From c593bdd8b7c62ea857fb196ceeb003bb87caf9fa Mon Sep 17 00:00:00 2001
From: "Artyom V. Poptsov" <address@hidden>
Date: Tue, 6 Oct 2015 10:20:57 +0300
Subject: [PATCH] Provide means to 'read' an #<unspecified> object

Currently there's no way to 'read' back an unspecified value, but in
some cases such a feature might be handy (eg. in case of reading a
vector filled with unspecified objects.)  This patch changes the way the
reader treats the returned value of a reader extension callback set by
'read-hash-extend': now when the callback returns a multiple values
object and the second value is '#t', the 1st value returned as is, even
if it is an unspecified object.

If a callback returns an unspecified object alone, it is considered as
an indication that the callback could not read an object -- in other
words, the solution should be backward compatible with existing reader
extenstions.

* libguile/read.c (scm_read_sharp): Check whether the value returned by
  'scm_read_sharp_extension' is a multiple values object and handle it
  appropriately if so.
  (read_inner_expression): Handle multiple values object returned by
  'scm_read_sharp'.
* test-suite/tests/reader.test: Add a test for 'read-hash-extend' to
  ensure that the callback can return an unspecified object.  Add a test
  for the same procedure that ensures that the callback can indicate an
  unknown object by returning an unspecified value alone.
* doc/ref/api-evaluation.texi: Update description of 'read-hash-extend'.
---
 doc/ref/api-evaluation.texi  |  8 ++++++++
 libguile/read.c              | 19 +++++++++++++------
 test-suite/tests/reader.test | 11 +++++++++++
 3 files changed, 32 insertions(+), 6 deletions(-)

diff --git a/doc/ref/api-evaluation.texi b/doc/ref/api-evaluation.texi
index 296f1da..8278ab9 100644
--- a/doc/ref/api-evaluation.texi
+++ b/doc/ref/api-evaluation.texi
@@ -298,6 +298,14 @@ starting with the character sequence @code{#} and @var{chr}.
 @var{proc} will be called with two arguments:  the character
 @var{chr} and the port to read further data from. The object
 returned will be the return value of @code{read}. 
+
+Returning of an unspecified value (value of the @code{*unspecified*}
+constant) alone from @var{proc} means that the procedure cannot parse
+the character sequence.  Despite of this, in some cases you may want to
+read and return an unspecified value as the correct value.  This can be
+achieved by returning of two values: an unspecified value as the first
+value and @code{#t} as the second, see (@pxref{Multiple Values}).
+
 Passing @code{#f} for @var{proc} will remove a previous setting. 
 
 @end deffn
diff --git a/libguile/read.c b/libguile/read.c
index ecf27ff..e9bb6f0 100644
--- a/libguile/read.c
+++ b/libguile/read.c
@@ -1656,8 +1656,15 @@ scm_read_sharp (scm_t_wchar chr, SCM port, scm_t_read_opts *opts,
   chr = scm_getc_unlocked (port);
 
   result = scm_read_sharp_extension (chr, port, opts);
-  if (!scm_is_eq (result, SCM_UNSPECIFIED))
-    return result;
+  if (! SCM_VALUESP (result))
+    {
+      if (! scm_is_eq (result, SCM_UNSPECIFIED))
+        return result;
+    }
+  else if (scm_is_true (scm_c_value_ref (result, 1)))
+    {
+      return result;
+    }
 
   switch (chr)
     {
@@ -1713,7 +1720,7 @@ scm_read_sharp (scm_t_wchar chr, SCM port, scm_t_read_opts *opts,
       return (scm_read_nil (chr, port, opts));
     default:
       result = scm_read_sharp_extension (chr, port, opts);
-      if (scm_is_eq (result, SCM_UNSPECIFIED))
+      if ((! SCM_VALUESP (result)) && scm_is_eq (result, SCM_UNSPECIFIED))
 	{
 	  /* To remain compatible with 1.8 and earlier, the following
 	     characters have lower precedence than `read-hash-extend'
@@ -1728,7 +1735,7 @@ scm_read_sharp (scm_t_wchar chr, SCM port, scm_t_read_opts *opts,
 	    }
 	}
       else
-	return result;
+	return scm_c_value_ref (result, 0);
     }
 
   return SCM_UNSPECIFIED;
@@ -1807,11 +1814,11 @@ read_inner_expression (SCM port, scm_t_read_opts *opts)
             long line  = SCM_LINUM (port);
             int column = SCM_COL (port) - 1;
 	    SCM result = scm_read_sharp (chr, port, opts, line, column);
-	    if (scm_is_eq (result, SCM_UNSPECIFIED))
+	    if ((! SCM_VALUESP (result)) && scm_is_eq (result, SCM_UNSPECIFIED))
 	      /* We read a comment or some such.  */
 	      break;
 	    else
-	      return result;
+	      return scm_c_value_ref (result, 0);
 	  }
 	case ')':
 	  scm_i_input_error (FUNC_NAME, port, "unexpected \")\"", SCM_EOL);
diff --git a/test-suite/tests/reader.test b/test-suite/tests/reader.test
index 5eb368d..b860abe 100644
--- a/test-suite/tests/reader.test
+++ b/test-suite/tests/reader.test
@@ -169,6 +169,17 @@
   (pass-if "square brackets are parens"
     (equal? '() (read-string "[]")))
 
+  (pass-if "reader callback can read an unspecified value"
+    (with-fluids ((%read-hash-procedures (fluid-ref %read-hash-procedures)))
+      (read-hash-extend #\< (lambda (c port) (values *unspecified* #t)))
+      (eq? *unspecified* (read-string (object->string *unspecified*)))))
+
+  (pass-if-exception "reader callback can indicate an unknown object"
+      exception:unknown-sharp-object
+    (with-fluids ((%read-hash-procedures (fluid-ref %read-hash-procedures)))
+      (read-hash-extend #\< (lambda (c port) *unspecified*))
+      (eq? *unspecified* (read-string (object->string *unspecified*)))))
+
   (pass-if-exception "paren mismatch" exception:unexpected-rparen
                      (read-string "'[)"))
 
-- 
2.4.6