Support long distance matching for zstd compression

zstd compression supports a special mode for finding matched in distant
past, which may result in better compression ratio, at the expense of
using more memory (the window size is 128MB).

To enable this optional mode, use the "long" keyword when specifying the
compression method (--compress=zstd:long).

Author: Justin Pryzby
Reviewed-by: Tomas Vondra, Jacob Champion
Discussion: https://postgr.es/m/20230224191840.GD1653@telsasoft.com
Discussion: https://postgr.es/m/20220327205020.GM28503@telsasoft.com

1 files changed, 56 insertions, 1 deletions

diff --git a/src/common/compression.c b/src/common/compression.c
index 2d3e56b4d62..35a7cade645 100644
--- a/src/common/compression.c
+++ b/src/common/compression.c
@@ -12,7 +12,7 @@
  * Otherwise, a compression specification is a comma-separated list of items,
  * each having the form keyword or keyword=value.
  *
- * Currently, the only supported keywords are "level" and "workers".
+ * Currently, the supported keywords are "level", "long", and "workers".
  *
  * Portions Copyright (c) 1996-2023, PostgreSQL Global Development Group
  *
@@ -38,6 +38,8 @@
 
 static int	expect_integer_value(char *keyword, char *value,
 								 pg_compress_specification *result);
+static bool expect_boolean_value(char *keyword, char *value,
+								 pg_compress_specification *result);
 
 /*
  * Look up a compression algorithm by name. Returns true and sets *algorithm
@@ -232,6 +234,11 @@ parse_compress_specification(pg_compress_algorithm algorithm, char *specificatio
 			result->workers = expect_integer_value(keyword, value, result);
 			result->options |= PG_COMPRESSION_OPTION_WORKERS;
 		}
+		else if (strcmp(keyword, "long") == 0)
+		{
+			result->long_distance = expect_boolean_value(keyword, value, result);
+			result->options |= PG_COMPRESSION_OPTION_LONG_DISTANCE;
+		}
 		else
 			result->parse_error =
 				psprintf(_("unrecognized compression option: \"%s\""), keyword);
@@ -290,6 +297,43 @@ expect_integer_value(char *keyword, char *value, pg_compress_specification *resu
 }
 
 /*
+ * Parse 'value' as a boolean and return the result.
+ *
+ * If parsing fails, set result->parse_error to an appropriate message
+ * and return -1.  The caller must check result->parse_error to determine if
+ * the call was successful.
+ *
+ * Valid values are: yes, no, on, off, 1, 0.
+ *
+ * Inspired by ParseVariableBool().
+ */
+static bool
+expect_boolean_value(char *keyword, char *value, pg_compress_specification *result)
+{
+	if (value == NULL)
+		return true;
+
+	if (pg_strcasecmp(value, "yes") == 0)
+		return true;
+	if (pg_strcasecmp(value, "on") == 0)
+		return true;
+	if (pg_strcasecmp(value, "1") == 0)
+		return true;
+
+	if (pg_strcasecmp(value, "no") == 0)
+		return false;
+	if (pg_strcasecmp(value, "off") == 0)
+		return false;
+	if (pg_strcasecmp(value, "0") == 0)
+		return false;
+
+	result->parse_error =
+		psprintf(_("value for compression option \"%s\" must be a boolean"),
+				 keyword);
+	return false;
+}
+
+/*
  * Returns NULL if the compression specification string was syntactically
  * valid and semantically sensible.  Otherwise, returns an error message.
  *
@@ -354,6 +398,17 @@ validate_compress_specification(pg_compress_specification *spec)
 						get_compress_algorithm_name(spec->algorithm));
 	}
 
+	/*
+	 * Of the compression algorithms that we currently support, only zstd
+	 * supports long-distance mode.
+	 */
+	if ((spec->options & PG_COMPRESSION_OPTION_LONG_DISTANCE) != 0 &&
+		(spec->algorithm != PG_COMPRESSION_ZSTD))
+	{
+		return psprintf(_("compression algorithm \"%s\" does not support long-distance mode"),
+						get_compress_algorithm_name(spec->algorithm));
+	}
+
 	return NULL;
 }