pg_dump: Fix incorrect parsing of object types in pg_dump --filter.

Previously, pg_dump --filter could misinterpret invalid object types
in the filter file as valid ones. For example, the invalid object type
"table-data" (likely a typo for the valid "table_data") could be
mistakenly recognized as "table", causing pg_dump to succeed
when it should have failed.

This happened because pg_dump identified keywords as sequences of
ASCII alphabetic characters, treating non-alphabetic characters
(like hyphens) as keyword boundaries. As a result, "table-data" was
parsed as "table".

To fix this, pg_dump --filter now treats keywords as strings of
non-whitespace characters, ensuring invalid types like "table-data"
are correctly rejected.

Back-patch to v17, where the --filter option was introduced.

Author: Fujii Masao <masao.fujii@gmail.com>
Reviewed-by: Xuneng Zhou <xunengzhou@gmail.com>
Reviewed-by: Srinath Reddy <srinath2133@gmail.com>
Reviewed-by: Daniel Gustafsson <daniel@yesql.se>
Discussion: https://postgr.es/m/CAHGQGwFzPKUwiV5C-NLBqz1oK1+z9K8cgrF+LcxFem-p3_Ftug@mail.gmail.com
Backpatch-through: 17

diff --git a/src/bin/pg_dump/filter.c b/src/bin/pg_dump/filter.c
index 7214d514137716a5c0146e5e9bffbb5ba38ebebe..e3cdcf4097563a1fb17703783244c9a048894921 100644 (file)
--- a/src/bin/pg_dump/filter.c
+++ b/src/bin/pg_dump/filter.c
@@ -171,9 +171,8 @@ pg_log_filter_error(FilterStateData *fstate, const char *fmt,...)
 /*
  * filter_get_keyword - read the next filter keyword from buffer
  *
- * Search for keywords (limited to ascii alphabetic characters) in
- * the passed in line buffer. Returns NULL when the buffer is empty or the first
- * char is not alpha. The char '_' is allowed, except as the first character.
+ * Search for keywords (strings of non-whitespace characters) in the passed
+ * in line buffer. Returns NULL when the buffer is empty or no keyword exists.
  * The length of the found keyword is returned in the size parameter.
  */
 static const char *
@@ -182,6 +181,9 @@ filter_get_keyword(const char **line, int *size)
        const char *ptr = *line;
        const char *result = NULL;
 
+       /* The passed buffer must not be NULL */
+       Assert(*line != NULL);
+
        /* Set returned length preemptively in case no keyword is found */
        *size = 0;
 
@@ -189,11 +191,12 @@ filter_get_keyword(const char **line, int *size)
        while (isspace((unsigned char) *ptr))
                ptr++;
 
-       if (isalpha((unsigned char) *ptr))
+       /* Grab one keyword that's the string of non-whitespace characters */
+       if (*ptr != '\0' && !isspace((unsigned char) *ptr))
        {
                result = ptr++;
 
-               while (isalpha((unsigned char) *ptr) || *ptr == '_')
+               while (*ptr != '\0' && !isspace((unsigned char) *ptr))
                        ptr++;
 
                *size = ptr - result;

diff --git a/src/bin/pg_dump/t/005_pg_dump_filterfile.pl b/src/bin/pg_dump/t/005_pg_dump_filterfile.pl
index f05e8a20e0559afa86de4eb06cef6007d485fbb2..5c69ec31c393f937da168f4fbfd4963b583b7078 100644 (file)
--- a/src/bin/pg_dump/t/005_pg_dump_filterfile.pl
+++ b/src/bin/pg_dump/t/005_pg_dump_filterfile.pl
@@ -418,10 +418,16 @@ command_fails_like(
        qr/invalid filter command/,
        "invalid syntax: incorrect filter command");
 
-# Test invalid object type
+# Test invalid object type.
+#
+# This test also verifies that keywords are correctly recognized as strings of
+# non-whitespace characters. If the parser incorrectly treats non-whitespace
+# delimiters (like hyphens) as keyword boundaries, "table-data" might be
+# misread as the valid object type "table". To catch such issues,
+# "table-data" is used here as an intentionally invalid object type.
 open $inputfile, '>', "$tempdir/inputfile.txt"
   or die "unable to open filterfile for writing";
-print $inputfile "include xxx";
+print $inputfile "exclude table-data one";
 close $inputfile;
 
 command_fails_like(
@@ -432,8 +438,8 @@ command_fails_like(
                '--filter' => "$tempdir/inputfile.txt",
                'postgres'
        ],
-       qr/unsupported filter object type: "xxx"/,
-       "invalid syntax: invalid object type specified, should be table, schema, foreign_data or data"
+       qr/unsupported filter object type: "table-data"/,
+       "invalid syntax: invalid object type specified"
 );
 
 # Test missing object identifier pattern