|
|
|
|
/*-------------------------------------------------------------------------
|
|
|
|
|
*
|
|
|
|
|
* genfile.c
|
|
|
|
|
* Functions for direct access to files
|
|
|
|
|
*
|
|
|
|
|
*
|
|
|
|
|
* Copyright (c) 2004-2018, PostgreSQL Global Development Group
|
|
|
|
|
*
|
|
|
|
|
* Author: Andreas Pflug <pgadmin@pse-consulting.de>
|
|
|
|
|
*
|
|
|
|
|
* IDENTIFICATION
|
|
|
|
|
* src/backend/utils/adt/genfile.c
|
|
|
|
|
*
|
|
|
|
|
*-------------------------------------------------------------------------
|
|
|
|
|
*/
|
|
|
|
|
#include "postgres.h"
|
|
|
|
|
|
|
|
|
|
#include <sys/file.h>
|
|
|
|
|
#include <sys/stat.h>
|
|
|
|
|
#include <unistd.h>
|
|
|
|
|
#include <dirent.h>
|
|
|
|
|
|
|
|
|
|
#include "access/htup_details.h"
|
|
|
|
|
#include "access/xlog_internal.h"
|
|
|
|
|
#include "catalog/pg_authid.h"
|
|
|
|
|
#include "catalog/pg_type.h"
|
|
|
|
|
#include "funcapi.h"
|
|
|
|
|
#include "mb/pg_wchar.h"
|
|
|
|
|
#include "miscadmin.h"
|
|
|
|
|
#include "postmaster/syslogger.h"
|
|
|
|
|
#include "storage/fd.h"
|
|
|
|
|
#include "utils/builtins.h"
|
|
|
|
|
#include "utils/memutils.h"
|
|
|
|
|
#include "utils/timestamp.h"
|
|
|
|
|
|
|
|
|
|
typedef struct
|
|
|
|
|
{
|
|
|
|
|
char *location;
|
|
|
|
|
DIR *dirdesc;
|
|
|
|
|
bool include_dot_dirs;
|
|
|
|
|
} directory_fctx;
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Convert a "text" filename argument to C string, and check it's allowable.
|
|
|
|
|
*
|
|
|
|
|
* Filename may be absolute or relative to the DataDir, but we only allow
|
|
|
|
|
* absolute paths that match DataDir or Log_directory.
|
|
|
|
|
*
|
|
|
|
|
* This does a privilege check against the 'pg_read_server_files' role, so
|
|
|
|
|
* this function is really only appropriate for callers who are only checking
|
|
|
|
|
* 'read' access. Do not use this function if you are looking for a check
|
|
|
|
|
* for 'write' or 'program' access without updating it to access the type
|
|
|
|
|
* of check as an argument and checking the appropriate role membership.
|
|
|
|
|
*/
|
|
|
|
|
static char *
|
|
|
|
|
convert_and_check_filename(text *arg)
|
|
|
|
|
{
|
|
|
|
|
char *filename;
|
|
|
|
|
|
|
|
|
|
filename = text_to_cstring(arg);
|
|
|
|
|
canonicalize_path(filename); /* filename can change length here */
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Members of the 'pg_read_server_files' role are allowed to access any
|
|
|
|
|
* files on the server as the PG user, so no need to do any further checks
|
|
|
|
|
* here.
|
|
|
|
|
*/
|
|
|
|
|
if (is_member_of_role(GetUserId(), DEFAULT_ROLE_READ_SERVER_FILES))
|
|
|
|
|
return filename;
|
|
|
|
|
|
|
|
|
|
/* User isn't a member of the default role, so check if it's allowable */
|
|
|
|
|
if (is_absolute_path(filename))
|
|
|
|
|
{
|
|
|
|
|
/* Disallow '/a/b/data/..' */
|
|
|
|
|
if (path_contains_parent_reference(filename))
|
|
|
|
|
ereport(ERROR,
|
|
|
|
|
(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
|
Phase 3 of pgindent updates.
Don't move parenthesized lines to the left, even if that means they
flow past the right margin.
By default, BSD indent lines up statement continuation lines that are
within parentheses so that they start just to the right of the preceding
left parenthesis. However, traditionally, if that resulted in the
continuation line extending to the right of the desired right margin,
then indent would push it left just far enough to not overrun the margin,
if it could do so without making the continuation line start to the left of
the current statement indent. That makes for a weird mix of indentations
unless one has been completely rigid about never violating the 80-column
limit.
This behavior has been pretty universally panned by Postgres developers.
