Feedback.txt

text/plain

Download

From b13f4cdf134eef5fbecf9ea06f9b1c99890b7c02 Mon Sep 17 00:00:00 2001
From: Nazir Bilal Yavuz <byavuz81@gmail.com>
Date: Thu, 7 Aug 2025 13:27:34 +0300
Subject: [PATCH] Feedback

---
 src/backend/commands/copyfromparse.c | 55 ++++++++++++++++++++++++++--
 1 file changed, 51 insertions(+), 4 deletions(-)

diff --git a/src/backend/commands/copyfromparse.c b/src/backend/commands/copyfromparse.c
index 5aba0fa6cb7..dae5c1f698c 100644
--- a/src/backend/commands/copyfromparse.c
+++ b/src/backend/commands/copyfromparse.c
@@ -670,8 +670,12 @@ CopyLoadInputBuf(CopyFromState cstate)
 		/* If we now have some unconverted data, try to convert it */
 		CopyConvertBuf(cstate);
 
-		/* If we now have some more input bytes ready, return them */
-		if (INPUT_BUF_BYTES(cstate) > nbytes)
+		/*
+		 * If we now have at least sizeof(Vector8) input bytes ready, return
+		 * them. This is beneficial for SIMD processing in the
+		 * CopyReadLineText() function.
+		 */
+		if (INPUT_BUF_BYTES(cstate) > nbytes + sizeof(Vector8))
 			return;
 
 		/*
@@ -1322,7 +1326,7 @@ CopyReadLineText(CopyFromState cstate, bool is_csv)
 		 * unsafe with the old v2 COPY protocol, but we don't support that
 		 * anymore.
 		 */
-		if (input_buf_ptr >= copy_buf_len || need_data)
+		if (input_buf_ptr + sizeof(Vector8) >= copy_buf_len || need_data)
 		{
 			REFILL_LINEBUF;
 
@@ -1359,7 +1363,7 @@ CopyReadLineText(CopyFromState cstate, bool is_csv)
 		 *   vector register, as SIMD operations require processing data in
 		 *   fixed-size chunks.
 		 */
-		if (!in_quote && copy_buf_len - input_buf_ptr >= sizeof(Vector8))
+		if (copy_buf_len - input_buf_ptr >= sizeof(Vector8))
 		{
 			Vector8		chunk;
 			Vector8		match;
@@ -1395,6 +1399,7 @@ CopyReadLineText(CopyFromState cstate, bool is_csv)
 			{
 				/* No special characters found, so skip the entire chunk */
 				input_buf_ptr += sizeof(Vector8);
+				last_was_esc = false;
 				continue;
 			}
 		}
@@ -1650,6 +1655,11 @@ CopyReadAttributesText(CopyFromState cstate)
 	char	   *cur_ptr;
 	char	   *line_end_ptr;
 
+#ifndef USE_NO_SIMD
+	Vector8		bs = vector8_broadcast('\\');
+	Vector8		delim = vector8_broadcast(delimc);;
+#endif
+
 	/*
 	 * We need a special case for zero-column tables: check that the input
 	 * line is empty, and return.
@@ -1717,6 +1727,43 @@ CopyReadAttributesText(CopyFromState cstate)
 		{
 			char		c;
 
+#ifndef USE_NO_SIMD
+		if (line_end_ptr - cur_ptr >= sizeof(Vector8))
+		{
+			Vector8		chunk;
+			Vector8		match;
+			uint32		mask;
+
+			/* Load a chunk of data into a vector register */
+			vector8_load(&chunk, (const uint8 *) cur_ptr);
+
+			/* Create a mask of all special characters we need to stop at */
+			match = vector8_or(vector8_eq(chunk, bs), vector8_eq(chunk, delim));
+
+			/* Check if we found any special characters */
+			mask = vector8_highbit_mask(match);
+			if (mask != 0)
+			{
+				/*
+				 * Found a special character. Advance up to that point and let
+				 * the scalar code handle it.
+				 */
+				int advance = pg_rightmost_one_pos32(mask);
+				memcpy(output_ptr, cur_ptr, advance);
+				output_ptr += advance;
+				cur_ptr += advance;
+			}
+			else
+			{
+				/* No special characters found, so skip the entire chunk */
+				memcpy(output_ptr, cur_ptr, sizeof(Vector8));
+				output_ptr += sizeof(Vector8);
+				cur_ptr += sizeof(Vector8);
+				continue;
+			}
+		}
+#endif
+
 			end_ptr = cur_ptr;
 			if (cur_ptr >= line_end_ptr)
 				break;
-- 
2.50.1