Add header matching mode to COPY FROM

COPY FROM supports the HEADER option to silently discard the header
line from a CSV or text file.  It is possible to load by mistake a
file that matches the expected format, for example, if two text
columns have been swapped, resulting in garbage in the database.

This adds a new option value HEADER MATCH that checks the column names
in the header line against the actual column names and errors out if
they do not match.

Author: Rémi Lapeyre <remi.lapeyre@lenstra.fr>
Reviewed-by: Daniel Verite <daniel@manitou-mail.org>
Reviewed-by: Peter Eisentraut <peter.eisentraut@enterprisedb.com>
Discussion: https://www.postgresql.org/message-id/flat/CAF1-J-0PtCWMeLtswwGV2M70U26n4g33gpe1rcKQqe6wVQDrFA@mail.gmail.com

2 files changed, 109 insertions, 4 deletions

diff --git a/src/backend/commands/copy.c b/src/backend/commands/copy.c
index 7a0c897cc97..689713ea580 100644
--- a/src/backend/commands/copy.c
+++ b/src/backend/commands/copy.c
@@ -314,6 +314,64 @@ DoCopy(ParseState *pstate, const CopyStmt *stmt,
 }
 
 /*
+ * Extract a CopyHeaderChoice value from a DefElem.  This is like
+ * defGetBoolean() but also accepts the special value "match".
+ */
+static CopyHeaderChoice
+defGetCopyHeaderChoice(DefElem *def)
+{
+	/*
+	 * If no parameter given, assume "true" is meant.
+	 */
+	if (def->arg == NULL)
+		return COPY_HEADER_TRUE;
+
+	/*
+	 * Allow 0, 1, "true", "false", "on", "off", or "match".
+	 */
+	switch (nodeTag(def->arg))
+	{
+		case T_Integer:
+			switch (intVal(def->arg))
+			{
+				case 0:
+					return COPY_HEADER_FALSE;
+				case 1:
+					return COPY_HEADER_TRUE;
+				default:
+					/* otherwise, error out below */
+					break;
+			}
+			break;
+		default:
+			{
+				char	*sval = defGetString(def);
+
+				/*
+				 * The set of strings accepted here should match up with the
+				 * grammar's opt_boolean_or_string production.
+				 */
+				if (pg_strcasecmp(sval, "true") == 0)
+					return COPY_HEADER_TRUE;
+				if (pg_strcasecmp(sval, "false") == 0)
+					return COPY_HEADER_FALSE;
+				if (pg_strcasecmp(sval, "on") == 0)
+					return COPY_HEADER_TRUE;
+				if (pg_strcasecmp(sval, "off") == 0)
+					return COPY_HEADER_FALSE;
+				if (pg_strcasecmp(sval, "match") == 0)
+					return COPY_HEADER_MATCH;
+			}
+			break;
+	}
+	ereport(ERROR,
+				(errcode(ERRCODE_SYNTAX_ERROR),
+				 errmsg("%s requires a Boolean value or \"match\"",
+					def->defname)));
+	return COPY_HEADER_FALSE;	/* keep compiler quiet */
+}
+
+/*
  * Process the statement option list for COPY.
  *
  * Scan the options list (a list of DefElem) and transpose the information
@@ -394,7 +452,7 @@ ProcessCopyOptions(ParseState *pstate,
 			if (header_specified)
 				errorConflictingDefElem(defel, pstate);
 			header_specified = true;
-			opts_out->header_line = defGetBoolean(defel);
+			opts_out->header_line = defGetCopyHeaderChoice(defel);
 		}
 		else if (strcmp(defel->defname, "quote") == 0)
 		{
diff --git a/src/backend/commands/copyfromparse.c b/src/backend/commands/copyfromparse.c
index baf328b620c..58017ec53b0 100644
--- a/src/backend/commands/copyfromparse.c
+++ b/src/backend/commands/copyfromparse.c
@@ -72,6 +72,7 @@
 #include "miscadmin.h"
 #include "pgstat.h"
 #include "port/pg_bswap.h"
+#include "utils/builtins.h"
 #include "utils/memutils.h"
 #include "utils/rel.h"
 
@@ -758,12 +759,58 @@ NextCopyFromRawFields(CopyFromState cstate, char ***fields, int *nfields)
 	/* only available for text or csv input */
 	Assert(!cstate->opts.binary);
 
-	/* on input just throw the header line away */
+	/* on input check that the header line is correct if needed */
 	if (cstate->cur_lineno == 0 && cstate->opts.header_line)
 	{
+		ListCell   *cur;
+		TupleDesc	tupDesc;
+
+		tupDesc = RelationGetDescr(cstate->rel);
+
 		cstate->cur_lineno++;
-		if (CopyReadLine(cstate))
-			return false;		/* done */
+		done = CopyReadLine(cstate);
+
+		if (cstate->opts.header_line == COPY_HEADER_MATCH)
+		{
+			int			fldnum;
+
+			if (cstate->opts.csv_mode)
+				fldct = CopyReadAttributesCSV(cstate);
+			else
+				fldct = CopyReadAttributesText(cstate);
+
+			if (fldct != list_length(cstate->attnumlist))
+				ereport(ERROR,
+						(errcode(ERRCODE_BAD_COPY_FILE_FORMAT),
+						 errmsg("wrong number of fields in header line: field count is %d, expected %d",
+								fldct, list_length(cstate->attnumlist))));
+
+			fldnum = 0;
+			foreach(cur, cstate->attnumlist)
+			{
+				int			attnum = lfirst_int(cur);
+				char	   *colName = cstate->raw_fields[attnum - 1];
+				Form_pg_attribute attr = TupleDescAttr(tupDesc, attnum - 1);
+
+				fldnum++;
+
+				if (colName == NULL)
+					ereport(ERROR,
+							(errcode(ERRCODE_BAD_COPY_FILE_FORMAT),
+							 errmsg("column name mismatch in header line field %d: got null value (\"%s\"), expected \"%s\"",
+									fldnum, cstate->opts.null_print, NameStr(attr->attname))));
+
+				if (namestrcmp(&attr->attname, colName) != 0) {
+					ereport(ERROR,
+							(errcode(ERRCODE_BAD_COPY_FILE_FORMAT),
+							 errmsg("column name mismatch in header line field %d: got \"%s\", expected \"%s\"",
+									fldnum, colName, NameStr(attr->attname))));
+				}
+			}
+		}
+
+		if (done)
+			return false;
 	}
 
 	cstate->cur_lineno++;