Hence, disable it with indent's new -lpl switch, so that parenthesized
lines are always lined up with the preceding left paren.
This patch is much less interesting than the first round of indent
changes, but also bulkier, so I thought it best to separate the effects.
Discussion: https://postgr.es/m/E1dAmxK-0006EE-1r@gemulon.postgresql.org
Discussion: https://postgr.es/m/30527.1495162840@sss.pgh.pa.us
9 years ago
|
|
|
(errmsg("reference to parent directory (\"..\") not allowed"))));
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Allow absolute paths if within DataDir or Log_directory, even
|
|
|
|
|
* though Log_directory might be outside DataDir.
|
|
|
|
|
*/
|
|
|
|
|
if (!path_is_prefix_of_path(DataDir, filename) &&
|
|
|
|
|
(!is_absolute_path(Log_directory) ||
|
|
|
|
|
!path_is_prefix_of_path(Log_directory, filename)))
|
|
|
|
|
ereport(ERROR,
|
|
|
|
|
(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
|
|
|
|
|
(errmsg("absolute path not allowed"))));
|
|
|
|
|
}
|
|
|
|
|
else if (!path_is_relative_and_below_cwd(filename))
|
|
|
|
|
ereport(ERROR,
|
|
|
|
|
(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
|
|
|
|
|
(errmsg("path must be in or below the current directory"))));
|
|
|
|
|
|
|
|
|
|
return filename;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Read a section of a file, returning it as bytea
|
|
|
|
|
*
|
|
|
|
|
* Caller is responsible for all permissions checking.
|
|
|
|
|
*
|
|
|
|
|
* We read the whole of the file when bytes_to_read is negative.
|
|
|
|
|
*/
|
|
|
|
|
static bytea *
|
|
|
|
|
read_binary_file(const char *filename, int64 seek_offset, int64 bytes_to_read,
|
|
|
|
|
bool missing_ok)
|
|
|
|
|
{
|
|
|
|
|
bytea *buf;
|
|
|
|
|
size_t nbytes;
|
|
|
|
|
FILE *file;
|
|
|
|
|
|
|
|
|
|
if (bytes_to_read < 0)
|
|
|
|
|
{
|
|
|
|
|
if (seek_offset < 0)
|
|
|
|
|
bytes_to_read = -seek_offset;
|
|
|
|
|
else
|
|
|
|
|
{
|
|
|
|
|
struct stat fst;
|
|
|
|
|
|
|
|
|
|
if (stat(filename, &fst) < 0)
|
|
|
|
|
{
|
|
|
|
|
if (missing_ok && errno == ENOENT)
|
|
|
|
|
return NULL;
|
|
|
|
|
else
|
|
|
|
|
ereport(ERROR,
|
|
|
|
|
(errcode_for_file_access(),
|
Phase 3 of pgindent updates.
Don't move parenthesized lines to the left, even if that means they
flow past the right margin.
By default, BSD indent lines up statement continuation lines that are
within parentheses so that they start just to the right of the preceding
left parenthesis. However, traditionally, if that resulted in the
continuation line extending to the right of the desired right margin,
then indent would push it left just far enough to not overrun the margin,
if it could do so without making the continuation line start to the left of
the current statement indent. That makes for a weird mix of indentations
unless one has been completely rigid about never violating the 80-column
limit.
This behavior has been pretty universally panned by Postgres developers.
Hence, disable it with indent's new -lpl switch, so that parenthesized
lines are always lined up with the preceding left paren.
This patch is much less interesting than the first round of indent
changes, but also bulkier, so I thought it best to separate the effects.
