Do not escape a unicode sequence when escaping JSON text.

Previously, any backslash in text being escaped for JSON was doubled so
that the result was still valid JSON. However, this led to some perverse
results in the case of Unicode sequences, These are now detected and the
initial backslash is no longer escaped. All other backslashes are
still escaped. No validity check is performed, all that is looked for is
\uXXXX where X is a hexidecimal digit.

This is a change from the 9.2 and 9.3 behaviour as noted in the Release
notes.

Per complaint from Teodor Sigaev.

diff --git a/doc/src/sgml/release-9.4.sgml b/doc/src/sgml/release-9.4.sgml
index 08307c8f667c72f1bce7afd716ceeb830d697f7e..3f30c636ba2f091bcd4c8a4535cf70a2f9645505 100644 (file)
--- a/doc/src/sgml/release-9.4.sgml
+++ b/doc/src/sgml/release-9.4.sgml
@@ -180,6 +180,21 @@
      </para>
     </listitem>
 
+    <listitem>
+     <para>
+      Unicode escapes in <link linkend="datatype-json"><type>JSON</type></link>
+      text values are no longer rendered with the backslash escaped.
+      (Andrew Dunstan)
+     </para>
+
+     <para>
+      Previously all backslashes in text values being formed into JSON were
+      escaped. Now a backslash followed by "u" and four hexadecimal digits is
+      not escaped, as this is a legal sequence in a JSON string value, and
+      escaping the backslash led to some perverse results.
+     </para>
+    </listitem>
+
     <listitem>
      <para>
       Rename <link linkend="SQL-EXPLAIN"><command>EXPLAIN

diff --git a/src/backend/utils/adt/json.c b/src/backend/utils/adt/json.c
index 2462111ecb3050cd0836677dda85e24fbd747860..8ca1ede83fb355aefcfa472fcd181168fcfa3a0a 100644 (file)
--- a/src/backend/utils/adt/json.c
+++ b/src/backend/utils/adt/json.c
@@ -2315,7 +2315,26 @@ escape_json(StringInfo buf, const char *str)
                                appendStringInfoString(buf, "\\\"");
                                break;
                        case '\\':
-                               appendStringInfoString(buf, "\\\\");
+                               /*
+                                * Unicode escapes are passed through as is. There is no
+                                * requirement that they denote a valid character in the
+                                * server encoding - indeed that is a big part of their
+                                * usefulness.
+                                *
+                                * All we require is that they consist of \uXXXX where
+                                * the Xs are hexadecimal digits. It is the responsibility
+                                * of the caller of, say, to_json() to make sure that the
+                                * unicode escape is valid.
+                                *
+                                * In the case of a jsonb string value being escaped, the
+                                * only unicode escape that should be present is \u0000,
+                                * all the other unicode escapes will have been resolved.
+                                */
+                               if (p[1] == 'u' && isxdigit(p[2]) && isxdigit(p[3])
+                                       && isxdigit(p[4]) && isxdigit(p[5]))
+                                       appendStringInfoCharMacro(buf, *p);
+                               else
+                                       appendStringInfoString(buf, "\\\\");
                                break;
                        default:
                                if ((unsigned char) *p < ' ')

diff --git a/src/test/regress/expected/json.out b/src/test/regress/expected/json.out
index c4dc8b0e3cb73f07ece801a7e8893ddf3b730b76..43341aa9bb5b62f5f20821c80acdce91f4cc2970 100644 (file)
--- a/src/test/regress/expected/json.out
+++ b/src/test/regress/expected/json.out
@@ -426,6 +426,20 @@ select to_json(timestamptz '2014-05-28 12:22:35.614298-04');
 (1 row)
 
 COMMIT;
+-- unicode escape - backslash is not escaped
+select to_json(text '\uabcd');
+ to_json  
+----------
+ "\uabcd"
+(1 row)
+
+-- any other backslash is escaped
+select to_json(text '\abcd');
+ to_json  
+----------
+ "\\abcd"
+(1 row)
+
 --json_agg
 SELECT json_agg(q)
   FROM ( SELECT $$a$$ || x AS b, y AS c,

diff --git a/src/test/regress/expected/json_1.out b/src/test/regress/expected/json_1.out
index 629e98e6c5f26952af1d01f2259ba7a2c160b473..953324637d8736f6a8a98fad148b40c6062bd44b 100644 (file)
--- a/src/test/regress/expected/json_1.out
+++ b/src/test/regress/expected/json_1.out
@@ -426,6 +426,20 @@ select to_json(timestamptz '2014-05-28 12:22:35.614298-04');
 (1 row)
 
 COMMIT;
+-- unicode escape - backslash is not escaped
+select to_json(text '\uabcd');
+ to_json  
+----------
+ "\uabcd"
+(1 row)
+
+-- any other backslash is escaped
+select to_json(text '\abcd');
+ to_json  
+----------
+ "\\abcd"
+(1 row)
+
 --json_agg
 SELECT json_agg(q)
   FROM ( SELECT $$a$$ || x AS b, y AS c,

diff --git a/src/test/regress/expected/jsonb.out b/src/test/regress/expected/jsonb.out
index ae7c5068119e7054b5febe7b75ac3992dd244019..1e46939b6fe9c28a169d0a234c33ada46fdb8ccc 100644 (file)
--- a/src/test/regress/expected/jsonb.out
+++ b/src/test/regress/expected/jsonb.out
@@ -61,9 +61,9 @@ LINE 1: SELECT '"\u000g"'::jsonb;
 DETAIL:  "\u" must be followed by four hexadecimal digits.
 CONTEXT:  JSON data, line 1: "\u000g...
 SELECT '"\u0000"'::jsonb;              -- OK, legal escape
-   jsonb   
------------
- "\\u0000"
+  jsonb   
+----------
+ "\u0000"
 (1 row)
 
 -- use octet_length here so we don't get an odd unicode char in the

diff --git a/src/test/regress/expected/jsonb_1.out b/src/test/regress/expected/jsonb_1.out
index 38a95b43f8c17ed536819abb1745fc667a177463..955dc424dce1b42237d7549b6b079b2a49133d8d 100644 (file)
--- a/src/test/regress/expected/jsonb_1.out
+++ b/src/test/regress/expected/jsonb_1.out
@@ -61,9 +61,9 @@ LINE 1: SELECT '"\u000g"'::jsonb;
 DETAIL:  "\u" must be followed by four hexadecimal digits.
 CONTEXT:  JSON data, line 1: "\u000g...
 SELECT '"\u0000"'::jsonb;              -- OK, legal escape
-   jsonb   
------------
- "\\u0000"
+  jsonb   
+----------
+ "\u0000"
 (1 row)
 
 -- use octet_length here so we don't get an odd unicode char in the

diff --git a/src/test/regress/sql/json.sql b/src/test/regress/sql/json.sql
index 6c2faeccd30d2c64114709d659ca7454f62ffd80..3d5ed50126e83bd28defb25f0748cafc26a1ff3b 100644 (file)
--- a/src/test/regress/sql/json.sql
+++ b/src/test/regress/sql/json.sql
@@ -111,6 +111,14 @@ SET LOCAL TIME ZONE -8;
 select to_json(timestamptz '2014-05-28 12:22:35.614298-04');
 COMMIT;
 
+-- unicode escape - backslash is not escaped
+
+select to_json(text '\uabcd');
+
+-- any other backslash is escaped
+
+select to_json(text '\abcd');
+
 --json_agg
 
 SELECT json_agg(q)