Fix pg_restore's direct-to-database mode for INSERT-style table data.

In commit 6545a901aaf84cb05212bb6a7674059908f527c3, I removed the mini SQL
lexer that was in pg_backup_db.c, thinking that it had no real purpose
beyond separating COPY data from SQL commands, which purpose had been
obsoleted by long-ago fixes in pg_dump's archive file format.
Unfortunately this was in error: that code was also used to identify
command boundaries in INSERT-style table data, which is run together as a
single string in the archive file for better compressibility.  As a result,
direct-to-database restores from archive files made with --inserts or
--column-inserts fail in our latest releases, as reported by Dick Visser.

To fix, restore the mini SQL lexer, but simplify it by adjusting the
calling logic so that it's only required to cope with INSERT-style table
data, not arbitrary SQL commands.  This allows us to not have to deal with
SQL comments, E'' strings, or dollar-quoted strings, none of which have
ever been emitted by dumpTableData_insert.

Also, fix the lexer to cope with standard-conforming strings, which was the
actual bug that the previous patch was meant to solve.

Back-patch to all supported branches.  The previous patch went back to 8.2,
which unfortunately means that the EOL release of 8.2 contains this bug,
but I don't think we're doing another 8.2 release just because of that.

1 files changed, 24 insertions, 1 deletions

diff --git a/src/bin/pg_dump/pg_backup_archiver.h b/src/bin/pg_dump/pg_backup_archiver.h
index a3a87dcd29b..fad1bc00a9f 100644
--- a/src/bin/pg_dump/pg_backup_archiver.h
+++ b/src/bin/pg_dump/pg_backup_archiver.h
@@ -139,6 +139,20 @@ typedef struct _outputContext
 
 typedef enum
 {
+	SQL_SCAN = 0,				/* normal */
+	SQL_IN_SINGLE_QUOTE,		/* '...' literal */
+	SQL_IN_DOUBLE_QUOTE			/* "..." identifier */
+} sqlparseState;
+
+typedef struct
+{
+	sqlparseState state;		/* see above */
+	bool		backSlash;		/* next char is backslash quoted? */
+	PQExpBuffer curCmd;			/* incomplete line (NULL if not created) */
+} sqlparseInfo;
+
+typedef enum
+{
 	STAGE_NONE = 0,
 	STAGE_INITIALIZING,
 	STAGE_PROCESSING,
@@ -147,6 +161,13 @@ typedef enum
 
 typedef enum
 {
+	OUTPUT_SQLCMDS = 0,			/* emitting general SQL commands */
+	OUTPUT_COPYDATA,			/* writing COPY data */
+	OUTPUT_OTHERDATA			/* writing data as INSERT commands */
+} ArchiverOutput;
+
+typedef enum
+{
 	REQ_SCHEMA = 1,
 	REQ_DATA = 2,
 	REQ_ALL = REQ_SCHEMA + REQ_DATA
@@ -172,6 +193,8 @@ typedef struct _archiveHandle
 								 * Added V1.7 */
 	ArchiveFormat format;		/* Archive format */
 
+	sqlparseInfo sqlparse;		/* state for parsing INSERT data */
+
 	time_t		createDate;		/* Date archive created */
 
 	/*
@@ -222,7 +245,7 @@ typedef struct _archiveHandle
 	PGconn	   *connection;
 	int			connectToDB;	/* Flag to indicate if direct DB connection is
 								 * required */
-	bool		writingCopyData;	/* True when we are sending COPY data */
+	ArchiverOutput outputKind;	/* Flag for what we're currently writing */
 	bool		pgCopyIn;		/* Currently in libpq 'COPY IN' mode. */
 
 	int			loFd;			/* BLOB fd */