Discussion: https://postgr.es/m/E1dAmxK-0006EE-1r@gemulon.postgresql.org
Discussion: https://postgr.es/m/30527.1495162840@sss.pgh.pa.us
9 years ago
|
|
|
errmsg("could not stat file \"%s\": %m", filename)));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
bytes_to_read = fst.st_size - seek_offset;
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/* not sure why anyone thought that int64 length was a good idea */
|
|
|
|
|
if (bytes_to_read > (MaxAllocSize - VARHDRSZ))
|
|
|
|
|
ereport(ERROR,
|
|
|
|
|
(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
|
|
|
|
|
errmsg("requested length too large")));
|
|
|
|
|
|
|
|
|
|
if ((file = AllocateFile(filename, PG_BINARY_R)) == NULL)
|
|
|
|
|
{
|
|
|
|
|
if (missing_ok && errno == ENOENT)
|
|
|
|
|
return NULL;
|
|
|
|
|
else
|
|
|
|
|
ereport(ERROR,
|
|
|
|
|
(errcode_for_file_access(),
|
|
|
|
|
errmsg("could not open file \"%s\" for reading: %m",
|
|
|
|
|
filename)));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
if (fseeko(file, (off_t) seek_offset,
|
|
|
|
|
(seek_offset >= 0) ? SEEK_SET : SEEK_END) != 0)
|
|
|
|
|
ereport(ERROR,
|
|
|
|
|
(errcode_for_file_access(),
|
|
|
|
|
errmsg("could not seek in file \"%s\": %m", filename)));
|
|
|
|
|
|
|
|
|
|
buf = (bytea *) palloc((Size) bytes_to_read + VARHDRSZ);
|
|
|
|
|
|
|
|
|
|
nbytes = fread(VARDATA(buf), 1, (size_t) bytes_to_read, file);
|
|
|
|
|
|
|
|
|
|
if (ferror(file))
|
|
|
|
|
ereport(ERROR,
|
|
|
|
|
(errcode_for_file_access(),
|
|
|
|
|
errmsg("could not read file \"%s\": %m", filename)));
|
|
|
|
|
|
|
|
|
|
SET_VARSIZE(buf, nbytes + VARHDRSZ);
|
|
|
|
|
|
|
|
|
|
FreeFile(file);
|
|
|
|
|
|
|
|
|
|
return buf;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Similar to read_binary_file, but we verify that the contents are valid
|
|
|
|
|
* in the database encoding.
|
|
|
|
|
*/
|
|
|
|
|
static text *
|
|
|
|
|
read_text_file(const char *filename, int64 seek_offset, int64 bytes_to_read,
|
|
|
|
|
bool missing_ok)
|
|
|
|
|
{
|
|
|
|
|
bytea *buf;
|
|
|
|
|
|
|
|
|
|
buf = read_binary_file(filename, seek_offset, bytes_to_read, missing_ok);
|
|
|
|
|
|
|
|
|
|
if (buf != NULL)
|
|
|
|
|
{
|
|
|
|
|
/* Make sure the input is valid */
|
|
|
|
|
pg_verifymbstr(VARDATA(buf), VARSIZE(buf) - VARHDRSZ, false);
|
|
|
|
|
|
|
|
|
|
/* OK, we can cast it to text safely */
|
|
|
|
|
return (text *) buf;
|
|
|
|
|
}
|
|
|
|
|
else
|
|
|
|
|
return NULL;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Read a section of a file, returning it as text
|
|
|
|
|
*/
|
|
|
|
|
Datum
|
|
|
|
|
pg_read_file(PG_FUNCTION_ARGS)
|
|
|
|
|
{
|
|
|
|
|
text *filename_t = PG_GETARG_TEXT_PP(0);
|
|
|
|
|
int64 seek_offset = 0;
|
|
|
|
|
int64 bytes_to_read = -1;
|
|
|
|
|
bool missing_ok = false;
|
|
|
|
|
char *filename;
|
|
|
|
|
text *result;
|
|
|
|
|
|
|
|
|
|
/* handle optional arguments */
|
|
|
|
|
if (PG_NARGS() >= 3)
|
|
|
|
|
{
|
|
|
|
|
seek_offset = PG_GETARG_INT64(1);
|
|
|
|
|
bytes_to_read = PG_GETARG_INT64(2);
|
|
|
|
|
|
|
|
|
|
if (bytes_to_read < 0)
|
|
|
|
|
ereport(ERROR,
|
|
|
|
|
(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
|
|
|
|
|
errmsg("requested length cannot be negative")));
|
|
|
|
|
}
|
|
|
|
|
if (PG_NARGS() >= 4)
|
|
|
|
|
missing_ok = PG_GETARG_BOOL(3);
|
|
|
|
|
|
|
|
|
|
filename = convert_and_check_filename(filename_t);
|
|
|
|
|
|
|
