0004-pg_waldump-Use-astreamer_libarchive.c.patch

From 7769392066efcd9c00a5c2be722eb91af10787a4 Mon Sep 17 00:00:00 2001
From: Thomas Munro <thomas.munro@gmail.com>
Date: Sun, 5 Apr 2026 02:40:56 +1200
Subject: [PATCH 4/4] pg_waldump: Use astreamer_libarchive.c.

If this build supports libarchive, use astreamer_libarchive_reader
instead of astreamer_tar_parser to read WAL archives.  This allows
modern tar formats with more types of compression to be used.

(Proof-of-concept)
---
 src/bin/pg_waldump/Makefile          |  5 +++++
 src/bin/pg_waldump/archive_waldump.c | 31 +++++++++++++++++++++++++++-
 src/bin/pg_waldump/meson.build       |  2 +-
 src/bin/pg_waldump/t/001_basic.pl    |  9 +++++++-
 4 files changed, 44 insertions(+), 3 deletions(-)

diff --git a/src/bin/pg_waldump/Makefile b/src/bin/pg_waldump/Makefile
index aabb87566a2..09005bf4ba4 100644
--- a/src/bin/pg_waldump/Makefile
+++ b/src/bin/pg_waldump/Makefile
@@ -23,6 +23,11 @@ OBJS = \
 override CPPFLAGS := -DFRONTEND -I$(libpq_srcdir) $(CPPFLAGS)
 LDFLAGS_INTERNAL += -L$(top_builddir)/src/fe_utils -lpgfeutils
 
+ifeq ($(with_libarchive), yes)
+# XXX figure out where this should go
+LDFLAGS_INTERNAL += $(LIBARCHIVE_LIBS)
+endif
+
 RMGRDESCSOURCES = $(sort $(notdir $(wildcard $(top_srcdir)/src/backend/access/rmgrdesc/*desc*.c)))
 RMGRDESCOBJS = $(patsubst %.c,%.o,$(RMGRDESCSOURCES))
 
diff --git a/src/bin/pg_waldump/archive_waldump.c b/src/bin/pg_waldump/archive_waldump.c
index e4a4bf44a7e..938a253ecab 100644
--- a/src/bin/pg_waldump/archive_waldump.c
+++ b/src/bin/pg_waldump/archive_waldump.c
@@ -129,12 +129,30 @@ void
 init_archive_reader(XLogDumpPrivate *privateInfo,
 					pg_compress_algorithm compression)
 {
-	int			fd;
 	astreamer  *streamer;
 	ArchivedWALFile *entry = NULL;
 	XLogLongPageHeader longhdr;
 	ArchivedWAL_iterator iter;
 
+#ifdef USE_LIBARCHIVE
+	char	   *pathname = NULL;
+
+	/* Open tar archive with libarchive. */
+	streamer = astreamer_waldump_new(privateInfo);
+	if (privateInfo->archive_dir)
+		pathname = psprintf("%s/%s",
+							privateInfo->archive_dir,
+							privateInfo->archive_name);
+	streamer =
+		astreamer_libarchive_reader_new_pathname(streamer,
+												 pathname ?
+												 pathname :
+												 privateInfo->archive_name);
+	if (pathname)
+		pfree(pathname);
+#else
+	int			fd;
+
 	/* Open tar archive and store its file descriptor */
 	fd = open_file_in_directory(privateInfo->archive_dir,
 								privateInfo->archive_name);
@@ -157,6 +175,7 @@ init_archive_reader(XLogDumpPrivate *privateInfo,
 		streamer = astreamer_lz4_decompressor_new(streamer);
 	else if (compression == PG_COMPRESSION_ZSTD)
 		streamer = astreamer_zstd_decompressor_new(streamer);
+#endif
 
 	privateInfo->archive_streamer = streamer;
 
@@ -286,10 +305,12 @@ free_archive_reader(XLogDumpPrivate *privateInfo)
 		privateInfo->archive_read_buf = NULL;
 	}
 
+#ifndef USE_LIBARCHIVE
 	/* Close the file. */
 	if (close(privateInfo->archive_fd) != 0)
 		pg_log_error("could not close file \"%s\": %m",
 					 privateInfo->archive_name);
+#endif
 }
 
 /*
@@ -537,12 +558,19 @@ get_archive_wal_entry(const char *fname, XLogDumpPrivate *privateInfo)
 static bool
 read_archive_file(XLogDumpPrivate *privateInfo)
 {
+#ifndef USE_LIBARCHIVE
 	int			rc;
+#endif
 
 	/* Fail if we already reached EOF in a prior call. */
 	if (privateInfo->archive_fd_eof)
 		return false;
 
+#ifdef USE_LIBARCHIVE
+	/* Tell libarchive to read more data. */
+	astreamer_pull(privateInfo->archive_streamer);
+#else
+
 	/* Try to read some more data. */
 	rc = read(privateInfo->archive_fd, privateInfo->archive_read_buf,
 			  privateInfo->archive_read_buf_size);
@@ -569,6 +597,7 @@ read_archive_file(XLogDumpPrivate *privateInfo)
 		/* Set flag to ensure we don't finalize more than once. */
 		privateInfo->archive_fd_eof = true;
 	}
+#endif
 
 	return true;
 }
diff --git a/src/bin/pg_waldump/meson.build b/src/bin/pg_waldump/meson.build
index 5296f21b82c..0b2c4021107 100644
--- a/src/bin/pg_waldump/meson.build
+++ b/src/bin/pg_waldump/meson.build
@@ -19,7 +19,7 @@ endif
 
 pg_waldump = executable('pg_waldump',
   pg_waldump_sources,
-  dependencies: [frontend_code, libpq, lz4, zstd],
+  dependencies: [frontend_code, libarchive, libpq, lz4, zstd],
   c_args: ['-DFRONTEND'], # needed for xlogreader et al
   kwargs: default_bin_args,
 )
diff --git a/src/bin/pg_waldump/t/001_basic.pl b/src/bin/pg_waldump/t/001_basic.pl
index 7dd1c3dd63e..62a15228b38 100644
--- a/src/bin/pg_waldump/t/001_basic.pl
+++ b/src/bin/pg_waldump/t/001_basic.pl
@@ -11,7 +11,13 @@ use Test::More;
 use List::Util qw(shuffle);
 
 my $tar = $ENV{TAR};
-my @tar_p_flags = tar_portability_options($tar);
+my @tar_p_flags;
+
+# If we don't have libarchive, then we tell tar to stick to ustar format that
+# astreamer_tar.c can decode.  Otherwise we should be able to accept anything
+# that any current tar produces.
+@tar_p_flags = tar_portability_options($tar)
+  if !check_pg_config("#define USE_LIBARCHIVE");
 
 program_help_ok('pg_waldump');
 program_version_ok('pg_waldump');
@@ -373,6 +379,7 @@ my @scenarios = (
 		'compression_flags' => '-czf',
 		'is_archive' => 1,
 		'enabled' => check_pg_config("#define HAVE_LIBZ 1")
+		  || check_pg_config("#define USE_LIBARCHIVE")
 	});
 
 for my $scenario (@scenarios)
-- 
2.53.0