postgresql/src/bin/pg_dump/pg_backup_archiver.h

386 lines
14 KiB
C
Raw Normal View History

/*-------------------------------------------------------------------------
*
* pg_backup_archiver.h
*
* Private interface to the pg_dump archiver routines.
2001-03-22 05:01:46 +01:00
* It is NOT intended that these routines be called by any
* dumper directly.
*
* See the headers to pg_restore for more details.
*
* Copyright (c) 2000, Philip Warner
2001-03-22 05:01:46 +01:00
* Rights are granted to use this software in any way so long
* as this notice is not removed.
*
* The author is not responsible for loss or damages that may
* result from it's use.
*
*
* IDENTIFICATION
2010-09-20 22:08:53 +02:00
* src/bin/pg_dump/pg_backup_archiver.h
*
*-------------------------------------------------------------------------
*/
#ifndef __PG_BACKUP_ARCHIVE__
#define __PG_BACKUP_ARCHIVE__
#include "postgres_fe.h"
#include <time.h>
#include "pg_backup.h"
#include "libpq-fe.h"
#include "pqexpbuffer.h"
#define LOBBUFSIZE 16384
/*
* Note: zlib.h must be included *after* libpq-fe.h, because the latter may
* include ssl.h, which has a naming conflict with zlib.h.
*/
#ifdef HAVE_LIBZ
#include <zlib.h>
#define GZCLOSE(fh) gzclose(fh)
#define GZWRITE(p, s, n, fh) gzwrite(fh, p, (n) * (s))
#define GZREAD(p, s, n, fh) gzread(fh, p, (n) * (s))
#else
#define GZCLOSE(fh) fclose(fh)
#define GZWRITE(p, s, n, fh) (fwrite(p, s, n, fh) * (s))
#define GZREAD(p, s, n, fh) fread(p, s, n, fh)
/* this is just the redefinition of a libz constant */
#define Z_DEFAULT_COMPRESSION (-1)
2001-03-22 05:01:46 +01:00
typedef struct _z_stream
{
void *next_in;
void *next_out;
size_t avail_in;
size_t avail_out;
} z_stream;
typedef z_stream *z_streamp;
#endif
/* Current archive version number (the format we can output) */
#define K_VERS_MAJOR 1
#define K_VERS_MINOR 12
#define K_VERS_REV 0
/* Data block types */
#define BLK_DATA 1
#define BLK_BLOBS 3
/* Historical version numbers (checked in code) */
#define K_VERS_1_0 (( (1 * 256 + 0) * 256 + 0) * 256 + 0)
2001-03-22 05:01:46 +01:00
#define K_VERS_1_2 (( (1 * 256 + 2) * 256 + 0) * 256 + 0) /* Allow No ZLIB */
#define K_VERS_1_3 (( (1 * 256 + 3) * 256 + 0) * 256 + 0) /* BLOBs */
#define K_VERS_1_4 (( (1 * 256 + 4) * 256 + 0) * 256 + 0) /* Date & name in header */
#define K_VERS_1_5 (( (1 * 256 + 5) * 256 + 0) * 256 + 0) /* Handle dependencies */
#define K_VERS_1_6 (( (1 * 256 + 6) * 256 + 0) * 256 + 0) /* Schema field in TOCs */
2003-08-04 02:43:34 +02:00
#define K_VERS_1_7 (( (1 * 256 + 7) * 256 + 0) * 256 + 0) /* File Offset size in
* header */
2004-08-29 07:07:03 +02:00
#define K_VERS_1_8 (( (1 * 256 + 8) * 256 + 0) * 256 + 0) /* change interpretation
* of ID numbers and
* dependencies */
#define K_VERS_1_9 (( (1 * 256 + 9) * 256 + 0) * 256 + 0) /* add default_with_oids
* tracking */
#define K_VERS_1_10 (( (1 * 256 + 10) * 256 + 0) * 256 + 0) /* add tablespace */
#define K_VERS_1_11 (( (1 * 256 + 11) * 256 + 0) * 256 + 0) /* add toc section
* indicator */
#define K_VERS_1_12 (( (1 * 256 + 12) * 256 + 0) * 256 + 0) /* add separate BLOB
* entries */
/* Newest format we can read */
#define K_VERS_MAX (( (1 * 256 + 12) * 256 + 255) * 256 + 0)
/* Flags to indicate disposition of offsets stored in files */
#define K_OFFSET_POS_NOT_SET 1
#define K_OFFSET_POS_SET 2
#define K_OFFSET_NO_DATA 3
struct _archiveHandle;
struct _tocEntry;
struct _restoreList;
2006-10-04 02:30:14 +02:00
typedef void (*ClosePtr) (struct _archiveHandle * AH);
