Provide a FORCE NULL option to COPY in CSV mode.

This forces an input field containing the quoted null string to be
returned as a NULL. Without this option, only unquoted null strings
behave this way. This helps where some CSV producers insist on quoting
every field, whether or not it is needed. The option takes a list of
fields, and only applies to those columns. There is an equivalent
column-level option added to file_fdw.

Ian Barwick, with some tweaking by Andrew Dunstan, reviewed by Payal
Singh.

Author: adunstan

contrib/file_fdw/data/text.csv

@@ -1,4 +1,5 @@
-AAA,aaa
-XYZ,xyz
-NULL,NULL
-ABC,abc
+AAA,aaa,123,""
+XYZ,xyz,"",321
+NULL,NULL,NULL,NULL
+NULL,NULL,"NULL",NULL
+ABC,abc,"",""

contrib/file_fdw/file_fdw.c

@@ -48,9 +48,9 @@ struct FileFdwOption
 
 /*
  * Valid options for file_fdw.
- * These options are based on the options for COPY FROM command.
- * But note that force_not_null is handled as a boolean option attached to
- * each column, not as a table option.
+ * These options are based on the options for the COPY FROM command.
+ * But note that force_not_null and force_null are handled as boolean options
+ * attached to a column, not as table options.
  *
  * Note: If you are adding new option for user mapping, you need to modify
  * fileGetOptions(), which currently doesn't bother to look at user mappings.
@@ -69,7 +69,7 @@ static const struct FileFdwOption valid_options[] = {
 	{"null", ForeignTableRelationId},
 	{"encoding", ForeignTableRelationId},
 	{"force_not_null", AttributeRelationId},
-
+	{"force_null", AttributeRelationId},
 	/*
 	 * force_quote is not supported by file_fdw because it's for COPY TO.
 	 */
@@ -187,6 +187,7 @@ file_fdw_validator(PG_FUNCTION_ARGS)
 	Oid			catalog = PG_GETARG_OID(1);
 	char	   *filename = NULL;
 	DefElem    *force_not_null = NULL;
+	DefElem    *force_null = NULL;
 	List	   *other_options = NIL;
 	ListCell   *cell;
 
@@ -243,10 +244,10 @@ file_fdw_validator(PG_FUNCTION_ARGS)
 		}
 
 		/*
-		 * Separate out filename and force_not_null, since ProcessCopyOptions
-		 * won't accept them.  (force_not_null only comes in a boolean
-		 * per-column flavor here.)
+		 * Separate out filename and column-specific options, since
+		 * ProcessCopyOptions won't accept them.
 		 */
+
 		if (strcmp(def->defname, "filename") == 0)
 		{
 			if (filename)
@@ -255,16 +256,42 @@ file_fdw_validator(PG_FUNCTION_ARGS)
 						 errmsg("conflicting or redundant options")));
 			filename = defGetString(def);
 		}
+		/*
+		 * force_not_null is a boolean option; after validation we can discard
+		 * it - it will be retrieved later in get_file_fdw_attribute_options()
+		 */
 		else if (strcmp(def->defname, "force_not_null") == 0)
 		{
 			if (force_not_null)
 				ereport(ERROR,
 						(errcode(ERRCODE_SYNTAX_ERROR),
-						 errmsg("conflicting or redundant options")));
+						 errmsg("conflicting or redundant options"),
+						 errhint("option \"force_not_null\" supplied more than once for a column")));
+			if(force_null)
+				ereport(ERROR,
+						(errcode(ERRCODE_SYNTAX_ERROR),
+						 errmsg("conflicting or redundant options"),
+						 errhint("option \"force_not_null\" cannot be used together with \"force_null\"")));
 			force_not_null = def;
 			/* Don't care what the value is, as long as it's a legal boolean */
 			(void) defGetBoolean(def);
 		}
+		/* See comments for force_not_null above */
+		else if (strcmp(def->defname, "force_null") == 0)
+		{
+			if (force_null)
+				ereport(ERROR,
+						(errcode(ERRCODE_SYNTAX_ERROR),
+						 errmsg("conflicting or redundant options"),
+						 errhint("option \"force_null\" supplied more than once for a column")));
+			if(force_not_null)
+				ereport(ERROR,
+						(errcode(ERRCODE_SYNTAX_ERROR),
+						 errmsg("conflicting or redundant options"),
+						 errhint("option \"force_null\" cannot be used together with \"force_not_null\"")));
+			force_null = def;
+			(void) defGetBoolean(def);
+		}
 		else
 			other_options = lappend(other_options, def);
 	}
@@ -369,8 +396,9 @@ fileGetOptions(Oid foreigntableid,
  * Retrieve per-column generic options from pg_attribute and construct a list
  * of DefElems representing them.
  *
- * At the moment we only have "force_not_null", which should be combined into
- * a single DefElem listing all such columns, since that's what COPY expects.
+ * At the moment we only have "force_not_null", and "force_null",
+ * which should each be combined into a single DefElem listing all such
+ * columns, since that's what COPY expects.
  */
 static List *
 get_file_fdw_attribute_options(Oid relid)
@@ -380,6 +408,9 @@ get_file_fdw_attribute_options(Oid relid)
 	AttrNumber	natts;
 	AttrNumber	attnum;
 	List	   *fnncolumns = NIL;
+	List	   *fncolumns = NIL;
+
+	List *options = NIL;
 
