Commit 9033b144 authored by Erich Hoover's avatar Erich Hoover Committed by Alexandre Julliard

hhctrl.ocx: Add HTML to Unicode decoding capability to the table of contents.

parent b527679d
......@@ -50,16 +50,6 @@ static void free_content_item(ContentItem *item)
}
}
static void store_param(LPWSTR *param, const char *value, int len)
{
int wlen;
wlen = MultiByteToWideChar(CP_ACP, 0, value, len, NULL, 0);
*param = heap_alloc((wlen+1)*sizeof(WCHAR));
MultiByteToWideChar(CP_ACP, 0, value, len, *param, wlen);
(*param)[wlen] = 0;
}
static void parse_obj_node_param(ContentItem *item, ContentItem *hhc_root, const char *text)
{
const char *ptr;
......@@ -99,11 +89,11 @@ static void parse_obj_node_param(ContentItem *item, ContentItem *hhc_root, const
const char *local = strstr(ptr, "::")+2;
int local_len = len-(local-ptr);
store_param(&item->local, local, local_len);
item->local = decode_html(local, local_len);
param = &merge;
}
store_param(param, ptr, len);
*param = decode_html(ptr, len);
if(param == &merge) {
SetChmPath(&item->merge, hhc_root->merge.chm_file, merge);
......
......@@ -50,6 +50,119 @@ static void ExpandContract(HHInfo *pHHInfo);
static const WCHAR szEmpty[] = {0};
struct html_encoded_symbol {
const char *html_code;
char ansi_symbol;
};
/*
* Table mapping the conversion between HTML encoded symbols and their ANSI code page equivalent.
* Note: Add additional entries in proper alphabetical order (a binary search is used on this table).
*/
struct html_encoded_symbol html_encoded_symbols[] =
{
{"AElig", 0xC6},
{"Aacute", 0xC1},
{"Acirc", 0xC2},
{"Agrave", 0xC0},
{"Aring", 0xC5},
{"Atilde", 0xC3},
{"Auml", 0xC4},
{"Ccedil", 0xC7},
{"ETH", 0xD0},
{"Eacute", 0xC9},
{"Ecirc", 0xCA},
{"Egrave", 0xC8},
{"Euml", 0xCB},
{"Iacute", 0xCD},
{"Icirc", 0xCE},
{"Igrave", 0xCC},
{"Iuml", 0xCF},
{"Ntilde", 0xD1},
{"Oacute", 0xD3},
{"Ocirc", 0xD4},
{"Ograve", 0xD2},
{"Oslash", 0xD8},
{"Otilde", 0xD5},
{"Ouml", 0xD6},
{"THORN", 0xDE},
{"Uacute", 0xDA},
{"Ucirc", 0xDB},
{"Ugrave", 0xD9},
{"Uuml", 0xDC},
{"Yacute", 0xDD},
{"aacute", 0xE1},
{"acirc", 0xE2},
{"acute", 0xB4},
{"aelig", 0xE6},
{"agrave", 0xE0},
{"amp", '&'},
{"aring", 0xE5},
{"atilde", 0xE3},
{"auml", 0xE4},
{"brvbar", 0xA6},
{"ccedil", 0xE7},
{"cedil", 0xB8},
{"cent", 0xA2},
{"copy", 0xA9},
{"curren", 0xA4},
{"deg", 0xB0},
{"divide", 0xF7},
{"eacute", 0xE9},
{"ecirc", 0xEA},
{"egrave", 0xE8},
{"eth", 0xF0},
{"euml", 0xEB},
{"frac12", 0xBD},
{"frac14", 0xBC},
{"frac34", 0xBE},
{"gt", '>'},
{"iacute", 0xED},
{"icirc", 0xEE},
{"iexcl", 0xA1},
{"igrave", 0xEC},
{"iquest", 0xBF},
{"iuml", 0xEF},
{"laquo", 0xAB},
{"lt", '<'},
{"macr", 0xAF},
{"micro", 0xB5},
{"middot", 0xB7},
{"nbsp", ' '},
{"not", 0xAC},
{"ntilde", 0xF1},
{"oacute", 0xF3},
{"ocirc", 0xF4},
{"ograve", 0xF2},
{"ordf", 0xAA},
{"ordm", 0xBA},
{"oslash", 0xF8},
{"otilde", 0xF5},
{"ouml", 0xF6},
{"para", 0xB6},
{"plusmn", 0xB1},
{"pound", 0xA3},
{"quot", '"'},
{"raquo", 0xBB},
{"reg", 0xAE},
{"sect", 0xA7},
{"shy", 0xAD},
{"sup1", 0xB9},
{"sup2", 0xB2},
{"sup3", 0xB3},
{"szlig", 0xDF},
{"thorn", 0xFE},
{"times", 0xD7},
{"uacute", 0xFA},
{"ucirc", 0xFB},
{"ugrave", 0xF9},
{"uml", 0xA8},
{"uuml", 0xFC},
{"yacute", 0xFD},
{"yen", 0xA5},
{"yuml", 0xFF}
};
/* Loads a string from the resource file */
static LPWSTR HH_LoadString(DWORD dwID)
{
......@@ -1654,3 +1767,92 @@ HHInfo *CreateHelpViewer(LPCWSTR filename)
return info;
}
/*
* Search the table of HTML entities and return the corresponding ANSI symbol.