typedef void (*ReopenPtr) (struct _archiveHandle * AH);
2006-10-04 02:30:14 +02:00
typedef void (*ArchiveEntryPtr) (struct _archiveHandle * AH, struct _tocEntry * te);
typedef void (*StartDataPtr) (struct _archiveHandle * AH, struct _tocEntry * te);
typedef size_t (*WriteDataPtr) (struct _archiveHandle * AH, const void *data, size_t dLen);
typedef void (*EndDataPtr) (struct _archiveHandle * AH, struct _tocEntry * te);
typedef void (*StartBlobsPtr) (struct _archiveHandle * AH, struct _tocEntry * te);
typedef void (*StartBlobPtr) (struct _archiveHandle * AH, struct _tocEntry * te, Oid oid);
typedef void (*EndBlobPtr) (struct _archiveHandle * AH, struct _tocEntry * te, Oid oid);
typedef void (*EndBlobsPtr) (struct _archiveHandle * AH, struct _tocEntry * te);
typedef int (*WriteBytePtr) (struct _archiveHandle * AH, const int i);
typedef int (*ReadBytePtr) (struct _archiveHandle * AH);
typedef size_t (*WriteBufPtr) (struct _archiveHandle * AH, const void *c, size_t len);
typedef size_t (*ReadBufPtr) (struct _archiveHandle * AH, void *buf, size_t len);
typedef void (*SaveArchivePtr) (struct _archiveHandle * AH);
typedef void (*WriteExtraTocPtr) (struct _archiveHandle * AH, struct _tocEntry * te);
typedef void (*ReadExtraTocPtr) (struct _archiveHandle * AH, struct _tocEntry * te);
typedef void (*PrintExtraTocPtr) (struct _archiveHandle * AH, struct _tocEntry * te);
typedef void (*PrintTocDataPtr) (struct _archiveHandle * AH, struct _tocEntry * te, RestoreOptions *ropt);
typedef void (*ClonePtr) (struct _archiveHandle * AH);
typedef void (*DeClonePtr) (struct _archiveHandle * AH);
2006-10-04 02:30:14 +02:00
typedef size_t (*CustomOutPtr) (struct _archiveHandle * AH, const void *buf, size_t len);
2001-03-22 05:01:46 +01:00
typedef enum
{
SQL_SCAN = 0, /* normal */
SQL_IN_SQL_COMMENT, /* -- comment */
SQL_IN_EXT_COMMENT, /* slash-star comment */
SQL_IN_SINGLE_QUOTE, /* '...' literal */
SQL_IN_E_QUOTE, /* E'...' literal */
SQL_IN_DOUBLE_QUOTE, /* "..." identifier */
SQL_IN_DOLLAR_TAG, /* possible dollar-quote starting tag */
SQL_IN_DOLLAR_QUOTE /* body of dollar quote */
2001-03-22 05:01:46 +01:00
} sqlparseState;
typedef struct
{
sqlparseState state; /* see above */
char lastChar; /* preceding char, or '\0' initially */
bool backSlash; /* next char is backslash quoted? */
int braceDepth; /* parenthesis nesting depth */
PQExpBuffer tagBuf; /* dollar quote tag (NULL if not created) */
int minTagEndPos; /* first possible end position of $-quote */
} sqlparseInfo;
2004-08-29 07:07:03 +02:00
typedef enum
They are two different problems; the TOC entry is important for any multiline command or to rerun the command easily later. Whereas displaying the failed SQL command is a matter of fixing the error messages. The latter is complicated by failed COPY commands which, with die-on-errors off, results in the data being processed as a command, so dumping the command will dump all of the data. In the case of long commands, should the whole command be dumped? eg. (eg. several pages of function definition). In the case of the COPY command, I'm not sure what to do. Obviously, it would be best to avoid sending the data, but the data and command are combined (from memory). Also, the 'data' may be in the form of INSERT statements. Attached patch produces the first 125 chars of the command: pg_restore: [archiver (db)] Error while PROCESSING TOC: pg_restore: [archiver (db)] Error from TOC Entry 26; 1255 16449270 FUNCTION plpgsql_call_handler() pjw pg_restore: [archiver (db)] could not execute query: ERROR: function "plpgsql_call_handler" already exists with same argument types Command was: CREATE FUNCTION plpgsql_call_handler() RETURNS language_handler AS '/var/lib/pgsql-8.0b1/lib/plpgsql', 'plpgsql_call_han... pg_restore: [archiver (db)] Error from TOC Entry 27; 1255 16449271 FUNCTION plpgsql_validator(oid) pjw pg_restore: [archiver (db)] could not execute query: ERROR: function "plpgsql_validator" already exists with same argument types Command was: CREATE FUNCTION plpgsql_validator(oid) RETURNS void AS '/var/lib/pgsql-8.0b1/lib/plpgsql', 'plpgsql_validator' LANGU... Philip Warner
2004-08-20 22:00:34 +02:00
{
2004-08-29 07:07:03 +02:00
STAGE_NONE = 0,
STAGE_INITIALIZING,
STAGE_PROCESSING,
STAGE_FINALIZING
They are two different problems; the TOC entry is important for any multiline command or to rerun the command easily later. Whereas displaying the failed SQL command is a matter of fixing the error messages. The latter is complicated by failed COPY commands which, with die-on-errors off, results in the data being processed as a command, so dumping the command will dump all of the data. In the case of long commands, should the whole command be dumped? eg. (eg. several pages of function definition). In the case of the COPY command, I'm not sure what to do. Obviously, it would be best to avoid sending the data, but the data and command are combined (from memory). Also, the 'data' may be in the form of INSERT statements. Attached patch produces the first 125 chars of the command: pg_restore: [archiver (db)] Error while PROCESSING TOC: pg_restore: [archiver (db)] Error from TOC Entry 26; 1255 16449270 FUNCTION plpgsql_call_handler() pjw pg_restore: [archiver (db)] could not execute query: ERROR: function "plpgsql_call_handler" already exists with same argument types Command was: CREATE FUNCTION plpgsql_call_handler() RETURNS language_handler AS '/var/lib/pgsql-8.0b1/lib/plpgsql', 'plpgsql_call_han... pg_restore: [archiver (db)] Error from TOC Entry 27; 1255 16449271 FUNCTION plpgsql_validator(oid) pjw pg_restore: [archiver (db)] could not execute query: ERROR: function "plpgsql_validator" already exists with same argument types Command was: CREATE FUNCTION plpgsql_validator(oid) RETURNS void AS '/var/lib/pgsql-8.0b1/lib/plpgsql', 'plpgsql_validator' LANGU... Philip Warner
2004-08-20 22:00:34 +02:00
} ArchiverStage;
typedef enum
{
REQ_SCHEMA = 1,
REQ_DATA = 2,
REQ_ALL = REQ_SCHEMA + REQ_DATA
} teReqs;
2001-03-22 05:01:46 +01:00
typedef struct _archiveHandle
{
Archive public; /* Public part of archive */
char vmaj; /* Version of file */
char vmin;
char vrev;
int version; /* Conveniently formatted version */
2005-10-15 04:49:52 +02:00
char *archiveRemoteVersion; /* When reading an archive, the
* version of the dumped DB */
char *archiveDumpVersion; /* When reading an archive, the
* version of the dumper */
2001-03-22 05:01:46 +01:00
int debugLevel; /* Used for logging (currently only by
* --verbose) */
size_t intSize; /* Size of an integer in the archive */
2003-08-04 02:43:34 +02:00
size_t offSize; /* Size of a file offset in the archive -
* Added V1.7 */
2001-03-22 05:01:46 +01:00
ArchiveFormat format; /* Archive format */
2001-03-22 05:01:46 +01:00
sqlparseInfo sqlparse;
PQExpBuffer sqlBuf;
2001-03-22 05:01:46 +01:00
time_t createDate; /* Date archive created */
/*
2001-03-22 05:01:46 +01:00
* Fields used when discovering header. A format can always get the
* previous read bytes from here...
