pg_backup_tar.c

PostgreSQL 8.1.4的源码 适用于Linux下的开源数据库系统

}

static void
_LoadBlobs(ArchiveHandle *AH, RestoreOptions *ropt)
{
	Oid			oid;
	lclContext *ctx = (lclContext *) AH->formatData;
	TAR_MEMBER *th;
	size_t		cnt;
	char		buf[4096];

	StartRestoreBlobs(AH);

	th = tarOpen(AH, NULL, 'r');	/* Open next file */
	while (th != NULL)
	{
		ctx->FH = th;

		if (strncmp(th->targetFile, "blob_", 5) == 0)
		{
			oid = atooid(&th->targetFile[5]);
			if (oid != 0)
			{
				ahlog(AH, 1, "restoring large object OID %u\n", oid);

				StartRestoreBlob(AH, oid);

				while ((cnt = tarRead(buf, 4095, th)) > 0)
				{
					buf[cnt] = '\0';
					ahwrite(buf, 1, cnt, AH);
				}
				EndRestoreBlob(AH, oid);
			}
		}

		tarClose(AH, th);

		th = tarOpen(AH, NULL, 'r');
	}
	EndRestoreBlobs(AH);
}


static int
_WriteByte(ArchiveHandle *AH, const int i)
{
	lclContext *ctx = (lclContext *) AH->formatData;
	int			res;
	char		b = i;			/* Avoid endian problems */

	res = tarWrite(&b, 1, ctx->FH);
	if (res != EOF)
		ctx->filePos += res;
	return res;
}

static int
_ReadByte(ArchiveHandle *AH)
{
	lclContext *ctx = (lclContext *) AH->formatData;
	int			res;
	char		c = '\0';

	res = tarRead(&c, 1, ctx->FH);
	if (res != EOF)
		ctx->filePos += res;
	return c;
}

static size_t
_WriteBuf(ArchiveHandle *AH, const void *buf, size_t len)
{
	lclContext *ctx = (lclContext *) AH->formatData;
	size_t		res;

	res = tarWrite((void *) buf, len, ctx->FH);
	ctx->filePos += res;
	return res;
}

static size_t
_ReadBuf(ArchiveHandle *AH, void *buf, size_t len)
{
	lclContext *ctx = (lclContext *) AH->formatData;
	size_t		res;

	res = tarRead(buf, len, ctx->FH);
	ctx->filePos += res;
	return res;
}

static void
_CloseArchive(ArchiveHandle *AH)
{
	lclContext *ctx = (lclContext *) AH->formatData;
	TAR_MEMBER *th;
	RestoreOptions *ropt;
	int			savVerbose,
				i;

	if (AH->mode == archModeWrite)
	{
		/*
		 * Write the Header & TOC to the archive FIRST
		 */
		th = tarOpen(AH, "toc.dat", 'w');
		ctx->FH = th;
		WriteHead(AH);
		WriteToc(AH);
		tarClose(AH, th);		/* Not needed any more */

		/*
		 * Now send the data (tables & blobs)
		 */
		WriteDataChunks(AH);

		/*
		 * Now this format wants to append a script which does a full restore
		 * if the files have been extracted.
		 */
		th = tarOpen(AH, "restore.sql", 'w');
		tarPrintf(AH, th, "create temporary table pgdump_restore_path(p text);\n");
		tarPrintf(AH, th, "--\n"
				  "-- NOTE:\n"
				  "--\n"
				  "-- File paths need to be edited. Search for $$PATH$$ and\n"
				  "-- replace it with the path to the directory containing\n"
				  "-- the extracted data files.\n"
				  "--\n"
				  "-- Edit the following to match the path where the\n"
				  "-- tar archive has been extracted.\n"
				  "--\n");
		tarPrintf(AH, th, "insert into pgdump_restore_path values('/tmp');\n\n");

		AH->CustomOutPtr = _scriptOut;

		ctx->isSpecialScript = 1;
		ctx->scriptTH = th;

		ropt = NewRestoreOptions();
		ropt->dropSchema = 1;
		ropt->compression = 0;
		ropt->superuser = NULL;
		ropt->suppressDumpWarnings = true;

		savVerbose = AH->public.verbose;
		AH->public.verbose = 0;

		RestoreArchive((Archive *) AH, ropt);

		AH->public.verbose = savVerbose;

		tarClose(AH, th);

		/* Add a block of NULLs since it's de-rigeur. */
		for (i = 0; i < 512; i++)
		{
			if (fputc(0, ctx->tarFH) == EOF)
				die_horribly(AH, modulename,
					   "could not write null block at end of tar archive\n");
		}
	}