*/
static char find_html_symbol(const char *entity, int entity_len)
{
int max = sizeof(html_encoded_symbols)/sizeof(html_encoded_symbols[0])-1;
int min = 0, dir;
while(min <= max)
{
int pos = (min+max)/2;
const char *encoded_symbol = html_encoded_symbols[pos].html_code;
dir = strncmp(encoded_symbol, entity, entity_len);
if(dir == 0 && !encoded_symbol[entity_len]) return html_encoded_symbols[pos].ansi_symbol;
if(dir < 0)
min = pos+1;
else
max = pos-1;
}
return 0;
}
/*
* Decode a string containing HTML encoded characters into a unicode string.
*/
WCHAR *decode_html(const char *html_fragment, int html_fragment_len)
{
const char *h = html_fragment;
char *amp, *sem, symbol, *tmp;
int len, tmp_len = 0;
WCHAR *unicode_text;
tmp = heap_alloc(html_fragment_len+1);
while(1)
{
symbol = 0;
amp = strchr(h, '&');
if(!amp) break;
len = amp-h;
/* Copy the characters prior to the HTML encoded character */
memcpy(&tmp[tmp_len], h, len);
tmp_len += len;
amp++; /* skip ampersand */
sem = strchr(amp, ';');
/* Require a semicolon after the ampersand */
if(!sem)
{
h = amp;
tmp[tmp_len++] = '&';
continue;
}
/* Find the symbol either by using the ANSI character number (prefixed by the pound symbol)
* or by searching the HTML entity table */
len = sem-amp;
if(amp[0] == '#')
{
char *endnum = NULL;
int tmp;
tmp = (char) strtol(amp, &endnum, 10);
if(endnum == sem)
symbol = tmp;
}
else
symbol = find_html_symbol(amp, len);
if(!symbol)
{
FIXME("Failed to translate HTML encoded character '&%.*s;'.\n", len, amp);
h = amp;
tmp[tmp_len++] = '&';
continue;
}
/* Insert the new symbol */
h = sem+1;
tmp[tmp_len++] = symbol;
}
/* Convert any remaining characters */
len = html_fragment_len-(h-html_fragment);
memcpy(&tmp[tmp_len], h, len);
tmp_len += len;
tmp[tmp_len++] = 0; /* NULL-terminate the string */
len = MultiByteToWideChar(CP_ACP, 0, tmp, tmp_len, NULL, 0);
unicode_text = heap_alloc(len*sizeof(WCHAR));
MultiByteToWideChar(CP_ACP, 0, tmp, tmp_len, unicode_text, len);
heap_free(tmp);
return unicode_text;
}
......@@ -193,6 +193,8 @@ void ReleaseSearch(HHInfo *info) DECLSPEC_HIDDEN;
LPCWSTR skip_schema(LPCWSTR url) DECLSPEC_HIDDEN;
WCHAR *decode_html(const char *html_fragment, int html_fragment_len);
/* memory allocation functions */
static inline void * __WINE_ALLOC_SIZE(1) heap_alloc(size_t len)
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment