos.
	 */
	fp0 = strtol(p, &p1, 0);
	if (p1 == p) {
	    fprintf(stderr, "Bad input line: %s\n", buffer);
	    exit(EX_DATAERR);
        }
	p = p1;

	while (*p == ' ' || *p == '\t') {
	    p++;
	}
	if (*p == '-') {
	    p++;
	    fp1 = strtol(p, &p1, 0);
	    if (p1 == p) {
		fprintf(stderr, "Bad input line: %s\n", buffer);
		exit(EX_DATAERR);
	    }
	    p = p1;
        } else {
	    fp1 = 0;
	}

	if (fp0 < 0 || fp0 >= fontlen) {
	    fprintf(stderr,
		    "%s: Glyph number (0x%x) larger than font length\n",
		    tblname, fp0);
	    exit(EX_DATAERR);
	}
	if (fp1 && (fp1 < fp0 || fp1 >= fontlen)) {
	    fprintf(stderr,
		    "%s: Bad end of range (0x%x)\n",
		    tblname, fp1);
	    exit(EX_DATAERR);
	}

	if (fp1) {
	    /*
	     *  We have a range; expect the word "idem"
	     *  or a Unicode range of the same length.
	     */
	    while (*p == ' ' || *p == '\t') {
		p++;
	    }
	    if (!strncmp(p, "idem", 4)) {
		for (i = fp0; i <= fp1; i++) {
		    addpair(i,i);
		}
		p += 4;
	    } else {
		un0 = getunicode(&p);
		while (*p == ' ' || *p == '\t') {
		    p++;
		}
		if (*p != '-') {
		    fprintf(stderr,
			    "%s: Corresponding to a range of font positions,",
			    tblname);
		    fprintf(stderr,
			    " there should be a Unicode range.\n");
		    exit(EX_DATAERR);
	        }
		p++;
		un1 = getunicode(&p);
		if (un0 < 0 || un1 < 0) {
		    fprintf(stderr,
     "%s: Bad Unicode range corresponding to font position range 0x%x-0x%x\n",
			    tblname, fp0, fp1);
		    exit(EX_DATAERR);
	        }
		if (un1 - un0 != fp1 - fp0) {
		    fprintf(stderr,
			"%s: Unicode range U+%x-U+%x not of the same length",
			    tblname, un0, un1);
		    fprintf(stderr,
			    " as font position range 0x%x-0x%x\n",
			    fp0, fp1);
		    exit(EX_DATAERR);
	        }
		for (i = fp0; i <= fp1; i++) {
		    addpair(i,un0-fp0+i);
		}
	    }
	} else {
	    /*
	     *  No range; expect a list of unicode values
	     *  or unicode ranges for a single font position,
	     *  or the word "idem"
	     */
	    while (*p == ' ' || *p == '\t') {
		p++;
	    }
	    if (!strncmp(p, "idem", 4)) {
		addpair(fp0,fp0);
		p += 4;
	    }
	    while ((un0 = getunicode(&p)) >= 0) {
		addpair(fp0, un0);
		while (*p == ' ' || *p == '\t') {
		    p++;
		}
		if (*p == '-') {
		    p++;
		    un1 = getunicode(&p);
		    if (un1 < un0) {
			fprintf(stderr,
				"%s: Bad Unicode range 0x%x-0x%x\n",
				tblname, un0, un1);
			exit(EX_DATAERR);
		    }
		    for (un0++; un0 <= un1; un0++) {
			addpair(fp0, un0);
		    }
		}
	    }
	}
	while (*p == ' ' || *p == '\t') {
	    p++;
	}
	if (*p && *p != '#') {
	    fprintf(stderr, "%s: trailing junk (%s) ignored\n", tblname, p);
	}
    }

    /*
     *  Okay, we hit EOF, now output tables.
     */
    fclose(ctbl);
  

    /*
     *  Compute total size of Unicode list.
     */
    nuni = 0;
    for (i = 0 ; i < fontlen ; i++) {
	nuni += unicount[i];
    }