	AH->FH = NULL;
}

static size_t
_scriptOut(ArchiveHandle *AH, const void *buf, size_t len)
{
	lclContext *ctx = (lclContext *) AH->formatData;

	return tarWrite(buf, len, ctx->scriptTH);
}

/*
 * BLOB support
 */

/*
 * Called by the archiver when starting to save all BLOB DATA (not schema).
 * This routine should save whatever format-specific information is needed
 * to read the BLOBs back into memory.
 *
 * It is called just prior to the dumper's DataDumper routine.
 *
 * Optional, but strongly recommended.
 *
 */
static void
_StartBlobs(ArchiveHandle *AH, TocEntry *te)
{
	lclContext *ctx = (lclContext *) AH->formatData;
	char		fname[K_STD_BUF_SIZE];

	sprintf(fname, "blobs.toc");
	ctx->blobToc = tarOpen(AH, fname, 'w');
}

/*
 * Called by the archiver when the dumper calls StartBlob.
 *
 * Mandatory.
 *
 * Must save the passed OID for retrieval at restore-time.
 */
static void
_StartBlob(ArchiveHandle *AH, TocEntry *te, Oid oid)
{
	lclContext *ctx = (lclContext *) AH->formatData;
	lclTocEntry *tctx = (lclTocEntry *) te->formatData;
	char		fname[255];
	char	   *sfx;

	if (oid == 0)
		die_horribly(AH, modulename, "invalid OID for large object (%u)\n", oid);

	if (AH->compression != 0)
		sfx = ".gz";
	else
		sfx = "";

	sprintf(fname, "blob_%u.dat%s", oid, sfx);

	tarPrintf(AH, ctx->blobToc, "%u %s\n", oid, fname);

	tctx->TH = tarOpen(AH, fname, 'w');
}

/*
 * Called by the archiver when the dumper calls EndBlob.
 *
 * Optional.
 *
 */
static void
_EndBlob(ArchiveHandle *AH, TocEntry *te, Oid oid)
{
	lclTocEntry *tctx = (lclTocEntry *) te->formatData;

	tarClose(AH, tctx->TH);
}

/*
 * Called by the archiver when finishing saving all BLOB DATA.
 *
 * Optional.
 *
 */
static void
_EndBlobs(ArchiveHandle *AH, TocEntry *te)
{
	lclContext *ctx = (lclContext *) AH->formatData;

	/* Write out a fake zero OID to mark end-of-blobs. */
	/* WriteInt(AH, 0); */

	tarClose(AH, ctx->blobToc);
}



/*------------
 * TAR Support
 *------------
 */

static int
tarPrintf(ArchiveHandle *AH, TAR_MEMBER *th, const char *fmt,...)
{
	char	   *p = NULL;
	va_list		ap;
	size_t		bSize = strlen(fmt) + 256;		/* Should be enough */
	int			cnt = -1;

	/*
	 * This is paranoid: deal with the possibility that vsnprintf is willing
	 * to ignore trailing null
	 */

	/*
	 * or returns > 0 even if string does not fit. It may be the case that it
	 * returns cnt = bufsize
	 */
	while (cnt < 0 || cnt >= (bSize - 1))
	{
		if (p != NULL)
			free(p);
		bSize *= 2;
		p = (char *) malloc(bSize);
		if (p == NULL)
			die_horribly(AH, modulename, "out of memory\n");
		va_start(ap, fmt);
		cnt = vsnprintf(p, bSize, fmt, ap);
		va_end(ap);
	}
	cnt = tarWrite(p, cnt, th);
	free(p);
	return cnt;
}

static int
_tarChecksum(char *header)
{
	int			i,
				sum;

	sum = 0;
	for (i = 0; i < 512; i++)
		if (i < 148 || i >= 156)
			sum += 0xFF & header[i];
	return sum + 256;			/* Assume 8 blanks in checksum field */
}

bool
isValidTarHeader(char *header)
{
	int			sum;
	int			chk = _tarChecksum(header);

	sscanf(&header[148], "%8o", &sum);

	if (sum != chk)
		return false;

	/* POSIX format */
	if (strncmp(&header[257], "ustar00", 7) == 0)
		return true;
	/* older format */
	if (strncmp(&header[257], "ustar  ", 7) == 0)
		return true;

	return false;
}

/* Given the member, write the TAR header & copy the file */
static void
_tarAddFile(ArchiveHandle *AH, TAR_MEMBER *th)
{
	lclContext *ctx = (lclContext *) AH->formatData;
	FILE	   *tmp = th->tmpFH;	/* Grab it for convenience */
	char		buf[32768];
	size_t		cnt;
	off_t		len = 0;
	size_t		res;
	size_t		i,
				pad;

