Adjust bytea get_bit/set_bit to cope with bytea strings > 256MB.

Since the existing bit number argument can't exceed INT32_MAX, it's
not possible for these functions to manipulate bits beyond the first
256MB of a bytea value.  However, it'd be good if they could do at
least that much, and not fall over entirely for longer bytea values.
Adjust the comparisons to be done in int64 arithmetic so that works.
Also tweak the error reports to show sane values in case of overflow.

Also add some test cases to improve the miserable code coverage
of these functions.

Apply patch to back branches only; HEAD has a better solution
as of commit 26a944cf2.

Extracted from a much larger patch by Movead Li

Discussion: https://postgr.es/m/20200312115135445367128@highgo.ca

diff --git a/src/backend/utils/adt/varlena.c b/src/backend/utils/adt/varlena.c
index 87ecf58adebeb89fc25a3a240a6e6c3607f81796..6d42bca1eaf2b6ca9ad697a7dfd1a6af5be10a1b 100644 (file)
--- a/src/backend/utils/adt/varlena.c
+++ b/src/backend/utils/adt/varlena.c
@@ -3081,11 +3081,12 @@ byteaGetBit(PG_FUNCTION_ARGS)
 
        len = VARSIZE_ANY_EXHDR(v);
 
-       if (n < 0 || n >= len * 8)
+       /* Do comparison arithmetic in int64 in case len exceeds INT_MAX/8 */
+       if (n < 0 || n >= (int64) len * 8)
                ereport(ERROR,
                                (errcode(ERRCODE_ARRAY_SUBSCRIPT_ERROR),
                                 errmsg("index %d out of valid range, 0..%d",
-                                               n, len * 8 - 1)));
+                                               n, (int) Min((int64) len * 8 - 1, INT_MAX))));
 
        byteNo = n / 8;
        bitNo = n % 8;
@@ -3152,11 +3153,12 @@ byteaSetBit(PG_FUNCTION_ARGS)
 
        len = VARSIZE(res) - VARHDRSZ;
 
-       if (n < 0 || n >= len * 8)
+       /* Do comparison arithmetic in int64 in case len exceeds INT_MAX/8 */
+       if (n < 0 || n >= (int64) len * 8)
                ereport(ERROR,
                                (errcode(ERRCODE_ARRAY_SUBSCRIPT_ERROR),
                                 errmsg("index %d out of valid range, 0..%d",
-                                               n, len * 8 - 1)));
+                                               n, (int) Min((int64) len * 8 - 1, INT_MAX))));
 
        byteNo = n / 8;
        bitNo = n % 8;

diff --git a/src/test/regress/expected/strings.out b/src/test/regress/expected/strings.out
index 189bdffdca084cbf126620ebc3e9428485ff68f2..ae7b1e15e8f3f5bbedb5ac38aa563506ef473a81 100644 (file)
--- a/src/test/regress/expected/strings.out
+++ b/src/test/regress/expected/strings.out
@@ -1509,6 +1509,82 @@ SELECT sha512('The quick brown fox jumps over the lazy dog.');
  \x91ea1245f20d46ae9a037a989f54f1f790f0a47607eeb8a14d12890cea77a1bbc6c7ed9cf205e67b7f2b8fd4c7dfd3a7a8617e45f3c463d481c7e586c39ac1ed
 (1 row)
 
