[uri] Decode/encode URIs when parsing/unparsing

Currently, handling of URI escapes is ad-hoc; escaped strings are
stored as-is in the URI structure, and it is up to the individual
protocol to unescape as necessary. This is error-prone and expensive
in terms of code size. Modify this behavior by unescaping in
parse_uri() and escaping in unparse_uri() those fields that typically
handle URI escapes (hostname, user, password, path, query, fragment),
and allowing unparse_uri() to accept a subset of fields to print so
it can be easily used to generate e.g. the escaped HTTP path?query
request.

Signed-off-by: Joshua Oreman <oremanj@rwcr.net>
Signed-off-by: Marty Connor <mdc@etherboot.org>

1 files changed, 41 insertions, 3 deletions

diff --git a/src/include/gpxe/uri.h b/src/include/gpxe/uri.h
index 03c88d25f..405d0ce9d 100644
--- a/src/include/gpxe/uri.h
+++ b/src/include/gpxe/uri.h
@@ -20,6 +20,10 @@ FILE_LICENCE ( GPL2_OR_LATER );
  *
  * Note that all fields within a URI are optional and may be NULL.
  *
+ * The pointers to the various fields are packed together so they can
+ * be accessed in array fashion in some places in uri.c where doing so
+ * saves significant code size.
+ *
  * Some examples are probably helpful:
  *
  *   http://www.etherboot.org/wiki :
@@ -61,8 +65,40 @@ struct uri {
 	const char *query;
 	/** Fragment */
 	const char *fragment;
+} __attribute__ (( packed ));
+
+/** A field in a URI
+ *
+ * The order of the indices in this enumeration must match the order
+ * of the fields in the URI structure.
+ */
+enum {
+	URI_SCHEME = 0,		URI_SCHEME_BIT = ( 1 << URI_SCHEME ),
+	URI_OPAQUE = 1,		URI_OPAQUE_BIT = ( 1 << URI_OPAQUE ),
+	URI_USER = 2,		URI_USER_BIT = ( 1 << URI_USER ),
+	URI_PASSWORD = 3,	URI_PASSWORD_BIT = ( 1 << URI_PASSWORD ),
+	URI_HOST = 4,		URI_HOST_BIT = ( 1 << URI_HOST ),
+	URI_PORT = 5,		URI_PORT_BIT = ( 1 << URI_PORT ),
+	URI_PATH = 6,		URI_PATH_BIT = ( 1 << URI_PATH ),
+	URI_QUERY = 7,		URI_QUERY_BIT = ( 1 << URI_QUERY ),
+	URI_FRAGMENT = 8,	URI_FRAGMENT_BIT = ( 1 << URI_FRAGMENT ),
+
+	URI_FIRST_FIELD = URI_SCHEME,
+	URI_LAST_FIELD = URI_FRAGMENT,
 };
 
+/** Extract field from URI */
+#define uri_get_field( uri, field )	(&uri->scheme)[field]
+
+/** All URI fields */
+#define URI_ALL		( URI_SCHEME_BIT | URI_OPAQUE_BIT | URI_USER_BIT | \
+			  URI_PASSWORD_BIT | URI_HOST_BIT | URI_PORT_BIT | \
+			  URI_PATH_BIT | URI_QUERY_BIT | URI_FRAGMENT_BIT )
+
+/** URI fields that should be decoded on storage */
+#define URI_ENCODED	( URI_USER_BIT | URI_PASSWORD_BIT | URI_HOST_BIT | \
+			  URI_PATH_BIT | URI_QUERY_BIT | URI_FRAGMENT_BIT )
+
 /**
  * URI is an absolute URI
  *
@@ -131,14 +167,16 @@ extern struct uri *cwuri;
 
 extern struct uri * parse_uri ( const char *uri_string );
 extern unsigned int uri_port ( struct uri *uri, unsigned int default_port );
-extern int unparse_uri ( char *buf, size_t size, struct uri *uri );
+extern int unparse_uri ( char *buf, size_t size, struct uri *uri,
+			 unsigned int fields );
 extern struct uri * uri_dup ( struct uri *uri );
 extern char * resolve_path ( const char *base_path,
 			     const char *relative_path );
 extern struct uri * resolve_uri ( struct uri *base_uri,
 				  struct uri *relative_uri );
 extern void churi ( struct uri *uri );
-extern size_t uri_encode ( const char *raw_string, char *buf, size_t len );
-extern size_t uri_decode ( const char *encoded_string, char *buf, size_t len );
+extern size_t uri_encode ( const char *raw_string, char *buf, ssize_t len,
+			   int field );
+extern size_t uri_decode ( const char *encoded_string, char *buf, ssize_t len );
 
 #endif /* _GPXE_URI_H */