    if (argc >= 3) {
	strncpy(this_MIMEcharset,argv[2],UC_MAXLEN_MIMECSNAME);
    } else if (this_MIMEcharset[0] == '\0') {
	strncpy(this_MIMEcharset,tblname,UC_MAXLEN_MIMECSNAME);
	if ((p = strchr(this_MIMEcharset,'.')) != 0) {
	    *p = '\0';
	}
    }
    for (p = this_MIMEcharset; *p; p++) {
	*p = TOLOWER(*p);
    }
    if (argc >= 4) {
	strncpy(this_LYNXcharset,argv[3],UC_MAXLEN_LYNXCSNAME);
    } else if (this_LYNXcharset[0] == '\0') {
	strncpy(this_LYNXcharset,this_MIMEcharset,UC_MAXLEN_LYNXCSNAME);
    }
    if ((i = strlen(this_LYNXcharset)) < UC_LEN_LYNXCSNAME) {
	for (; i < UC_LEN_LYNXCSNAME; i++) {
	    this_LYNXcharset[i] = ' ';
	}
	this_LYNXcharset[i] = '\0';
    }
#ifdef NOTDEFINED
    fprintf(stderr,"this_MIMEcharset: %s.\n",this_MIMEcharset);
    fprintf(stderr,"this_LYNXcharset: %s.\n",this_LYNXcharset);
#endif /* NOTDEFINED */
    if (this_isDefaultMap == -1) {
	this_isDefaultMap = !strncmp(this_MIMEcharset,"iso-8859-1", 10);
    }
    fprintf(stderr,
    	    "makeuctb: %s: %stranslation map",
 	    this_MIMEcharset, (this_isDefaultMap ? "default " : ""));
    if (this_isDefaultMap == 1) {
	*id_append = '\0';
    } else {
	for (i = 0, p = this_MIMEcharset;
	     *p && (i < UC_MAXLEN_ID_APPEND-1);
	     p++, i++) {
	    id_append[i+1] = isalnum(*p) ? *p : '_';
	}
    }
    id_append[i+1] = '\0';
    fprintf(stderr, " (%s).\n", id_append);

    printf("\
/*\n\
 *  uni_hash.tbl\n\
 *\n\
 *  Do not edit this file; it was automatically generated by\n\
 *\n\
 *  %s %s\n\
 *\n\
 */\n\
\n\
static u8 dfont_unicount%s[%d] = \n\
{\n\t", argv[0], argv[1], id_append, fontlen);

    for (i = 0; i < fontlen; i++) {
	if (i >= 128 && unicount[i] > 0 && i < lowest_eight) {
	    lowest_eight = i;
	}
	printf("%3d", unicount[i]);
	if (i == (fontlen - 1)) {
	    printf("\n};\n");
	} else if ((i % 8) == 7) {
	    printf(",\n\t");
	} else {
	    printf(", ");
	}
    }

    /*
     *  If lowest_eightbit is anything else but 999,
     *  this can't be 7-bit only.
     */
    if (lowest_eight != 999 && !RawOrEnc) {
	RawOrEnc = UCT_ENC_8BIT;
    }

    if (nuni) {
	printf("\nstatic u16 dfont_unitable%s[%d] = \n{\n\t",
	       id_append, nuni);
    } else {
	printf("\nstatic u16 dfont_unitable%s[1]; /* dummy */\n", id_append);
    }

    fp0 = 0;
    nent = 0;
    for (i = 0; i < nuni; i++) {
	while (nent >= unicount[fp0]) {
	    fp0++;
	    nent = 0;
	}
	printf("0x%04x", unitable[fp0][nent++]);
	if (i == (nuni - 1)) {
	    printf("\n};\n");
	} else if ((i % 8) == 7) {
	    printf(",\n\t");
	} else {
	    printf(", ");
	}
    }

    if (themap_str.entry_ct) {
	printf("\n\
static struct unipair_str repl_map%s[%d] = \n\
{\n\t", id_append, themap_str.entry_ct);
    } else {
	printf("\n\
/* static struct unipair_str repl_map%s[]; */\n", id_append);
    }
    
    for (i = 0; i < themap_str.entry_ct; i++) {
	printf("{0x%x,\"%s\"}",
	       themap_str.entries[i].unicode,
	       themap_str.entries[i].replace_str);
	if (i == (themap_str.entry_ct - 1)) {
	    printf("\n};\n");
	} else if ((i % 4) == 3) {
	    printf(",\n\t");
	} else {
	    printf(", ");
	}
    }
    if (themap_str.entry_ct) {
	printf("\n\
static struct unimapdesc_str dfont_replacedesc%s = {%d,repl_map%s,",
id_append, themap_str.entry_ct, id_append);
    } else {
	printf("\n\
static struct unimapdesc_str dfont_replacedesc%s = {0,NULL,",id_append);
    }
    printf("%d,%d};\n",
    this_isDefaultMap ? 1 : 0,
    (useDefaultMap && !this_isDefaultMap) ? 1 : 0
    );


    printf("#define UC_CHARSET_SETUP%s UC_Charset_Setup(\
\"%s\",\\\n\"%s\",\\\n\
dfont_unicount%s,dfont_unitable%s,%d,\\\n\
dfont_replacedesc%s,%d,%d)\n",
id_append, this_MIMEcharset, this_LYNXcharset,
id_append, id_append, nuni, id_append, lowest_eight, RawOrEnc);

    exit(EX_OK);
}