diff options
| author | Mark Lodato <lodatom@gmail.com> | 2010-02-09 10:12:43 -0500 | 
|---|---|---|
| committer | Mark Lodato <lodatom@gmail.com> | 2010-02-09 10:12:43 -0500 | 
| commit | a2c6355f9fdede78ce46aeee39ef649637aaadf9 (patch) | |
| tree | 4ed595f688691e7a35c5684ca59164bcc777b74c | |
| parent | 8aab27f24de70acfbdcee31c634a4b1facf23b92 (diff) | |
html: properly percent-escape URLs
The only valid characters for a URL are unreserved characters
a-zA-Z0-9_-.~ and the reserved characters !*'();:@&=+$,/?%#[] , as per
RFC 3986.  Everything else must be escaped.  Additionally, the # and
? always have special meaning, and the &, =, and + have special meaning
in a query string, so they too must be escaped.  To make this easier,
a table of escapes is now used so that we do not have to call fmt() for
each character; if the entry is 0, no escaping is needed.
Signed-off-by: Mark Lodato <lodatom@gmail.com>
| -rw-r--r-- | html.c | 36 | 
1 files changed, 32 insertions, 4 deletions
| @@ -13,6 +13,32 @@  #include <string.h>  #include <errno.h> +/* Percent-encoding of each character, except: a-zA-Z0-9!$()*,./:;@- */ +static const char* url_escape_table[256] = { +	"%00", "%01", "%02", "%03", "%04", "%05", "%06", "%07", "%08", "%09", +	"%0a", "%0b", "%0c", "%0d", "%0e", "%0f", "%10", "%11", "%12", "%13", +	"%14", "%15", "%16", "%17", "%18", "%19", "%1a", "%1b", "%1c", "%1d", +	"%1e", "%1f", "%20", 0, "%22", "%23", 0, "%25", "%26", "%27", 0, 0, 0, +	"%2b", 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, "%3c", "%3d", +	"%3e", "%3f", 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, +	0, 0, 0, 0, 0, 0, 0, 0, 0, "%5c", 0, "%5e", 0, "%60", 0, 0, 0, 0, 0, +	0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, "%7b", +	"%7c", "%7d", 0, "%7f", "%80", "%81", "%82", "%83", "%84", "%85", +	"%86", "%87", "%88", "%89", "%8a", "%8b", "%8c", "%8d", "%8e", "%8f", +	"%90", "%91", "%92", "%93", "%94", "%95", "%96", "%97", "%98", "%99", +	"%9a", "%9b", "%9c", "%9d", "%9e", "%9f", "%a0", "%a1", "%a2", "%a3", +	"%a4", "%a5", "%a6", "%a7", "%a8", "%a9", "%aa", "%ab", "%ac", "%ad", +	"%ae", "%af", "%b0", "%b1", "%b2", "%b3", "%b4", "%b5", "%b6", "%b7", +	"%b8", "%b9", "%ba", "%bb", "%bc", "%bd", "%be", "%bf", "%c0", "%c1", +	"%c2", "%c3", "%c4", "%c5", "%c6", "%c7", "%c8", "%c9", "%ca", "%cb", +	"%cc", "%cd", "%ce", "%cf", "%d0", "%d1", "%d2", "%d3", "%d4", "%d5", +	"%d6", "%d7", "%d8", "%d9", "%da", "%db", "%dc", "%dd", "%de", "%df", +	"%e0", "%e1", "%e2", "%e3", "%e4", "%e5", "%e6", "%e7", "%e8", "%e9", +	"%ea", "%eb", "%ec", "%ed", "%ee", "%ef", "%f0", "%f1", "%f2", "%f3", +	"%f4", "%f5", "%f6", "%f7", "%f8", "%f9", "%fa", "%fb", "%fc", "%fd", +	"%fe", "%ff" +}; +  int htmlfd = STDOUT_FILENO;  char *fmt(const char *format, ...) @@ -135,9 +161,10 @@ void html_url_path(const char *txt)  	const char *t = txt;  	while(t && *t){  		int c = *t; -		if (c=='"' || c=='#' || c=='\'' || c=='?') { +		const char *e = url_escape_table[c]; +		if (e && c!='+' && c!='&' && c!='+') {  			write(htmlfd, txt, t - txt); -			write(htmlfd, fmt("%%%2x", c), 3); +			write(htmlfd, e, 3);  			txt = t+1;  		}  		t++; @@ -151,9 +178,10 @@ void html_url_arg(const char *txt)  	const char *t = txt;  	while(t && *t){  		int c = *t; -		if (c=='"' || c=='#' || c=='%' || c=='&' || c=='\'' || c=='+' || c=='?') { +		const char *e = url_escape_table[c]; +		if (e) {  			write(htmlfd, txt, t - txt); -			write(htmlfd, fmt("%%%2x", c), 3); +			write(htmlfd, e, 3);  			txt = t+1;  		}  		t++; | 
