Fix JSON error reporting for many cases of erroneous string values.

The majority of error exit cases in json_lex_string() failed to
set lex->token_terminator, causing problems for the error context
reporting code: it would see token_terminator less than token_start
and do something more or less nuts.  In v14 and up the end result
could be as bad as a crash in report_json_context().  Older
versions accidentally avoided that fate; but all versions produce
error context lines that are far less useful than intended,
because they'd stop at the end of the prior token instead of
continuing to where the actually-bad input is.

To fix, invent some macros that make it less notationally painful
to do the right thing.  Also add documentation about what the
function is actually required to do; and in >= v14, add an assertion
in report_json_context about token_terminator being sufficiently
far advanced.

Per report from Nikolay Shaplov.  Back-patch to all supported
versions.

Discussion: https://postgr.es/m/7332649.x5DLKWyVIX@thinkpad-pgpro

3 files changed, 57 insertions, 32 deletions

diff --git a/src/backend/utils/adt/json.c b/src/backend/utils/adt/json.c
index 26d293709aa..40d1dff39c9 100644
--- a/src/backend/utils/adt/json.c
+++ b/src/backend/utils/adt/json.c
@@ -750,6 +750,13 @@ json_lex(JsonLexContext *lex)
 
 /*
  * The next token in the input stream is known to be a string; lex it.
+ *
+ * If lex->strval isn't NULL, fill it with the decoded string.
+ * Set lex->token_terminator to the end of the decoded input, and in
+ * success cases, transfer its previous value to lex->prev_token_terminator.
+ *
+ * Note: be careful that all error cases advance lex->token_terminator
+ * to the point after the character we detected the error on.
  */
 static inline void
 json_lex_string(JsonLexContext *lex)
@@ -837,33 +844,42 @@ json_lex_string(JsonLexContext *lex)
 					if (ch >= 0xd800 && ch <= 0xdbff)
 					{
 						if (hi_surrogate != -1)
+						{
+							lex->token_terminator = s + pg_mblen(s);
 							ereport(ERROR,
 									(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
 									 errmsg("invalid input syntax for type %s",
 											"json"),
 									 errdetail("Unicode high surrogate must not follow a high surrogate."),
 									 report_json_context(lex)));
+						}
 						hi_surrogate = (ch & 0x3ff) << 10;
 						continue;
 					}
 					else if (ch >= 0xdc00 && ch <= 0xdfff)
 					{
 						if (hi_surrogate == -1)
+						{
+							lex->token_terminator = s + pg_mblen(s);
 							ereport(ERROR,
 									(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
 									 errmsg("invalid input syntax for type %s", "json"),
 									 errdetail("Unicode low surrogate must follow a high surrogate."),
 									 report_json_context(lex)));
+						}
 						ch = 0x10000 + hi_surrogate + (ch & 0x3ff);
 						hi_surrogate = -1;
 					}
 
 					if (hi_surrogate != -1)
+					{
+						lex->token_terminator = s + pg_mblen(s);
 						ereport(ERROR,
 								(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
 								 errmsg("invalid input syntax for type %s", "json"),
 								 errdetail("Unicode low surrogate must follow a high surrogate."),
 								 report_json_context(lex)));
+					}
 
 					/*
 					 * For UTF8, replace the escape sequence by the actual
@@ -875,6 +891,7 @@ json_lex_string(JsonLexContext *lex)
 					if (ch == 0)
 					{
 						/* We can't allow this, since our TEXT type doesn't */
+						lex->token_terminator = s + pg_mblen(s);
 						ereport(ERROR,
 								(errcode(ERRCODE_UNTRANSLATABLE_CHARACTER),
 								 errmsg("unsupported Unicode escape sequence"),
@@ -898,24 +915,27 @@ json_lex_string(JsonLexContext *lex)
 					}
 					else
 					{
+						lex->token_terminator = s + pg_mblen(s);
 						ereport(ERROR,
 								(errcode(ERRCODE_UNTRANSLATABLE_CHARACTER),
 								 errmsg("unsupported Unicode escape sequence"),
 								 errdetail("Unicode escape values cannot be used for code point values above 007F when the server encoding is not UTF8."),
 								 report_json_context(lex)));
 					}
-
 				}
 			}
 			else if (lex->strval != NULL)
 			{
 				if (hi_surrogate != -1)
+				{
+					lex->token_terminator = s + pg_mblen(s);
 					ereport(ERROR,
 							(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
 							 errmsg("invalid input syntax for type %s",
 									"json"),
 							 errdetail("Unicode low surrogate must follow a high surrogate."),
 							 report_json_context(lex)));
+				}
 
