Introduce a generic pg_dump compression API

Switch pg_dump to use the Compression API, implemented by bf9aa490db.

The CompressFileHandle replaces the cfp* family of functions with a
struct of callbacks for accessing (compressed) files. This allows adding
new compression methods simply by introducing a new struct instance with
appropriate implementation of the callbacks.

Archives compressed using custom compression methods store an identifier
of the compression algorithm in their header instead of the compression
level. The header version is bumped.

Author: Georgios Kokolatos
Reviewed-by: Michael Paquier, Rachel Heaton, Justin Pryzby, Tomas Vondra
Discussion: https://postgr.es/m/faUNEOpts9vunEaLnmxmG-DldLSg_ql137OC3JYDmgrOMHm1RvvWY2IdBkv_CRxm5spCCb_OmKNk2T03TMm0fBEWveFF9wA1WizPuAgB7Ss%3D%40protonmail.com

src/bin/pg_dump/compress_gzip.c

@@ -0,0 +1,401 @@
+/*-------------------------------------------------------------------------
+ *
+ * compress_gzip.c
+ *	 Routines for archivers to read or write a gzip compressed data stream.
+ *
+ * Portions Copyright (c) 1996-2023, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1994, Regents of the University of California
+ *
+ * IDENTIFICATION
+ *	   src/bin/pg_dump/compress_gzip.c
+ *
+ *-------------------------------------------------------------------------
+ */
+#include "postgres_fe.h"
+#include <unistd.h>
+
+#include "compress_gzip.h"
+#include "pg_backup_utils.h"
+
+#ifdef HAVE_LIBZ
+#include "zlib.h"
+
+/*----------------------
+ * Compressor API
+ *----------------------
+ */
+typedef struct GzipCompressorState
+{
+	z_streamp	zp;
+
+	void	   *outbuf;
+	size_t		outsize;
+} GzipCompressorState;
+
+/* Private routines that support gzip compressed data I/O */
+static void
+DeflateCompressorGzip(ArchiveHandle *AH, CompressorState *cs, bool flush)
+{
+	GzipCompressorState *gzipcs = (GzipCompressorState *) cs->private_data;
+	z_streamp	zp = gzipcs->zp;
+	void	   *out = gzipcs->outbuf;
+	int			res = Z_OK;
+
+	while (gzipcs->zp->avail_in != 0 || flush)
+	{
+		res = deflate(zp, flush ? Z_FINISH : Z_NO_FLUSH);
+		if (res == Z_STREAM_ERROR)
+			pg_fatal("could not compress data: %s", zp->msg);
+		if ((flush && (zp->avail_out < gzipcs->outsize))
+			|| (zp->avail_out == 0)
+			|| (zp->avail_in != 0)
+			)
+		{
+			/*
+			 * Extra paranoia: avoid zero-length chunks, since a zero length
+			 * chunk is the EOF marker in the custom format. This should never
+			 * happen but ...
+			 */
+			if (zp->avail_out < gzipcs->outsize)
+			{
+				/*
+				 * Any write function should do its own error checking but to
+				 * make sure we do a check here as well ...
+				 */
+				size_t		len = gzipcs->outsize - zp->avail_out;
+
+				cs->writeF(AH, (char *) out, len);
+			}
+			zp->next_out = out;
+			zp->avail_out = gzipcs->outsize;
+		}
+
+		if (res == Z_STREAM_END)
+			break;
+	}
+}
+
+static void
+EndCompressorGzip(ArchiveHandle *AH, CompressorState *cs)
+{
+	GzipCompressorState *gzipcs = (GzipCompressorState *) cs->private_data;
+	z_streamp	zp;
+
+	if (gzipcs->zp)
+	{
+		zp = gzipcs->zp;
+		zp->next_in = NULL;
+		zp->avail_in = 0;
+
+		/* Flush any remaining data from zlib buffer */
+		DeflateCompressorGzip(AH, cs, true);
+
+		if (deflateEnd(zp) != Z_OK)
+			pg_fatal("could not close compression stream: %s", zp->msg);
+
+		pg_free(gzipcs->outbuf);
+		pg_free(gzipcs->zp);
+	}
+
+	pg_free(gzipcs);
+	cs->private_data = NULL;
+}
+
+static void
