Explain the table's encoded ampersand and plus

1 file changed, 5 insertions, 6 deletions

diff --git a/source/html.c b/source/html.cindex 7ad4642..7d2e668 100644--- a/source/html.c+++ b/source/html.c@@ -16,7 +16,11 @@ #define HTML_WRITE_BUFSIZE (64 * 1024)  // The percent encoding for each byte, with NULL marking the bytes a URL may-// carry as themselves. Those are the letters, the digits, and !$()*,-./:;@[]_~+// carry as themselves. An ampersand or plus is legal in a path but encoded all+// the same, since a bare plus in a query argument decodes back as a space, and+// an ampersand in an attribute value can start a character reference and+// quietly turn "a&copy.txt" into a different filename. The bytes left as+// themselves are the letters, the digits, and !$()*,-./:;@[]_~ static const char *url_escape_table[256] = { 	"%00", "%01", "%02", "%03", "%04", "%05", "%06", "%07", 	"%08", "%09", "%0A", "%0B", "%0C", "%0D", "%0E", "%0F",@@ -388,11 +392,6 @@ void html_url_path(const char *txt)  	while (p && *p) { 		unsigned char c = *p;-		// A raw ampersand or plus is legal in a URL path, but this-		// table is shared with html_url_arg, where a bare plus decodes-		// back as a space, and the paths written here land in attribute-		// values, where an ampersand can start a character reference-		// and quietly turn "a&copy.txt" into a different filename. 		const char *esc = url_escape_table[c]; 		if (esc) { 			html_raw(txt, p - txt);
diff --git a/source/html.c b/source/html.c
index 7ad4642..7d2e668 100644
--- a/source/html.c
+++ b/source/html.c
@@ -16,7 +16,11 @@
 #define HTML_WRITE_BUFSIZE (64 * 1024)
 
 // The percent encoding for each byte, with NULL marking the bytes a URL may
-// carry as themselves. Those are the letters, the digits, and !$()*,-./:;@[]_~
+// carry as themselves. An ampersand or plus is legal in a path but encoded all
+// the same, since a bare plus in a query argument decodes back as a space, and
+// an ampersand in an attribute value can start a character reference and
+// quietly turn "a&copy.txt" into a different filename. The bytes left as
+// themselves are the letters, the digits, and !$()*,-./:;@[]_~
 static const char *url_escape_table[256] = {
 	"%00", "%01", "%02", "%03", "%04", "%05", "%06", "%07",
 	"%08", "%09", "%0A", "%0B", "%0C", "%0D", "%0E", "%0F",
@@ -388,11 +392,6 @@ void html_url_path(const char *txt)
 
 	while (p && *p) {
 		unsigned char c = *p;
-		// A raw ampersand or plus is legal in a URL path, but this
-		// table is shared with html_url_arg, where a bare plus decodes
-		// back as a space, and the paths written here land in attribute
-		// values, where an ampersand can start a character reference
-		// and quietly turn "a&copy.txt" into a different filename.
 		const char *esc = url_escape_table[c];
 		if (esc) {
 			html_raw(txt, p - txt);