Reject a copy EOF marker that has data ahead of it on the same line.

tglsfdc · tglsfdc · commit da8a4c166647 · 2024-10-01T16:53:54.000-04:00
We have always documented that a copy EOF marker (\.) must appear by itself on a line, and that is how psql interprets the rule. However, the backend's actual COPY FROM logic only insists that there not be data between the \. and the following newline. Any data ahead of the \. is parsed as a final line of input. It's hard to interpret this as anything but an ancient mistake that we've faithfully carried forward. Continuing to allow it is not cost-free, since it could mask client-side bugs that unnecessarily backslash-escape periods (and thereby risk accidentally creating an EOF marker). So, let's remove that provision and throw error if the EOF marker isn't alone on its line, matching what the documentation has said right along. Adjust the relevant error messages to be clearer, too. Discussion: https://postgr.es/m/ed659f37-a9dd-42a7-82b9-0da562cc4006@manitou-mail.org
diff --git a/src/backend/commands/copyfromparse.c b/src/backend/commands/copyfromparse.c
@@ -1403,7 +1403,7 @@ CopyReadLineText(CopyFromState cstate)
 					else if (c2 != '\r')
 						ereport(ERROR,
 								(errcode(ERRCODE_BAD_COPY_FILE_FORMAT),
-								 errmsg("end-of-copy marker corrupt")));
+								 errmsg("end-of-copy marker is not alone on its line")));
 				}
 
 				/* Get the next character */
@@ -1414,25 +1414,27 @@ CopyReadLineText(CopyFromState cstate)
 				if (c2 != '\r' && c2 != '\n')
 					ereport(ERROR,
 							(errcode(ERRCODE_BAD_COPY_FILE_FORMAT),
-							 errmsg("end-of-copy marker corrupt")));
+							 errmsg("end-of-copy marker is not alone on its line")));
 
 				if ((cstate->eol_type == EOL_NL && c2 != '\n') ||
 					(cstate->eol_type == EOL_CRNL && c2 != '\n') ||
 					(cstate->eol_type == EOL_CR && c2 != '\r'))
-				{
 					ereport(ERROR,
 							(errcode(ERRCODE_BAD_COPY_FILE_FORMAT),
 							 errmsg("end-of-copy marker does not match previous newline style")));
-				}
 
 				/*
-				 * Transfer only the data before the \. into line_buf, then
-				 * discard the data and the \. sequence.
+				 * If there is any data on this line before the \., complain.
+				 */
+				if (cstate->line_buf.len > 0 ||
+					prev_raw_ptr > cstate->input_buf_index)
+					ereport(ERROR,
+							(errcode(ERRCODE_BAD_COPY_FILE_FORMAT),
+							 errmsg("end-of-copy marker is not alone on its line")));
+
+				/*
+				 * Discard the \. and newline, then report EOF.
 				 */
-				if (prev_raw_ptr > cstate->input_buf_index)
-					appendBinaryStringInfo(&cstate->line_buf,
-										   cstate->input_buf + cstate->input_buf_index,
-										   prev_raw_ptr - cstate->input_buf_index);
 				cstate->input_buf_index = input_buf_ptr;
 				result = true;	/* report EOF */
 				break;
diff --git a/src/test/regress/expected/copy.out b/src/test/regress/expected/copy.out
@@ -50,6 +50,19 @@ select test from copytest2 order by test collate "C";
  line2
 (3 rows)
 
+-- in text mode, \. must be alone on its line
+truncate copytest2;
+copy copytest2(test) from stdin;
+ERROR:  end-of-copy marker is not alone on its line
+CONTEXT:  COPY copytest2, line 3
+copy copytest2(test) from stdin;
+ERROR:  end-of-copy marker is not alone on its line
+CONTEXT:  COPY copytest2, line 3
+select test from copytest2;
+ test 
+------
+(0 rows)
+
 -- test header line feature
 create temp table copytest3 (
 	c1 int,
diff --git a/src/test/regress/sql/copy.sql b/src/test/regress/sql/copy.sql
@@ -50,6 +50,22 @@ truncate copytest2;
 copy copytest2(test) from :'filename' csv;
 select test from copytest2 order by test collate "C";
 
+-- in text mode, \. must be alone on its line
+truncate copytest2;
+copy copytest2(test) from stdin;
+line1
+line2
+foo\.
+line3
+\.
+copy copytest2(test) from stdin;
+line4
+line5
+\.foo
+line6
+\.
+select test from copytest2;
+
 
 -- test header line feature
 