	/*
	 * Find file len & go back to start.
	 */
	fseeko(tmp, 0, SEEK_END);
	th->fileLen = ftello(tmp);

	/*
	 * Some compilers with throw a warning knowing this test can never be true
	 * because off_t can't exceed the compared maximum.
	 */
	if (th->fileLen > MAX_TAR_MEMBER_FILELEN)
		die_horribly(AH, modulename, "archive member too large for tar format\n");
	fseeko(tmp, 0, SEEK_SET);

	_tarWriteHeader(th);

	while ((cnt = fread(&buf[0], 1, 32767, tmp)) > 0)
	{
		res = fwrite(&buf[0], 1, cnt, th->tarFH);
		if (res != cnt)
			die_horribly(AH, modulename,
						 "write error appending to tar archive (wrote %lu, attempted %lu)\n",
						 (unsigned long) res, (unsigned long) cnt);
		len += res;
	}

	if (fclose(tmp) != 0)		/* This *should* delete it... */
		die_horribly(AH, modulename, "could not close tar member: %s\n", strerror(errno));

	if (len != th->fileLen)
	{
		char		buf1[100],
					buf2[100];

		snprintf(buf1, sizeof(buf1), INT64_FORMAT, (int64) len);
		snprintf(buf2, sizeof(buf2), INT64_FORMAT, (int64) th->pos);
		die_horribly(AH, modulename, "actual file length (%s) does not match expected (%s)\n",
					 buf1, buf2);
	}

	pad = ((len + 511) & ~511) - len;
	for (i = 0; i < pad; i++)
	{
		if (fputc('\0', th->tarFH) == EOF)
			die_horribly(AH, modulename, "could not output padding at end of tar member\n");
	}

	ctx->tarFHpos += len + pad;
}

/* Locate the file in the archive, read header and position to data */
static TAR_MEMBER *
_tarPositionTo(ArchiveHandle *AH, const char *filename)
{
	lclContext *ctx = (lclContext *) AH->formatData;
	TAR_MEMBER *th = calloc(1, sizeof(TAR_MEMBER));
	char		c;
	char		header[512];
	size_t		i,
				len,
				blks;
	int			id;

	th->AH = AH;

	/* Go to end of current file, if any */
	if (ctx->tarFHpos != 0)
	{
		char		buf1[100],
					buf2[100];

		snprintf(buf1, sizeof(buf1), INT64_FORMAT, (int64) ctx->tarFHpos);
		snprintf(buf2, sizeof(buf2), INT64_FORMAT, (int64) ctx->tarNextMember);
		ahlog(AH, 4, "moving from position %s to next member at file position %s\n",
			  buf1, buf2);

		while (ctx->tarFHpos < ctx->tarNextMember)
			_tarReadRaw(AH, &c, 1, NULL, ctx->tarFH);
	}

	{
		char		buf[100];

		snprintf(buf, sizeof(buf), INT64_FORMAT, (int64) ctx->tarFHpos);
		ahlog(AH, 4, "now at file position %s\n", buf);
	}

	/* We are at the start of the file. or at the next member */

	/* Get the header */
	if (!_tarGetHeader(AH, th))
	{
		if (filename)
			die_horribly(AH, modulename, "could not find header for file %s in tar archive\n", filename);
		else

			/*
			 * We're just scanning the archibe for the next file, so return
			 * null
			 */
		{
			free(th);
			return NULL;
		}
	}

	while (filename != NULL && strcmp(th->targetFile, filename) != 0)
	{
		ahlog(AH, 4, "skipping tar member %s\n", th->targetFile);

		id = atoi(th->targetFile);
		if ((TocIDRequired(AH, id, AH->ropt) & REQ_DATA) != 0)
			die_horribly(AH, modulename, "dumping data out of order is not supported in this archive format: "
				"%s is required, but comes before %s in the archive file.\n",
						 th->targetFile, filename);

		/* Header doesn't match, so read to next header */
		len = ((th->fileLen + 511) & ~511);		/* Padded length */
		blks = len >> 9;		/* # of 512 byte blocks */

		for (i = 0; i < blks; i++)
			_tarReadRaw(AH, &header[0], 512, NULL, ctx->tarFH);

		if (!_tarGetHeader(AH, th))
			die_horribly(AH, modulename, "could not find header for file %s in tar archive\n", filename);