|
|
|
result = read_text_file(filename, seek_offset, bytes_to_read, missing_ok);
|
|
|
|
|
if (result)
|
|
|
|
|
PG_RETURN_TEXT_P(result);
|
|
|
|
|
else
|
|
|
|
|
PG_RETURN_NULL();
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Read a section of a file, returning it as bytea
|
|
|
|
|
*/
|
|
|
|
|
Datum
|
|
|
|
|
pg_read_binary_file(PG_FUNCTION_ARGS)
|
|
|
|
|
{
|
|
|
|
|
text *filename_t = PG_GETARG_TEXT_PP(0);
|
|
|
|
|
int64 seek_offset = 0;
|
|
|
|
|
int64 bytes_to_read = -1;
|
|
|
|
|
bool missing_ok = false;
|
|
|
|
|
char *filename;
|
|
|
|
|
bytea *result;
|
|
|
|
|
|
|
|
|
|
/* handle optional arguments */
|
|
|
|
|
if (PG_NARGS() >= 3)
|
|
|
|
|
{
|
|
|
|
|
seek_offset = PG_GETARG_INT64(1);
|
|
|
|
|
bytes_to_read = PG_GETARG_INT64(2);
|
|
|
|
|
|
|
|
|
|
if (bytes_to_read < 0)
|
|
|
|
|
ereport(ERROR,
|
|
|
|
|
(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
|
|
|
|
|
errmsg("requested length cannot be negative")));
|
|
|
|
|
}
|
|
|
|
|
if (PG_NARGS() >= 4)
|
|
|
|
|
missing_ok = PG_GETARG_BOOL(3);
|
|
|
|
|
|
|
|
|
|
filename = convert_and_check_filename(filename_t);
|
|
|
|
|
|
|
|
|
|
result = read_binary_file(filename, seek_offset,
|
|
|
|
|
bytes_to_read, missing_ok);
|
|
|
|
|
if (result)
|
|
|
|
|
PG_RETURN_BYTEA_P(result);
|
|
|
|
|
else
|
|
|
|
|
PG_RETURN_NULL();
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Wrapper functions for the 1 and 3 argument variants of pg_read_file()
|
|
|
|
|
* and pg_binary_read_file().
|
|
|
|
|
*
|
|
|
|
|
* These are necessary to pass the sanity check in opr_sanity, which checks
|
|
|
|
|
* that all built-in functions that share the implementing C function take
|
|
|
|
|
* the same number of arguments.
|
|
|
|
|
*/
|
|
|
|
|
Datum
|
|
|
|
|
pg_read_file_off_len(PG_FUNCTION_ARGS)
|
|
|
|
|
{
|
|
|
|
|
return pg_read_file(fcinfo);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
Datum
|
|
|
|
|
pg_read_file_all(PG_FUNCTION_ARGS)
|
|
|
|
|
{
|
|
|
|
|
return pg_read_file(fcinfo);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
Datum
|
|
|
|
|
pg_read_binary_file_off_len(PG_FUNCTION_ARGS)
|
|
|
|
|
{
|
|
|
|
|
return pg_read_binary_file(fcinfo);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
Datum
|
|
|
|
|
pg_read_binary_file_all(PG_FUNCTION_ARGS)
|
|
|
|
|
{
|
|
|
|
|
return pg_read_binary_file(fcinfo);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* stat a file
|
|
|
|
|
*/
|
|
|
|
|
Datum
|
|
|
|
|
pg_stat_file(PG_FUNCTION_ARGS)
|
|
|
|
|
{
|
|
|
|
|
text *filename_t = PG_GETARG_TEXT_PP(0);
|
|
|
|
|
char *filename;
|
|
|
|
|
struct stat fst;
|
|
|
|
|
Datum values[6];
|
|
|
|
|
bool isnull[6];
|
|
|
|
|
HeapTuple tuple;
|
|
|
|
|
TupleDesc tupdesc;
|
|
|
|
|
bool missing_ok = false;
|
|
|
|
|
|
|
|
|
|
/* check the optional argument */
|
|
|
|
|
if (PG_NARGS() == 2)
|
|
|
|
|
missing_ok = PG_GETARG_BOOL(1);
|
|
|
|
|
|
|
|
|
|
filename = convert_and_check_filename(filename_t);
|
|
|
|
|
|
|
|
|
|
if (stat(filename, &fst) < 0)
|
|
|
|
|
{
|
|
|
|
|
if (missing_ok && errno == ENOENT)
|
|
|
|
|
PG_RETURN_NULL();
|
|
|
|
|
else
|
|
|
|
|
ereport(ERROR,
|
|
|
|
|
(errcode_for_file_access(),
|
|
|
|
|
errmsg("could not stat file \"%s\": %m", filename)));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* This record type had better match the output parameters declared for me
|
|
|
|
|
* in pg_proc.h.