 	rel = heap_open(relid, AccessShareLock);
 	tupleDesc = RelationGetDescr(rel);
@@ -410,17 +441,29 @@ get_file_fdw_attribute_options(Oid relid)
 					fnncolumns = lappend(fnncolumns, makeString(attname));
 				}
 			}
+			else if (strcmp(def->defname, "force_null") == 0)
+			{
+				if (defGetBoolean(def))
+				{
+					char	   *attname = pstrdup(NameStr(attr->attname));
+
+					fncolumns = lappend(fncolumns, makeString(attname));
+				}
+			}
 			/* maybe in future handle other options here */
 		}
 	}
 
 	heap_close(rel, AccessShareLock);
 
-	/* Return DefElem only when some column(s) have force_not_null */
+	/* Return DefElem only when some column(s) have force_not_null / force_null options set */
 	if (fnncolumns != NIL)
-		return list_make1(makeDefElem("force_not_null", (Node *) fnncolumns));
-	else
-		return NIL;
+		options = lappend(options, makeDefElem("force_not_null", (Node *) fnncolumns));
+
+	if (fncolumns != NIL)
+		options = lappend(options,makeDefElem("force_null", (Node *) fncolumns));
+
+	return options;
 }
 
 /*

contrib/file_fdw/input/file_fdw.source

@@ -81,11 +81,14 @@ OPTIONS (format 'csv', filename '@abs_srcdir@/data/agg.bad', header 'true', deli
 -- per-column options tests
 CREATE FOREIGN TABLE text_csv (
     word1 text OPTIONS (force_not_null 'true'),
-    word2 text OPTIONS (force_not_null 'off')
+    word2 text OPTIONS (force_not_null 'off'),
+    word3 text OPTIONS (force_null 'true'),
+    word4 text OPTIONS (force_null 'off')
 ) SERVER file_server
 OPTIONS (format 'text', filename '@abs_srcdir@/data/text.csv', null 'NULL');
 SELECT * FROM text_csv; -- ERROR
 ALTER FOREIGN TABLE text_csv OPTIONS (SET format 'csv');
+\pset null _null_
 SELECT * FROM text_csv;
 
 -- force_not_null is not allowed to be specified at any foreign object level:
@@ -94,6 +97,18 @@ ALTER SERVER file_server OPTIONS (ADD force_not_null '*'); -- ERROR
 CREATE USER MAPPING FOR public SERVER file_server OPTIONS (force_not_null '*'); -- ERROR
 CREATE FOREIGN TABLE tbl () SERVER file_server OPTIONS (force_not_null '*'); -- ERROR
 
