[Guile-commits] 03/11: Fix uri-decode behavior for "+"

[Andy Wingo]

wingo pushed a commit to branch stable-2.0
in repository guile.

commit 0a3ea0586d77030e5dda2b39b0a949a2231f0aee
Author: Andy Wingo <address@hidden>
Date:   Mon Jun 20 14:34:19 2016 +0200

    Fix uri-decode behavior for "+"
    
    * module/web/uri.scm (uri-decode): Add #:decode-plus-to-space? keyword
      argument.
      (split-and-decode-uri-path): Don't decode plus to space.
    * doc/ref/web.texi (URIs): Update documentation.
    * test-suite/tests/web-uri.test ("decode"): Add tests.
    * NEWS: Add entry.
    
    Based on a patch by Brent <address@hidden>.
---
 NEWS                          |    7 +++++++
 doc/ref/web.texi              |    7 ++++++-
 module/web/uri.scm            |   11 ++++++++---
 test-suite/tests/web-uri.test |    5 ++++-
 4 files changed, 25 insertions(+), 5 deletions(-)

diff --git a/NEWS b/NEWS
index 8ed1b8d..80f1cd4 100644
--- a/NEWS
+++ b/NEWS
@@ -19,6 +19,13 @@ Guile's reader conform more closely to the R6RS syntax. In 
particular:
 - It enables the `square-brackets', `hungry-eol-escapes' and
   `r6rs-hex-escapes' reader options.
 
+* Bug fixes
+
+** Don't replace + with space when splitting and decoding URI paths
+
+See the documentation for `uri-decode', for more on the new
+`#:decode-plus-to-space?' keyword argument.
+
 
 Changes in 2.0.11 (since 2.0.10):
 
diff --git a/doc/ref/web.texi b/doc/ref/web.texi
index 9e6e0fd..bb478e0 100644
--- a/doc/ref/web.texi
+++ b/doc/ref/web.texi
@@ -245,7 +245,7 @@ serialization.
 Declare a default port for the given URI scheme.
 @end deffn
 
address@hidden {Scheme Procedure} uri-decode str [#:address@hidden"utf-8"}]
address@hidden {Scheme Procedure} uri-decode str [#:address@hidden"utf-8"}] 
[#:decode-plus-to-space? #t]
 Percent-decode the given @var{str}, according to @var{encoding}, which
 should be the name of a character encoding.
 
@@ -262,6 +262,11 @@ decoded bytes are not valid for the given encoding. Pass 
@code{#f} for
 @xref{Ports, @code{set-port-encoding!}}, for more information on
 character encodings.
 
+If @var{decode-plus-to-space?} is true, which is the default, also
+replace instances of the plus character @samp{+} with a space character.
+This is needed when parsing @code{application/x-www-form-urlencoded}
+data.
+
 Returns a string of the decoded characters, or a bytevector if
 @var{encoding} was @code{#f}.
 @end deffn
diff --git a/module/web/uri.scm b/module/web/uri.scm
index 3ab820d..179618d 100644
--- a/module/web/uri.scm
+++ b/module/web/uri.scm
@@ -304,7 +304,7 @@ serialization."
 (define hex-chars
   (string->char-set "0123456789abcdefABCDEF"))
 
-(define* (uri-decode str #:key (encoding "utf-8"))
+(define* (uri-decode str #:key (encoding "utf-8") (decode-plus-to-space? #t))
   "Percent-decode the given STR, according to ENCODING,
 which should be the name of a character encoding.
 
@@ -320,6 +320,10 @@ bytes are not valid for the given encoding. Pass ‘#f’ for 
ENCODING if
 you want decoded bytes as a bytevector directly.  ‘set-port-encoding!’,
 for more information on character encodings.
 
+If DECODE-PLUS-TO-SPACE? is true, which is the default, also replace
+instances of the plus character (+) with a space character.  This is
+needed when parsing application/x-www-form-urlencoded data.
+
 Returns a string of the decoded characters, or a bytevector if
 ENCODING was ‘#f’."
   (let* ((len (string-length str))
@@ -330,7 +334,7 @@ ENCODING was ‘#f’."
                (if (< i len)
                    (let ((ch (string-ref str i)))
                      (cond
-                      ((eqv? ch #\+)
+                      ((and (eqv? ch #\+) decode-plus-to-space?)
                        (put-u8 port (char->integer #\space))
                        (lp (1+ i)))
                       ((and (< (+ i 2) len) (eqv? ch #\%)
@@ -413,7 +417,8 @@ removing empty components.
 For example, ‘\"/foo/bar%20baz/\"’ decodes to the two-element list,
 ‘(\"foo\" \"bar baz\")’."
   (filter (lambda (x) (not (string-null? x)))
-          (map uri-decode (string-split path #\/))))
+          (map (lambda (s) (uri-decode s #:decode-plus-to-space? #f))
+               (string-split path #\/))))
 
 (define (encode-and-join-uri-path parts)
   "URI-encode each element of PARTS, which should be a list of
diff --git a/test-suite/tests/web-uri.test b/test-suite/tests/web-uri.test
index 3d14d9d..e1b6ca3 100644
--- a/test-suite/tests/web-uri.test
+++ b/test-suite/tests/web-uri.test
@@ -255,7 +255,10 @@
     (equal? "foo bar" (uri-decode "foo%20bar")))
 
   (pass-if "foo+bar"
-    (equal? "foo bar" (uri-decode "foo+bar"))))
+    (equal? "foo bar" (uri-decode "foo+bar")))
+
+  (pass-if "foo+bar"
+    (equal? '("foo+bar") (split-and-decode-uri-path "foo+bar"))))
 
 (with-test-prefix "encode"
   (pass-if (equal? "foo%20bar" (uri-encode "foo bar")))