+WriteDataToArchiveGzip(ArchiveHandle *AH, CompressorState *cs,
+					   const void *data, size_t dLen)
+{
+	GzipCompressorState *gzipcs = (GzipCompressorState *) cs->private_data;
+	z_streamp	zp;
+
+	if (!gzipcs->zp)
+	{
+		zp = gzipcs->zp = (z_streamp) pg_malloc(sizeof(z_stream));
+		zp->zalloc = Z_NULL;
+		zp->zfree = Z_NULL;
+		zp->opaque = Z_NULL;
+
+		/*
+		 * outsize is the buffer size we tell zlib it can output to.  We
+		 * actually allocate one extra byte because some routines want to
+		 * append a trailing zero byte to the zlib output.
+		 */
+		gzipcs->outbuf = pg_malloc(ZLIB_OUT_SIZE + 1);
+		gzipcs->outsize = ZLIB_OUT_SIZE;
+
+		/*
+		 * A level of zero simply copies the input one block at the time. This
+		 * is probably not what the user wanted when calling this interface.
+		 */
+		if (cs->compression_spec.level == 0)
+			pg_fatal("requested to compress the archive yet no level was specified");
+
+		if (deflateInit(zp, cs->compression_spec.level) != Z_OK)
+			pg_fatal("could not initialize compression library: %s", zp->msg);
+
+		/* Just be paranoid - maybe End is called after Start, with no Write */
+		zp->next_out = gzipcs->outbuf;
+		zp->avail_out = gzipcs->outsize;
+	}
+
+	gzipcs->zp->next_in = (void *) unconstify(void *, data);
+	gzipcs->zp->avail_in = dLen;
+	DeflateCompressorGzip(AH, cs, false);
+}
+
+static void
+ReadDataFromArchiveGzip(ArchiveHandle *AH, CompressorState *cs)
+{
+	z_streamp	zp;
+	char	   *out;
+	int			res = Z_OK;
+	size_t		cnt;
+	char	   *buf;
+	size_t		buflen;
+
+	zp = (z_streamp) pg_malloc(sizeof(z_stream));
+	zp->zalloc = Z_NULL;
+	zp->zfree = Z_NULL;
+	zp->opaque = Z_NULL;
+
+	buf = pg_malloc(ZLIB_IN_SIZE);
+	buflen = ZLIB_IN_SIZE;
+
+	out = pg_malloc(ZLIB_OUT_SIZE + 1);
+
+	if (inflateInit(zp) != Z_OK)
+		pg_fatal("could not initialize compression library: %s",
+				 zp->msg);
+
+	/* no minimal chunk size for zlib */
+	while ((cnt = cs->readF(AH, &buf, &buflen)))
+	{
+		zp->next_in = (void *) buf;
+		zp->avail_in = cnt;
+
+		while (zp->avail_in > 0)
+		{
+			zp->next_out = (void *) out;
+			zp->avail_out = ZLIB_OUT_SIZE;
+
+			res = inflate(zp, 0);
+			if (res != Z_OK && res != Z_STREAM_END)
+				pg_fatal("could not uncompress data: %s", zp->msg);
+
+			out[ZLIB_OUT_SIZE - zp->avail_out] = '\0';
+			ahwrite(out, 1, ZLIB_OUT_SIZE - zp->avail_out, AH);
+		}
+	}
+
+	zp->next_in = NULL;
+	zp->avail_in = 0;
+	while (res != Z_STREAM_END)
+	{
+		zp->next_out = (void *) out;
+		zp->avail_out = ZLIB_OUT_SIZE;
+		res = inflate(zp, 0);
+		if (res != Z_OK && res != Z_STREAM_END)
+			pg_fatal("could not uncompress data: %s", zp->msg);
+
+		out[ZLIB_OUT_SIZE - zp->avail_out] = '\0';
+		ahwrite(out, 1, ZLIB_OUT_SIZE - zp->avail_out, AH);
+	}
+
+	if (inflateEnd(zp) != Z_OK)
+		pg_fatal("could not close compression library: %s", zp->msg);
+
+	free(buf);
+	free(out);
+	free(zp);
+}
+
+/* Public routines that support gzip compressed data I/O */
+void
+InitCompressorGzip(CompressorState *cs,
+				   const pg_compress_specification compression_spec)
+{
+	GzipCompressorState *gzipcs;
+
+	cs->readData = ReadDataFromArchiveGzip;
+	cs->writeData = WriteDataToArchiveGzip;
+	cs->end = EndCompressorGzip;
+
+	cs->compression_spec = compression_spec;
+
+	gzipcs = (GzipCompressorState *) pg_malloc0(sizeof(GzipCompressorState));
+
+	cs->private_data = gzipcs;
+}
+
+
+/*----------------------
+ * Compress File API
+ *----------------------
+ */
+
+static size_t
+Gzip_read(void *ptr, size_t size, CompressFileHandle *CFH)