+-- force_not_null cannot be specified together with force_null
+ALTER FOREIGN TABLE text_csv ALTER COLUMN word1 OPTIONS (force_null 'true'); --ERROR
+
+-- force_null is not allowed to be specified at any foreign object level:
+ALTER FOREIGN DATA WRAPPER file_fdw OPTIONS (ADD force_null '*'); -- ERROR
+ALTER SERVER file_server OPTIONS (ADD force_null '*'); -- ERROR
+CREATE USER MAPPING FOR public SERVER file_server OPTIONS (force_null '*'); -- ERROR
+CREATE FOREIGN TABLE tbl () SERVER file_server OPTIONS (force_null '*'); -- ERROR
+
+-- force_null cannot be specified together with force_not_null
+ALTER FOREIGN TABLE text_csv ALTER COLUMN word3 OPTIONS (force_not_null 'true'); --ERROR
+
 -- basic query tests
 SELECT * FROM agg_text WHERE b > 10.0 ORDER BY a;
 SELECT * FROM agg_csv ORDER BY a;

contrib/file_fdw/output/file_fdw.source

@@ -96,20 +96,24 @@ OPTIONS (format 'csv', filename '@abs_srcdir@/data/agg.bad', header 'true', deli
 -- per-column options tests
 CREATE FOREIGN TABLE text_csv (
     word1 text OPTIONS (force_not_null 'true'),
-    word2 text OPTIONS (force_not_null 'off')
+    word2 text OPTIONS (force_not_null 'off'),
+    word3 text OPTIONS (force_null 'true'),
+    word4 text OPTIONS (force_null 'off')
 ) SERVER file_server
 OPTIONS (format 'text', filename '@abs_srcdir@/data/text.csv', null 'NULL');
 SELECT * FROM text_csv; -- ERROR
 ERROR:  COPY force not null available only in CSV mode
 ALTER FOREIGN TABLE text_csv OPTIONS (SET format 'csv');
+\pset null _null_
 SELECT * FROM text_csv;
- word1 | word2 
--------+-------
- AAA   | aaa
- XYZ   | xyz
- NULL  | 
- ABC   | abc
-(4 rows)
+ word1 | word2  | word3  | word4  
+-------+--------+--------+--------
+ AAA   | aaa    | 123    | 
+ XYZ   | xyz    |        | 321
+ NULL  | _null_ | _null_ | _null_
+ NULL  | _null_ | _null_ | _null_
+ ABC   | abc    |        | 
+(5 rows)
 
 -- force_not_null is not allowed to be specified at any foreign object level:
 ALTER FOREIGN DATA WRAPPER file_fdw OPTIONS (ADD force_not_null '*'); -- ERROR
@@ -124,6 +128,27 @@ HINT:  There are no valid options in this context.
 CREATE FOREIGN TABLE tbl () SERVER file_server OPTIONS (force_not_null '*'); -- ERROR
 ERROR:  invalid option "force_not_null"
 HINT:  Valid options in this context are: filename, format, header, delimiter, quote, escape, null, encoding
+-- force_not_null cannot be specified together with force_null
+ALTER FOREIGN TABLE text_csv ALTER COLUMN word1 OPTIONS (force_null 'true'); --ERROR
+ERROR:  conflicting or redundant options
+HINT:  option "force_null" cannot be used together with "force_not_null"
+-- force_null is not allowed to be specified at any foreign object level:
+ALTER FOREIGN DATA WRAPPER file_fdw OPTIONS (ADD force_null '*'); -- ERROR
+ERROR:  invalid option "force_null"
+HINT:  There are no valid options in this context.
+ALTER SERVER file_server OPTIONS (ADD force_null '*'); -- ERROR
+ERROR:  invalid option "force_null"
+HINT:  There are no valid options in this context.
+CREATE USER MAPPING FOR public SERVER file_server OPTIONS (force_null '*'); -- ERROR
+ERROR:  invalid option "force_null"
+HINT:  There are no valid options in this context.
+CREATE FOREIGN TABLE tbl () SERVER file_server OPTIONS (force_null '*'); -- ERROR
+ERROR:  invalid option "force_null"
+HINT:  Valid options in this context are: filename, format, header, delimiter, quote, escape, null, encoding
+-- force_null cannot be specified together with force_not_null
+ALTER FOREIGN TABLE text_csv ALTER COLUMN word3 OPTIONS (force_not_null 'true'); --ERROR
+ERROR:  conflicting or redundant options
+HINT:  option "force_not_null" cannot be used together with "force_null"
 -- basic query tests
 SELECT * FROM agg_text WHERE b > 10.0 ORDER BY a;
   a  |   b    