 				switch (*s)
 				{
@@ -968,16 +988,18 @@ json_lex_string(JsonLexContext *lex)
 								   extract_mb_char(s)),
 						 report_json_context(lex)));
 			}
-
 		}
 		else if (lex->strval != NULL)
 		{
 			if (hi_surrogate != -1)
+			{
+				lex->token_terminator = s + pg_mblen(s);
 				ereport(ERROR,
 						(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
 						 errmsg("invalid input syntax for type %s", "json"),
 						 errdetail("Unicode low surrogate must follow a high surrogate."),
 						 report_json_context(lex)));
+			}
 
 			appendStringInfoChar(lex->strval, *s);
 		}
@@ -985,11 +1007,14 @@ json_lex_string(JsonLexContext *lex)
 	}
 
 	if (hi_surrogate != -1)
+	{
+		lex->token_terminator = s + pg_mblen(s);
 		ereport(ERROR,
 				(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
 				 errmsg("invalid input syntax for type %s", "json"),
 				 errdetail("Unicode low surrogate must follow a high surrogate."),
 				 report_json_context(lex)));
+	}
 
 	/* Hooray, we found the end of the string! */
 	lex->prev_token_terminator = lex->token_terminator;
diff --git a/src/test/regress/expected/json_encoding.out b/src/test/regress/expected/json_encoding.out
index d8d34f4ff6a..3156c63c6ff 100644
--- a/src/test/regress/expected/json_encoding.out
+++ b/src/test/regress/expected/json_encoding.out
@@ -41,19 +41,19 @@ select json '{ "a":  "\ud83d\ude04\ud83d\udc36" }' -> 'a' as correct_in_utf8;
 select json '{ "a":  "\ud83d\ud83d" }' -> 'a'; -- 2 high surrogates in a row
 ERROR:  invalid input syntax for type json
 DETAIL:  Unicode high surrogate must not follow a high surrogate.
-CONTEXT:  JSON data, line 1: { "a":...
+CONTEXT:  JSON data, line 1: { "a":  "\ud83d\ud83d...
 select json '{ "a":  "\ude04\ud83d" }' -> 'a'; -- surrogates in wrong order
 ERROR:  invalid input syntax for type json
 DETAIL:  Unicode low surrogate must follow a high surrogate.
-CONTEXT:  JSON data, line 1: { "a":...
+CONTEXT:  JSON data, line 1: { "a":  "\ude04...
 select json '{ "a":  "\ud83dX" }' -> 'a'; -- orphan high surrogate
 ERROR:  invalid input syntax for type json
 DETAIL:  Unicode low surrogate must follow a high surrogate.
-CONTEXT:  JSON data, line 1: { "a":...
+CONTEXT:  JSON data, line 1: { "a":  "\ud83dX...
 select json '{ "a":  "\ude04X" }' -> 'a'; -- orphan low surrogate
 ERROR:  invalid input syntax for type json
 DETAIL:  Unicode low surrogate must follow a high surrogate.
-CONTEXT:  JSON data, line 1: { "a":...
+CONTEXT:  JSON data, line 1: { "a":  "\ude04...
 --handling of simple unicode escapes
 select json '{ "a":  "the Copyright \u00a9 sign" }' as correct_in_utf8;
             correct_in_utf8            
@@ -106,7 +106,7 @@ select json '{ "a":  "dollar \\u0024 character" }' ->> 'a' as not_an_escape;
 select json '{ "a":  "null \u0000 escape" }' ->> 'a' as fails;
 ERROR:  unsupported Unicode escape sequence
 DETAIL:  \u0000 cannot be converted to text.
-CONTEXT:  JSON data, line 1: { "a":...
+CONTEXT:  JSON data, line 1: { "a":  "null \u0000...
 select json '{ "a":  "null \\u0000 escape" }' ->> 'a' as not_an_escape;
    not_an_escape    
 --------------------
@@ -144,7 +144,7 @@ ERROR:  unsupported Unicode escape sequence
 LINE 1: SELECT '"\u0000"'::jsonb;
                ^
 DETAIL:  \u0000 cannot be converted to text.
-CONTEXT:  JSON data, line 1: ...
+CONTEXT:  JSON data, line 1: "\u0000...