*/
2005-10-15 04:49:52 +02:00
int readHeader; /* Used if file header has been read already */
char *lookahead; /* Buffer used when reading header to discover
* format */
size_t lookaheadSize; /* Size of allocated buffer */
size_t lookaheadLen; /* Length of data in lookahead */
pgoff_t lookaheadPos; /* Current read position in lookahead buffer */
2001-03-22 05:01:46 +01:00
ArchiveEntryPtr ArchiveEntryPtr; /* Called for each metadata object */
StartDataPtr StartDataPtr; /* Called when table data is about to be
* dumped */
WriteDataPtr WriteDataPtr; /* Called to send some table data to the
* archive */
EndDataPtr EndDataPtr; /* Called when table data dump is finished */
WriteBytePtr WriteBytePtr; /* Write a byte to output */
ReadBytePtr ReadBytePtr; /* Read a byte from an archive */
WriteBufPtr WriteBufPtr; /* Write a buffer of output to the archive */
ReadBufPtr ReadBufPtr; /* Read a buffer of input from the archive */
ClosePtr ClosePtr; /* Close the archive */
ReopenPtr ReopenPtr; /* Reopen the archive */
2001-03-22 05:01:46 +01:00
WriteExtraTocPtr WriteExtraTocPtr; /* Write extra TOC entry data
2005-10-15 04:49:52 +02:00
* associated with the current archive
* format */
2001-03-22 05:01:46 +01:00
ReadExtraTocPtr ReadExtraTocPtr; /* Read extr info associated with
* archie format */
PrintExtraTocPtr PrintExtraTocPtr; /* Extra TOC info for format */
PrintTocDataPtr PrintTocDataPtr;
StartBlobsPtr StartBlobsPtr;
EndBlobsPtr EndBlobsPtr;
StartBlobPtr StartBlobPtr;
EndBlobPtr EndBlobPtr;
ClonePtr ClonePtr; /* Clone format-specific fields */
DeClonePtr DeClonePtr; /* Clean up cloned fields */
CustomOutPtr CustomOutPtr; /* Alternative script output routine */
/* Stuff for direct DB connection */
2001-03-22 05:01:46 +01:00
char *archdbname; /* DB name *read* from archive */
enum trivalue promptPassword;
char *savedPassword; /* password for ropt->username, if known */
2001-03-22 05:01:46 +01:00
PGconn *connection;
2005-10-15 04:49:52 +02:00
int connectToDB; /* Flag to indicate if direct DB connection is
* required */
bool writingCopyData; /* True when we are sending COPY data */
bool pgCopyIn; /* Currently in libpq 'COPY IN' mode. */
2001-03-22 05:01:46 +01:00
PQExpBuffer pgCopyBuf; /* Left-over data from incomplete lines in
* COPY IN */
int loFd; /* BLOB fd */
int writingBlob; /* Flag */
int blobCount; /* # of blobs restored */
char *fSpec; /* Archive File Spec */
FILE *FH; /* General purpose file handle */
void *OF;
int gzOut; /* Output file */
struct _tocEntry *toc; /* List of TOC entries */
int tocCount; /* Number of TOC entries */
DumpId maxDumpId; /* largest DumpId among all TOC entries */
2001-03-22 05:01:46 +01:00
struct _tocEntry *currToc; /* Used when dumping data */
int compression; /* Compression requested on open
* Possible values for compression:
* -1 Z_DEFAULT_COMPRESSION
* 0 COMPRESSION_NONE
* 1-9 levels for gzip compression */
2001-03-22 05:01:46 +01:00
ArchiveMode mode; /* File mode - r or w */
void *formatData; /* Header data specific to file format */
2005-10-15 04:49:52 +02:00
RestoreOptions *ropt; /* Used to check restore options in ahwrite
* etc */
