Improve character name escapes

* doc/lispref/nonascii.texi (Character Properties):
Avoid duplication of Unicode names.  Reformat examples to fit in
narrow pages.
* doc/lispref/objects.texi (General Escape Syntax):
Simplify and better-organize explanation of \N{...} escapes.
* src/character.h (CHAR_SURROGATE_PAIR_P): Remove; unused.
(char_surrogate_p): New inline function.
* src/lread.c: Do not include string.h; no longer needed.
(invalid_character_name, check_scalar_value): Remove; the ideas
behind these functions are now bundled into character_name_to_code.
(character_name_to_code): Remove undocumented support for "CJK
IDEOGRAPH-XXXX" names, as "U+XXXX" suffices.  Reject monstrosities
like "\N{U+-0}" and null bytes in \N escapes.  Reject floating
point in \N escapes instead of returning garbage.  Use
AUTO_STRING_WITH_LEN to lessen pressure on the garbage collector.
* test/src/lread-tests.el (lread-char-number, lread-char-name)
(lread-string-char-number, lread-string-char-name):
Test runtime behavior, not compile-time, as the test framework
is not set up to test compile-time.
(lread-char-surrogate-1, lread-char-surrogate-2)
(lread-char-surrogate-3, lread-char-surrogate-4)
(lread-string-char-number-2, lread-string-char-number-3):
New tests.
(lread-string-char-number-1): Rename from lread-string-char-number.

1 files changed, 19 insertions, 13 deletions

diff --git a/test/src/lread-tests.el b/test/src/lread-tests.el
index ff5d0f655f3..2ebaf491120 100644
--- a/test/src/lread-tests.el
+++ b/test/src/lread-tests.el
@@ -1,6 +1,6 @@
 ;;; lread-tests.el --- tests for lread.c -*- lexical-binding: t; -*-
 
-;; Copyright (C) 2016  Google Inc.
+;; Copyright (C) 2016 Free Software Foundation, Inc.
 
 ;; Author: Philipp Stephani <phst@google.com>
 
@@ -26,11 +26,10 @@
 ;;; Code:
 
 (ert-deftest lread-char-number ()
-  (should (equal ?\N{U+A817} #xA817)))
+  (should (equal (read "?\\N{U+A817}") #xA817)))
 
 (ert-deftest lread-char-name ()
-  (should (equal ?\N{SYLOTI  NAGRI LETTER
-                 DHO}
+  (should (equal (read "?\\N{SYLOTI  NAGRI LETTER \n DHO}")
                  #xA817)))
 
 (ert-deftest lread-char-invalid-number ()
@@ -46,16 +45,23 @@
 (ert-deftest lread-char-empty-name ()
   (should-error (read "?\\N{}") :type 'invalid-read-syntax))
 
-(ert-deftest lread-char-cjk-name ()
-  (should (equal ?\N{CJK IDEOGRAPH-2B734} #x2B734)))
-
-(ert-deftest lread-char-invalid-cjk-name ()
-  (should-error (read "?\\N{CJK IDEOGRAPH-2B735}") :type 'invalid-read-syntax))
-
-(ert-deftest lread-string-char-number ()
-  (should (equal "a\N{U+A817}b" "a\uA817b")))
+(ert-deftest lread-char-surrogate-1 ()
+  (should-error (read "?\\N{U+D800}") :type 'invalid-read-syntax))
+(ert-deftest lread-char-surrogate-2 ()
+  (should-error (read "?\\N{U+D801}") :type 'invalid-read-syntax))
+(ert-deftest lread-char-surrogate-3 ()
+  (should-error (read "?\\N{U+Dffe}") :type 'invalid-read-syntax))
+(ert-deftest lread-char-surrogate-4 ()
+  (should-error (read "?\\N{U+DFFF}") :type 'invalid-read-syntax))
+
+(ert-deftest lread-string-char-number-1 ()
+  (should (equal (read "a\\N{U+A817}b") "a\uA817bx")))
+(ert-deftest lread-string-char-number-2 ()
+  (should-error (read "?\\N{0.5}") :type 'invalid-read-syntax))
+(ert-deftest lread-string-char-number-3 ()
+  (should-error (read "?\\N{U+-0}") :type 'invalid-read-syntax))
 
 (ert-deftest lread-string-char-name ()
-  (should (equal "a\N{SYLOTI NAGRI  LETTER DHO}b" "a\uA817b")))
+  (should (equal (read "a\\N{SYLOTI NAGRI  LETTER DHO}b") "a\uA817b")))
 
 ;;; lread-tests.el ends here