 -- use octet_length here so we don't get an odd unicode char in the
 -- output
 SELECT octet_length('"\uaBcD"'::jsonb::text); -- OK, uppercase and lower case both OK
@@ -165,25 +165,25 @@ ERROR:  invalid input syntax for type json
 LINE 1: SELECT jsonb '{ "a":  "\ud83d\ud83d" }' -> 'a';
                      ^
 DETAIL:  Unicode high surrogate must not follow a high surrogate.
-CONTEXT:  JSON data, line 1: { "a":...
+CONTEXT:  JSON data, line 1: { "a":  "\ud83d\ud83d...
 SELECT jsonb '{ "a":  "\ude04\ud83d" }' -> 'a'; -- surrogates in wrong order
 ERROR:  invalid input syntax for type json
 LINE 1: SELECT jsonb '{ "a":  "\ude04\ud83d" }' -> 'a';
                      ^
 DETAIL:  Unicode low surrogate must follow a high surrogate.
-CONTEXT:  JSON data, line 1: { "a":...
+CONTEXT:  JSON data, line 1: { "a":  "\ude04...
 SELECT jsonb '{ "a":  "\ud83dX" }' -> 'a'; -- orphan high surrogate
 ERROR:  invalid input syntax for type json
 LINE 1: SELECT jsonb '{ "a":  "\ud83dX" }' -> 'a';
                      ^
 DETAIL:  Unicode low surrogate must follow a high surrogate.
-CONTEXT:  JSON data, line 1: { "a":...
+CONTEXT:  JSON data, line 1: { "a":  "\ud83dX...
 SELECT jsonb '{ "a":  "\ude04X" }' -> 'a'; -- orphan low surrogate
 ERROR:  invalid input syntax for type json
 LINE 1: SELECT jsonb '{ "a":  "\ude04X" }' -> 'a';
                      ^
 DETAIL:  Unicode low surrogate must follow a high surrogate.
-CONTEXT:  JSON data, line 1: { "a":...
+CONTEXT:  JSON data, line 1: { "a":  "\ude04...
 -- handling of simple unicode escapes
 SELECT jsonb '{ "a":  "the Copyright \u00a9 sign" }' as correct_in_utf8;
         correct_in_utf8        
@@ -208,7 +208,7 @@ ERROR:  unsupported Unicode escape sequence
 LINE 1: SELECT jsonb '{ "a":  "null \u0000 escape" }' as fails;
                      ^
 DETAIL:  \u0000 cannot be converted to text.
-CONTEXT:  JSON data, line 1: { "a":...
+CONTEXT:  JSON data, line 1: { "a":  "null \u0000...
 SELECT jsonb '{ "a":  "null \\u0000 escape" }' as not_an_escape;
         not_an_escape         
 ------------------------------
@@ -238,7 +238,7 @@ ERROR:  unsupported Unicode escape sequence
 LINE 1: SELECT jsonb '{ "a":  "null \u0000 escape" }' ->> 'a' as fai...
                      ^
 DETAIL:  \u0000 cannot be converted to text.
-CONTEXT:  JSON data, line 1: { "a":...
+CONTEXT:  JSON data, line 1: { "a":  "null \u0000...
 SELECT jsonb '{ "a":  "null \\u0000 escape" }' ->> 'a' as not_an_escape;
    not_an_escape    
 --------------------
diff --git a/src/test/regress/expected/json_encoding_1.out b/src/test/regress/expected/json_encoding_1.out
index 79ed78e1c5f..d320bfa8118 100644
--- a/src/test/regress/expected/json_encoding_1.out
+++ b/src/test/regress/expected/json_encoding_1.out
@@ -35,23 +35,23 @@ SELECT '"\uaBcD"'::json;		-- OK, uppercase and lower case both OK
 select json '{ "a":  "\ud83d\ude04\ud83d\udc36" }' -> 'a' as correct_in_utf8;
 ERROR:  unsupported Unicode escape sequence
 DETAIL:  Unicode escape values cannot be used for code point values above 007F when the server encoding is not UTF8.
-CONTEXT:  JSON data, line 1: { "a":...
+CONTEXT:  JSON data, line 1: { "a":  "\ud83d\ude04...
 select json '{ "a":  "\ud83d\ud83d" }' -> 'a'; -- 2 high surrogates in a row
 ERROR:  invalid input syntax for type json
 DETAIL:  Unicode high surrogate must not follow a high surrogate.
