From b8adfd6a6514c18dd612a1940ad9b2acc98d2ced Mon Sep 17 00:00:00 2001 From: Bryce Kwon Date: Fri, 14 Aug 2026 09:31:16 -1000 Subject: Fix ampersand handling in generated urls --- source/html.c | 50 ++++++++++++++++++++++++++------------------------ 1 file changed, 26 insertions(+), 24 deletions(-) (limited to 'source/html.c') diff --git a/source/html.c b/source/html.c index 58ccf3b..f69f109 100644 --- a/source/html.c +++ b/source/html.c @@ -18,37 +18,37 @@ // carry as themselves. Those are the letters, the digits, and !$()*,-./:;@[]_~ static const char *url_escape_table[256] = { "%00", "%01", "%02", "%03", "%04", "%05", "%06", "%07", - "%08", "%09", "%0a", "%0b", "%0c", "%0d", "%0e", "%0f", + "%08", "%09", "%0A", "%0B", "%0C", "%0D", "%0E", "%0F", "%10", "%11", "%12", "%13", "%14", "%15", "%16", "%17", - "%18", "%19", "%1a", "%1b", "%1c", "%1d", "%1e", "%1f", + "%18", "%19", "%1A", "%1B", "%1C", "%1D", "%1E", "%1F", "%20", NULL, "%22", "%23", NULL, "%25", "%26", "%27", - NULL, NULL, NULL, "%2b", NULL, NULL, NULL, NULL, + NULL, NULL, NULL, "%2B", NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, - NULL, NULL, NULL, NULL, "%3c", "%3d", "%3e", "%3f", + NULL, NULL, NULL, NULL, "%3C", "%3D", "%3E", "%3F", NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, - NULL, NULL, NULL, NULL, "%5c", NULL, "%5e", NULL, + NULL, NULL, NULL, NULL, "%5C", NULL, "%5E", NULL, "%60", NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, - NULL, NULL, NULL, "%7b", "%7c", "%7d", NULL, "%7f", + NULL, NULL, NULL, "%7B", "%7C", "%7D", NULL, "%7F", "%80", "%81", "%82", "%83", "%84", "%85", "%86", "%87", - "%88", "%89", "%8a", "%8b", "%8c", "%8d", "%8e", "%8f", + "%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" + "%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" }; static char out_buf[HTML_WRITE_BUFSIZE]; @@ -256,11 +256,13 @@ void html_url_path(const char *txt) const char *p = txt; while (p && *p) { unsigned char c = *p; + // A raw ampersand or plus is legal in a URL path, but the + // paths written here land in attribute values, where a bare + // ampersand can start a character reference and quietly turn + // "a©.txt" into a different filename. Encoding both keeps + // the output byte-safe in every sink. const char *esc = url_escape_table[c]; - // The table is shared with the query string case, where a plus - // means a space and an ampersand separates parameters. Neither - // carries that meaning in a path. - if (esc && c != '+' && c != '&') { + if (esc) { html_raw(txt, p - txt); html(esc); txt = p + 1; -- cgit v2.8.0