doc/src/sgml/file-fdw.sgml

@@ -112,11 +112,11 @@
  </variablelist>
 
  <para>
-  Note that while <command>COPY</> allows options such as OIDS and HEADER 
+  Note that while <command>COPY</> allows options such as OIDS and HEADER
   to be specified without a corresponding value, the foreign data wrapper
-  syntax requires a value to be present in all cases.  To activate 
+  syntax requires a value to be present in all cases.  To activate
   <command>COPY</> options normally supplied without a value, you can
-  instead pass the value TRUE. 
+  instead pass the value TRUE.
  </para>
 
  <para>
@@ -140,6 +140,21 @@
    </listitem>
   </varlistentry>
 
+  <varlistentry>
+   <term><literal>force_null</literal></term>
+
+   <listitem>
+    <para>
+     This is a Boolean option.  If true, it specifies that values of the
+     column which match the null string are returned as <literal>NULL</>
+     even if the value is quoted. Without this option, only unquoted
+     values matching the null string are returned as <literal>NULL</>.
+     This has the same effect  as listing the column in
+     <command>COPY</>'s <literal>FORCE_NULL</literal> option.
+    </para>
+   </listitem>
+  </varlistentry>
+
  </variablelist>
 
  <para>

doc/src/sgml/ref/copy.sgml

@@ -42,6 +42,7 @@ COPY { <replaceable class="parameter">table_name</replaceable> [ ( <replaceable
     ESCAPE '<replaceable class="parameter">escape_character</replaceable>'
     FORCE_QUOTE { ( <replaceable class="parameter">column_name</replaceable> [, ...] ) | * }
     FORCE_NOT_NULL ( <replaceable class="parameter">column_name</replaceable> [, ...] )
+    FORCE_NULL ( <replaceable class="parameter">column_name</replaceable> [, ...] )
     ENCODING '<replaceable class="parameter">encoding_name</replaceable>'
 </synopsis>
  </refsynopsisdiv>
@@ -328,6 +329,20 @@ COPY { <replaceable class="parameter">table_name</replaceable> [ ( <replaceable
     </listitem>
    </varlistentry>
 
+   <varlistentry>
+    <term><literal>FORCE_NULL</></term>
+    <listitem>
+     <para>
+      Match the specified columns' values against the null string, even
+      if it has been quoted, and if a match is found set the value to
+      <literal>NULL</>. In the default case where the null string is empty,
+      this converts a quoted empty string into NULL.
+      This option is allowed only in <command>COPY FROM</>, and only when
+      using <literal>CSV</> format.
+     </para>
+    </listitem>
+   </varlistentry>
+
    <varlistentry>
     <term><literal>ENCODING</></term>
     <listitem>
@@ -637,7 +652,9 @@ COPY <replaceable class="parameter">count</replaceable>
     string, while an empty string data value is written with double quotes
     (<literal>""</>). Reading values follows similar rules. You can
     use <literal>FORCE_NOT_NULL</> to prevent <literal>NULL</> input
-    comparisons for specific columns.
+    comparisons for specific columns. You can also use
+    <literal>FORCE_NULL</> to convert quoted null string data values to
+    <literal>NULL</>.
    </para>
 
    <para>