-CONTEXT:  JSON data, line 1: { "a":...
+CONTEXT:  JSON data, line 1: { "a":  "\ud83d\ud83d...
 select json '{ "a":  "\ude04\ud83d" }' -> 'a'; -- surrogates in wrong order
 ERROR:  invalid input syntax for type json
 DETAIL:  Unicode low surrogate must follow a high surrogate.
-CONTEXT:  JSON data, line 1: { "a":...
+CONTEXT:  JSON data, line 1: { "a":  "\ude04...
 select json '{ "a":  "\ud83dX" }' -> 'a'; -- orphan high surrogate
 ERROR:  invalid input syntax for type json
 DETAIL:  Unicode low surrogate must follow a high surrogate.
-CONTEXT:  JSON data, line 1: { "a":...
+CONTEXT:  JSON data, line 1: { "a":  "\ud83dX...
 select json '{ "a":  "\ude04X" }' -> 'a'; -- orphan low surrogate
 ERROR:  invalid input syntax for type json
 DETAIL:  Unicode low surrogate must follow a high surrogate.
-CONTEXT:  JSON data, line 1: { "a":...
+CONTEXT:  JSON data, line 1: { "a":  "\ude04...
 --handling of simple unicode escapes
 select json '{ "a":  "the Copyright \u00a9 sign" }' as correct_in_utf8;
             correct_in_utf8            
@@ -86,7 +86,7 @@ select json '{ "a":  "null \\u0000 escape" }' as not_an_escape;
 select json '{ "a":  "the Copyright \u00a9 sign" }' ->> 'a' as correct_in_utf8;
 ERROR:  unsupported Unicode escape sequence
 DETAIL:  Unicode escape values cannot be used for code point values above 007F when the server encoding is not UTF8.
-CONTEXT:  JSON data, line 1: { "a":...
+CONTEXT:  JSON data, line 1: { "a":  "the Copyright \u00a9...
 select json '{ "a":  "dollar \u0024 character" }' ->> 'a' as correct_everywhere;
  correct_everywhere 
 --------------------
@@ -102,7 +102,7 @@ select json '{ "a":  "dollar \\u0024 character" }' ->> 'a' as not_an_escape;
 select json '{ "a":  "null \u0000 escape" }' ->> 'a' as fails;
 ERROR:  unsupported Unicode escape sequence
 DETAIL:  \u0000 cannot be converted to text.
-CONTEXT:  JSON data, line 1: { "a":...
+CONTEXT:  JSON data, line 1: { "a":  "null \u0000...
 select json '{ "a":  "null \\u0000 escape" }' ->> 'a' as not_an_escape;
    not_an_escape    
 --------------------
@@ -140,7 +140,7 @@ ERROR:  unsupported Unicode escape sequence
 LINE 1: SELECT '"\u0000"'::jsonb;
                ^
 DETAIL:  \u0000 cannot be converted to text.
-CONTEXT:  JSON data, line 1: ...
+CONTEXT:  JSON data, line 1: "\u0000...
 -- use octet_length here so we don't get an odd unicode char in the
 -- output
 SELECT octet_length('"\uaBcD"'::jsonb::text); -- OK, uppercase and lower case both OK
@@ -148,45 +148,45 @@ ERROR:  unsupported Unicode escape sequence
 LINE 1: SELECT octet_length('"\uaBcD"'::jsonb::text);
                             ^
 DETAIL:  Unicode escape values cannot be used for code point values above 007F when the server encoding is not UTF8.
-CONTEXT:  JSON data, line 1: ...
+CONTEXT:  JSON data, line 1: "\uaBcD...
 -- handling of unicode surrogate pairs
 SELECT octet_length((jsonb '{ "a":  "\ud83d\ude04\ud83d\udc36" }' -> 'a')::text) AS correct_in_utf8;
 ERROR:  unsupported Unicode escape sequence
 LINE 1: SELECT octet_length((jsonb '{ "a":  "\ud83d\ude04\ud83d\udc3...
                                    ^
 DETAIL:  Unicode escape values cannot be used for code point values above 007F when the server encoding is not UTF8.
-CONTEXT:  JSON data, line 1: { "a":...
+CONTEXT:  JSON data, line 1: { "a":  "\ud83d\ude04...