/* these vars track state to avoid sending redundant SET commands */
char *currUser; /* current username, or NULL if unknown */
char *currSchema; /* current schema, or NULL */
char *currTablespace; /* current tablespace, or NULL */
bool currWithOids; /* current default_with_oids setting */
2004-08-29 07:07:03 +02:00
2002-09-04 22:31:48 +02:00
void *lo_buf;
size_t lo_buf_used;
size_t lo_buf_size;
They are two different problems; the TOC entry is important for any multiline command or to rerun the command easily later. Whereas displaying the failed SQL command is a matter of fixing the error messages. The latter is complicated by failed COPY commands which, with die-on-errors off, results in the data being processed as a command, so dumping the command will dump all of the data. In the case of long commands, should the whole command be dumped? eg. (eg. several pages of function definition). In the case of the COPY command, I'm not sure what to do. Obviously, it would be best to avoid sending the data, but the data and command are combined (from memory). Also, the 'data' may be in the form of INSERT statements. Attached patch produces the first 125 chars of the command: pg_restore: [archiver (db)] Error while PROCESSING TOC: pg_restore: [archiver (db)] Error from TOC Entry 26; 1255 16449270 FUNCTION plpgsql_call_handler() pjw pg_restore: [archiver (db)] could not execute query: ERROR: function "plpgsql_call_handler" already exists with same argument types Command was: CREATE FUNCTION plpgsql_call_handler() RETURNS language_handler AS '/var/lib/pgsql-8.0b1/lib/plpgsql', 'plpgsql_call_han... pg_restore: [archiver (db)] Error from TOC Entry 27; 1255 16449271 FUNCTION plpgsql_validator(oid) pjw pg_restore: [archiver (db)] could not execute query: ERROR: function "plpgsql_validator" already exists with same argument types Command was: CREATE FUNCTION plpgsql_validator(oid) RETURNS void AS '/var/lib/pgsql-8.0b1/lib/plpgsql', 'plpgsql_validator' LANGU... Philip Warner
2004-08-20 22:00:34 +02:00
2004-08-29 07:07:03 +02:00
int noTocComments;
ArchiverStage stage;
ArchiverStage lastErrorStage;
struct _tocEntry *currentTE;
struct _tocEntry *lastErrorTE;
} ArchiveHandle;
2001-03-22 05:01:46 +01:00
typedef struct _tocEntry
{
struct _tocEntry *prev;
struct _tocEntry *next;
CatalogId catalogId;
DumpId dumpId;
teSection section;
2005-10-15 04:49:52 +02:00
bool hadDumper; /* Archiver was passed a dumper routine (used
* in restore) */
2002-09-04 22:31:48 +02:00
char *tag; /* index tag */
char *namespace; /* null or empty string if not in a schema */
char *tablespace; /* null if not in a tablespace; empty string
* means use database default */
char *owner;
bool withOids; /* Used only by "TABLE" tags */
2001-03-22 05:01:46 +01:00
char *desc;
char *defn;
char *dropStmt;
char *copyStmt;
DumpId *dependencies; /* dumpIds of objects this one depends on */
int nDeps; /* number of dependencies */
2001-03-22 05:01:46 +01:00
DataDumperPtr dataDumper; /* Routine to dump data for object */
void *dataDumperArg; /* Arg for above routine */
void *formatData; /* TOC Entry data specific to file format */