+{
+	gzFile		gzfp = (gzFile) CFH->private_data;
+	size_t		ret;
+
+	ret = gzread(gzfp, ptr, size);
+	if (ret != size && !gzeof(gzfp))
+	{
+		int			errnum;
+		const char *errmsg = gzerror(gzfp, &errnum);
+
+		pg_fatal("could not read from input file: %s",
+				 errnum == Z_ERRNO ? strerror(errno) : errmsg);
+	}
+
+	return ret;
+}
+
+static size_t
+Gzip_write(const void *ptr, size_t size, CompressFileHandle *CFH)
+{
+	gzFile		gzfp = (gzFile) CFH->private_data;
+
+	return gzwrite(gzfp, ptr, size);
+}
+
+static int
+Gzip_getc(CompressFileHandle *CFH)
+{
+	gzFile		gzfp = (gzFile) CFH->private_data;
+	int			ret;
+
+	errno = 0;
+	ret = gzgetc(gzfp);
+	if (ret == EOF)
+	{
+		if (!gzeof(gzfp))
+			pg_fatal("could not read from input file: %s", strerror(errno));
+		else
+			pg_fatal("could not read from input file: end of file");
+	}
+
+	return ret;
+}
+
+static char *
+Gzip_gets(char *ptr, int size, CompressFileHandle *CFH)
+{
+	gzFile		gzfp = (gzFile) CFH->private_data;
+
+	return gzgets(gzfp, ptr, size);
+}
+
+static int
+Gzip_close(CompressFileHandle *CFH)
+{
+	gzFile		gzfp = (gzFile) CFH->private_data;
+
+	CFH->private_data = NULL;
+
+	return gzclose(gzfp);
+}
+
+static int
+Gzip_eof(CompressFileHandle *CFH)
+{
+	gzFile		gzfp = (gzFile) CFH->private_data;
+
+	return gzeof(gzfp);
+}
+
+static const char *
+Gzip_get_error(CompressFileHandle *CFH)
+{
+	gzFile		gzfp = (gzFile) CFH->private_data;
+	const char *errmsg;
+	int			errnum;
+
+	errmsg = gzerror(gzfp, &errnum);
+	if (errnum == Z_ERRNO)
+		errmsg = strerror(errno);
+
+	return errmsg;
+}
+
+static int
+Gzip_open(const char *path, int fd, const char *mode, CompressFileHandle *CFH)
+{
+	gzFile		gzfp;
+	char		mode_compression[32];
+
+	if (CFH->compression_spec.level != Z_DEFAULT_COMPRESSION)
+	{
+		/*
+		 * user has specified a compression level, so tell zlib to use it
+		 */
+		snprintf(mode_compression, sizeof(mode_compression), "%s%d",
+				 mode, CFH->compression_spec.level);
+	}
+	else
+		strcpy(mode_compression, mode);
+
+	if (fd >= 0)
+		gzfp = gzdopen(dup(fd), mode_compression);
+	else
+		gzfp = gzopen(path, mode_compression);
+
+	if (gzfp == NULL)
+		return 1;
+
+	CFH->private_data = gzfp;
+
+	return 0;
+}
+
+static int
+Gzip_open_write(const char *path, const char *mode, CompressFileHandle *CFH)
+{
+	char	   *fname;
+	int			ret;
+	int			save_errno;
+
+	fname = psprintf("%s.gz", path);
+	ret = CFH->open_func(fname, -1, mode, CFH);
+
+	save_errno = errno;
+	pg_free(fname);
+	errno = save_errno;
+
+	return ret;
+}
+
+void
+InitCompressFileHandleGzip(CompressFileHandle *CFH,
+						   const pg_compress_specification compression_spec)
+{
+	CFH->open_func = Gzip_open;
+	CFH->open_write_func = Gzip_open_write;
+	CFH->read_func = Gzip_read;
+	CFH->write_func = Gzip_write;
+	CFH->gets_func = Gzip_gets;
+	CFH->getc_func = Gzip_getc;
+	CFH->close_func = Gzip_close;
+	CFH->eof_func = Gzip_eof;
+	CFH->get_error_func = Gzip_get_error;
+
+	CFH->compression_spec = compression_spec;
+
+	CFH->private_data = NULL;
+}
+#else							/* HAVE_LIBZ */
+void
+InitCompressorGzip(CompressorState *cs,
+				   const pg_compress_specification compression_spec)
+{
+	pg_fatal("this build does not support compression with %s", "gzip");
+}
+
+void
+InitCompressFileHandleGzip(CompressFileHandle *CFH,
+						   const pg_compress_specification compression_spec)
+{
+	pg_fatal("this build does not support compression with %s", "gzip");
+}
+#endif							/* HAVE_LIBZ */