 SELECT jsonb '{ "a":  "\ud83d\ud83d" }' -> 'a'; -- 2 high surrogates in a row
 ERROR:  invalid input syntax for type json
 LINE 1: SELECT jsonb '{ "a":  "\ud83d\ud83d" }' -> 'a';
                      ^
 DETAIL:  Unicode high surrogate must not follow a high surrogate.
-CONTEXT:  JSON data, line 1: { "a":...
+CONTEXT:  JSON data, line 1: { "a":  "\ud83d\ud83d...
 SELECT jsonb '{ "a":  "\ude04\ud83d" }' -> 'a'; -- surrogates in wrong order
 ERROR:  invalid input syntax for type json
 LINE 1: SELECT jsonb '{ "a":  "\ude04\ud83d" }' -> 'a';
                      ^
 DETAIL:  Unicode low surrogate must follow a high surrogate.
-CONTEXT:  JSON data, line 1: { "a":...
+CONTEXT:  JSON data, line 1: { "a":  "\ude04...
 SELECT jsonb '{ "a":  "\ud83dX" }' -> 'a'; -- orphan high surrogate
 ERROR:  invalid input syntax for type json
 LINE 1: SELECT jsonb '{ "a":  "\ud83dX" }' -> 'a';
                      ^
 DETAIL:  Unicode low surrogate must follow a high surrogate.
-CONTEXT:  JSON data, line 1: { "a":...
+CONTEXT:  JSON data, line 1: { "a":  "\ud83dX...
 SELECT jsonb '{ "a":  "\ude04X" }' -> 'a'; -- orphan low surrogate
 ERROR:  invalid input syntax for type json
 LINE 1: SELECT jsonb '{ "a":  "\ude04X" }' -> 'a';
                      ^
 DETAIL:  Unicode low surrogate must follow a high surrogate.
-CONTEXT:  JSON data, line 1: { "a":...
+CONTEXT:  JSON data, line 1: { "a":  "\ude04...
 -- handling of simple unicode escapes
 SELECT jsonb '{ "a":  "the Copyright \u00a9 sign" }' as correct_in_utf8;
 ERROR:  unsupported Unicode escape sequence
 LINE 1: SELECT jsonb '{ "a":  "the Copyright \u00a9 sign" }' as corr...
                      ^
 DETAIL:  Unicode escape values cannot be used for code point values above 007F when the server encoding is not UTF8.
-CONTEXT:  JSON data, line 1: { "a":...
+CONTEXT:  JSON data, line 1: { "a":  "the Copyright \u00a9...
 SELECT jsonb '{ "a":  "dollar \u0024 character" }' as correct_everywhere;
      correct_everywhere      
 -----------------------------
@@ -204,7 +204,7 @@ ERROR:  unsupported Unicode escape sequence
 LINE 1: SELECT jsonb '{ "a":  "null \u0000 escape" }' as fails;
                      ^
 DETAIL:  \u0000 cannot be converted to text.
-CONTEXT:  JSON data, line 1: { "a":...
+CONTEXT:  JSON data, line 1: { "a":  "null \u0000...
 SELECT jsonb '{ "a":  "null \\u0000 escape" }' as not_an_escape;
         not_an_escape         
 ------------------------------
@@ -216,7 +216,7 @@ ERROR:  unsupported Unicode escape sequence
 LINE 1: SELECT jsonb '{ "a":  "the Copyright \u00a9 sign" }' ->> 'a'...
                      ^
 DETAIL:  Unicode escape values cannot be used for code point values above 007F when the server encoding is not UTF8.
-CONTEXT:  JSON data, line 1: { "a":...
+CONTEXT:  JSON data, line 1: { "a":  "the Copyright \u00a9...
 SELECT jsonb '{ "a":  "dollar \u0024 character" }' ->> 'a' as correct_everywhere;
  correct_everywhere 
 --------------------
@@ -234,7 +234,7 @@ ERROR:  unsupported Unicode escape sequence
 LINE 1: SELECT jsonb '{ "a":  "null \u0000 escape" }' ->> 'a' as fai...
                      ^
 DETAIL:  \u0000 cannot be converted to text.
-CONTEXT:  JSON data, line 1: { "a":...
+CONTEXT:  JSON data, line 1: { "a":  "null \u0000...
 SELECT jsonb '{ "a":  "null \\u0000 escape" }' ->> 'a' as not_an_escape;
    not_an_escape    
 --------------------