/* working state (needed only for parallel restore) */
2010-02-26 03:01:40 +01:00
struct _tocEntry *par_prev; /* list links for pending/ready items; */
struct _tocEntry *par_next; /* these are NULL if not in either list */
bool created; /* set for DATA member if TABLE was created */
int depCount; /* number of dependencies not yet restored */
DumpId *revDeps; /* dumpIds of objects depending on this one */
int nRevDeps; /* number of such dependencies */
DumpId *lockDeps; /* dumpIds of objects this one needs lock on */
int nLockDeps; /* number of such dependencies */
} TocEntry;
/* Used everywhere */
extern const char *progname;
extern void die_horribly(ArchiveHandle *AH, const char *modulename, const char *fmt,...) __attribute__((format(printf, 3, 4)));
extern void warn_or_die_horribly(ArchiveHandle *AH, const char *modulename, const char *fmt,...) __attribute__((format(printf, 3, 4)));
extern void write_msg(const char *modulename, const char *fmt,...) __attribute__((format(printf, 2, 3)));
2001-03-22 05:01:46 +01:00
extern void WriteTOC(ArchiveHandle *AH);
extern void ReadTOC(ArchiveHandle *AH);
extern void WriteHead(ArchiveHandle *AH);
extern void ReadHead(ArchiveHandle *AH);
extern void WriteToc(ArchiveHandle *AH);
extern void ReadToc(ArchiveHandle *AH);
extern void WriteDataChunks(ArchiveHandle *AH);
extern teReqs TocIDRequired(ArchiveHandle *AH, DumpId id, RestoreOptions *ropt);
extern bool checkSeek(FILE *fp);
#define appendStringLiteralAHX(buf,str,AH) \
appendStringLiteral(buf, str, (AH)->public.encoding, (AH)->public.std_strings)
#define appendByteaLiteralAHX(buf,str,len,AH) \
appendByteaLiteral(buf, str, len, (AH)->public.std_strings)
/*
* Mandatory routines for each supported format
*/
2002-09-04 22:31:48 +02:00
extern size_t WriteInt(ArchiveHandle *AH, int i);
2001-03-22 05:01:46 +01:00
extern int ReadInt(ArchiveHandle *AH);
extern char *ReadStr(ArchiveHandle *AH);
2002-09-04 22:31:48 +02:00
extern size_t WriteStr(ArchiveHandle *AH, const char *s);
int ReadOffset(ArchiveHandle *, pgoff_t *);
size_t WriteOffset(ArchiveHandle *, pgoff_t, int);
2001-03-22 05:01:46 +01:00
extern void StartRestoreBlobs(ArchiveHandle *AH);
extern void StartRestoreBlob(ArchiveHandle *AH, Oid oid, bool drop);
extern void EndRestoreBlob(ArchiveHandle *AH, Oid oid);
2001-03-22 05:01:46 +01:00
extern void EndRestoreBlobs(ArchiveHandle *AH);
2001-03-22 05:01:46 +01:00
extern void InitArchiveFmt_Custom(ArchiveHandle *AH);
extern void InitArchiveFmt_Files(ArchiveHandle *AH);
extern void InitArchiveFmt_Null(ArchiveHandle *AH);
extern void InitArchiveFmt_Tar(ArchiveHandle *AH);
extern bool isValidTarHeader(char *header);
extern int ReconnectToServer(ArchiveHandle *AH, const char *dbname, const char *newUser);
2010-02-26 03:01:40 +01:00
extern void DropBlobIfExists(ArchiveHandle *AH, Oid oid);
2001-03-22 05:01:46 +01:00
int ahwrite(const void *ptr, size_t size, size_t nmemb, ArchiveHandle *AH);
int ahprintf(ArchiveHandle *AH, const char *fmt,...) __attribute__((format(printf, 2, 3)));
void ahlog(ArchiveHandle *AH, int level, const char *fmt,...) __attribute__((format(printf, 3, 4)));
#endif