+--
+-- encode/decode
+--
+SELECT encode('\x1234567890abcdef00', 'hex');
+       encode       
+--------------------
+ 1234567890abcdef00
+(1 row)
+
+SELECT decode('1234567890abcdef00', 'hex');
+        decode        
+----------------------
+ \x1234567890abcdef00
+(1 row)
+
+SELECT encode(('\x' || repeat('1234567890abcdef0001', 7))::bytea, 'base64');
+                                    encode                                    
+------------------------------------------------------------------------------
+ EjRWeJCrze8AARI0VniQq83vAAESNFZ4kKvN7wABEjRWeJCrze8AARI0VniQq83vAAESNFZ4kKvN+
+ 7wABEjRWeJCrze8AAQ==
+(1 row)
+
+SELECT decode(encode(('\x' || repeat('1234567890abcdef0001', 7))::bytea,
+                     'base64'), 'base64');
+                                                                     decode                                                                     
+------------------------------------------------------------------------------------------------------------------------------------------------
+ \x1234567890abcdef00011234567890abcdef00011234567890abcdef00011234567890abcdef00011234567890abcdef00011234567890abcdef00011234567890abcdef0001
+(1 row)
+
+SELECT encode('\x1234567890abcdef00', 'escape');
+           encode            
+-----------------------------
+ \x124Vx\220\253\315\357\000
+(1 row)
+
+SELECT decode(encode('\x1234567890abcdef00', 'escape'), 'escape');
+        decode        
+----------------------
+ \x1234567890abcdef00
+(1 row)
+
+--
+-- get_bit/set_bit etc
+--
+SELECT get_bit('\x1234567890abcdef00'::bytea, 43);
+ get_bit 
+---------
+       1
+(1 row)
+
+SELECT get_bit('\x1234567890abcdef00'::bytea, 99);  -- error
+ERROR:  index 99 out of valid range, 0..71
+SELECT set_bit('\x1234567890abcdef00'::bytea, 43, 0);
+       set_bit        
+----------------------
+ \x1234567890a3cdef00
+(1 row)
+
+SELECT set_bit('\x1234567890abcdef00'::bytea, 99, 0);  -- error
+ERROR:  index 99 out of valid range, 0..71
+SELECT get_byte('\x1234567890abcdef00'::bytea, 3);
+ get_byte 
+----------
+      120
+(1 row)
+
+SELECT get_byte('\x1234567890abcdef00'::bytea, 99);  -- error
+ERROR:  index 99 out of valid range, 0..8
+SELECT set_byte('\x1234567890abcdef00'::bytea, 7, 11);
+       set_byte       
+----------------------
+ \x1234567890abcd0b00
+(1 row)
+
+SELECT set_byte('\x1234567890abcdef00'::bytea, 99, 11);  -- error
+ERROR:  index 99 out of valid range, 0..8
 --
 -- test behavior of escape_string_warning and standard_conforming_strings options
 --

diff --git a/src/test/regress/sql/strings.sql b/src/test/regress/sql/strings.sql
index f2203ef1b1d23af8b5d797f1c6dcbb82d7113c1b..9433ec1550693670f86453488b11813fb52221b5 100644 (file)
--- a/src/test/regress/sql/strings.sql
+++ b/src/test/regress/sql/strings.sql
@@ -526,6 +526,29 @@ SELECT sha384('The quick brown fox jumps over the lazy dog.');
 SELECT sha512('');
 SELECT sha512('The quick brown fox jumps over the lazy dog.');
 
+--
+-- encode/decode
+--
+SELECT encode('\x1234567890abcdef00', 'hex');
+SELECT decode('1234567890abcdef00', 'hex');
+SELECT encode(('\x' || repeat('1234567890abcdef0001', 7))::bytea, 'base64');
+SELECT decode(encode(('\x' || repeat('1234567890abcdef0001', 7))::bytea,
+                     'base64'), 'base64');
+SELECT encode('\x1234567890abcdef00', 'escape');
+SELECT decode(encode('\x1234567890abcdef00', 'escape'), 'escape');
+
+--
+-- get_bit/set_bit etc
+--
+SELECT get_bit('\x1234567890abcdef00'::bytea, 43);
+SELECT get_bit('\x1234567890abcdef00'::bytea, 99);  -- error
+SELECT set_bit('\x1234567890abcdef00'::bytea, 43, 0);
+SELECT set_bit('\x1234567890abcdef00'::bytea, 99, 0);  -- error
+SELECT get_byte('\x1234567890abcdef00'::bytea, 3);
+SELECT get_byte('\x1234567890abcdef00'::bytea, 99);  -- error
+SELECT set_byte('\x1234567890abcdef00'::bytea, 7, 11);
+SELECT set_byte('\x1234567890abcdef00'::bytea, 99, 11);  -- error
+
 --
 -- test behavior of escape_string_warning and standard_conforming_strings options
 --