	}

	ctx->tarNextMember = ctx->tarFHpos + ((th->fileLen + 511) & ~511);
	th->pos = 0;

	return th;
}

/* Read & verify a header */
static int
_tarGetHeader(ArchiveHandle *AH, TAR_MEMBER *th)
{
	lclContext *ctx = (lclContext *) AH->formatData;
	char		h[512];
	char		tag[100];
	int			sum,
				chk;
	size_t		len;
	unsigned long ullen;
	off_t		hPos;
	bool		gotBlock = false;

	while (!gotBlock)
	{
#if 0
		if (ftello(ctx->tarFH) != ctx->tarFHpos)
		{
			char		buf1[100],
						buf2[100];

			snprintf(buf1, sizeof(buf1), INT64_FORMAT, (int64) ftello(ctx->tarFH));
			snprintf(buf2, sizeof(buf2), INT64_FORMAT, (int64) ftello(ctx->tarFHpos));
			die_horribly(AH, modulename,
			  "mismatch in actual vs. predicted file position (%s vs. %s)\n",
						 buf1, buf2);
		}
#endif

		/* Save the pos for reporting purposes */
		hPos = ctx->tarFHpos;

		/* Read a 512 byte block, return EOF, exit if short */
		len = _tarReadRaw(AH, h, 512, NULL, ctx->tarFH);
		if (len == 0)			/* EOF */
			return 0;

		if (len != 512)
			die_horribly(AH, modulename,
						 "incomplete tar header found (%lu bytes)\n",
						 (unsigned long) len);

		/* Calc checksum */
		chk = _tarChecksum(h);
		sscanf(&h[148], "%8o", &sum);

		/*
		 * If the checksum failed, see if it is a null block. If so, silently
		 * continue to the next block.
		 */
		if (chk == sum)
			gotBlock = true;
		else
		{
			int			i;

			for (i = 0; i < 512; i++)
			{
				if (h[i] != 0)
				{
					gotBlock = true;
					break;
				}
			}
		}
	}

	sscanf(&h[0], "%99s", tag);
	sscanf(&h[124], "%12lo", &ullen);
	len = (size_t) ullen;

	{
		char		buf[100];

		snprintf(buf, sizeof(buf), INT64_FORMAT, (int64) hPos);
		ahlog(AH, 3, "TOC Entry %s at %s (length %lu, checksum %d)\n",
			  tag, buf, (unsigned long) len, sum);
	}

	if (chk != sum)
	{
		char		buf[100];

		snprintf(buf, sizeof(buf), INT64_FORMAT, (int64) ftello(ctx->tarFH));
		die_horribly(AH, modulename,
					 "corrupt tar header found in %s "
					 "(expected %d, computed %d) file position %s\n",
					 tag, sum, chk, buf);
	}

	th->targetFile = strdup(tag);
	th->fileLen = len;

	return 1;
}


/*
 * Utility routine to print possibly larger than 32 bit integers in a
 * portable fashion.  Filled with zeros.
 */
static void
print_val(char *s, uint64 val, unsigned int base, size_t len)
{
	int			i;

	for (i = len; i > 0; i--)
	{
		int			digit = val % base;

		s[i - 1] = '0' + digit;
		val = val / base;
	}
}


static void
_tarWriteHeader(TAR_MEMBER *th)
{
	char		h[512];
	int			lastSum = 0;
	int			sum;

	memset(h, 0, sizeof(h));

	/* Name 100 */
	sprintf(&h[0], "%.99s", th->targetFile);

	/* Mode 8 */
	sprintf(&h[100], "100600 ");

	/* User ID 8 */
	sprintf(&h[108], "004000 ");

	/* Group 8 */
	sprintf(&h[116], "002000 ");

	/* File size 12 - 11 digits, 1 space, no NUL */
	print_val(&h[124], th->fileLen, 8, 11);
	sprintf(&h[135], " ");

	/* Mod Time 12 */
	sprintf(&h[136], "%011o ", (int) time(NULL));

	/* Checksum 8 */
	sprintf(&h[148], "%06o ", lastSum);

	/* Type - regular file */
	sprintf(&h[156], "0");

	/* Link tag 100 (NULL) */

	/* Magic 6 + Version 2 */
	sprintf(&h[257], "ustar00");

#if 0
	/* User 32 */
	sprintf(&h[265], "%.31s", "");		/* How do I get username reliably? Do
										 * I need to? */

	/* Group 32 */
	sprintf(&h[297], "%.31s", "");		/* How do I get group reliably? Do I
										 * need to? */

	/* Maj Dev 8 */
	sprintf(&h[329], "%6o ", 0);

	/* Min Dev 8 */
	sprintf(&h[337], "%6o ", 0);
#endif

	while ((sum = _tarChecksum(h)) != lastSum)
	{
		sprintf(&h[148], "%06o ", sum);
		lastSum = sum;
	}

	if (fwrite(h, 1, 512, th->tarFH) != 512)
		die_horribly(th->AH, modulename, "could not write tar header\n");

}