|
|
|
|
|
*/
|
|
|
|
|
tupdesc = CreateTemplateTupleDesc(6, false);
|
|
|
|
|
TupleDescInitEntry(tupdesc, (AttrNumber) 1,
|
|
|
|
|
"size", INT8OID, -1, 0);
|
|
|
|
|
TupleDescInitEntry(tupdesc, (AttrNumber) 2,
|
|
|
|
|
"access", TIMESTAMPTZOID, -1, 0);
|
|
|
|
|
TupleDescInitEntry(tupdesc, (AttrNumber) 3,
|
|
|
|
|
"modification", TIMESTAMPTZOID, -1, 0);
|
|
|
|
|
TupleDescInitEntry(tupdesc, (AttrNumber) 4,
|
|
|
|
|
"change", TIMESTAMPTZOID, -1, 0);
|
|
|
|
|
TupleDescInitEntry(tupdesc, (AttrNumber) 5,
|
|
|
|
|
"creation", TIMESTAMPTZOID, -1, 0);
|
|
|
|
|
TupleDescInitEntry(tupdesc, (AttrNumber) 6,
|
|
|
|
|
"isdir", BOOLOID, -1, 0);
|
|
|
|
|
BlessTupleDesc(tupdesc);
|
|
|
|
|
|
|
|
|
|
memset(isnull, false, sizeof(isnull));
|
|
|
|
|
|
|
|
|
|
values[0] = Int64GetDatum((int64) fst.st_size);
|
|
|
|
|
values[1] = TimestampTzGetDatum(time_t_to_timestamptz(fst.st_atime));
|
|
|
|
|
values[2] = TimestampTzGetDatum(time_t_to_timestamptz(fst.st_mtime));
|
|
|
|
|
/* Unix has file status change time, while Win32 has creation time */
|
|
|
|
|
#if !defined(WIN32) && !defined(__CYGWIN__)
|
|
|
|
|
values[3] = TimestampTzGetDatum(time_t_to_timestamptz(fst.st_ctime));
|
|
|
|
|
isnull[4] = true;
|
|
|
|
|
#else
|
|
|
|
|
isnull[3] = true;
|
|
|
|
|
values[4] = TimestampTzGetDatum(time_t_to_timestamptz(fst.st_ctime));
|
|
|
|
|
#endif
|
Fix a number of places that were making file-type tests infelicitously.
The places that did, eg,
(statbuf.st_mode & S_IFMT) == S_IFDIR
were correct, but there is no good reason not to use S_ISDIR() instead,
especially when that's what the other 90% of our code does. The places
that did, eg,
(statbuf.st_mode & S_IFDIR)
were flat out *wrong* and would fail in various platform-specific ways,
eg a symlink could be mistaken for a regular file on most Unixen.
The actual impact of this is probably small, since the problem cases
seem to always involve symlinks or sockets, which are unlikely to be
found in the directories that PG code might be scanning. But it's
clearly trouble waiting to happen, so patch all the way back anyway.
(There seem to be no occurrences of the mistake in 7.4.)
18 years ago
|
|
|
values[5] = BoolGetDatum(S_ISDIR(fst.st_mode));
|
|
|
|
|
|
|
|
|
|
tuple = heap_form_tuple(tupdesc, values, isnull);
|
|
|
|
|
|
|
|
|
|
pfree(filename);
|
|
|
|
|
|
|
|
|
|
PG_RETURN_DATUM(HeapTupleGetDatum(tuple));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* stat a file (1 argument version)
|
|
|
|
|
*
|
|
|
|
|
* note: this wrapper is necessary to pass the sanity check in opr_sanity,
|
|
|
|
|
* which checks that all built-in functions that share the implementing C
|
|
|
|
|
* function take the same number of arguments
|
|
|
|
|
*/
|
|
|
|
|
Datum
|
|
|
|
|
pg_stat_file_1arg(PG_FUNCTION_ARGS)
|
|
|
|
|
{
|
|
|
|
|
return pg_stat_file(fcinfo);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* List a directory (returns the filenames only)
|
|
|
|
|
*/
|
|
|
|
|
Datum
|
|
|
|
|
pg_ls_dir(PG_FUNCTION_ARGS)
|
|
|
|
|
{
|
|
|
|
|
FuncCallContext *funcctx;
|
|
|
|
|
struct dirent *de;
|
|
|
|
|
directory_fctx *fctx;
|
|
|
|
|
MemoryContext oldcontext;
|
|
|
|
|
|
|
|
|
|
if (SRF_IS_FIRSTCALL())
|
|
|
|
|
{
|
|
|
|
|
bool missing_ok = false;
|
|
|
|
|
bool include_dot_dirs = false;
|
|
|
|
|
|
|
|
|
|
/* check the optional arguments */
|
|
|
|
|
if (PG_NARGS() == 3)
|
|
|
|
|
{
|
|
|
|
|
if (!PG_ARGISNULL(1))
|
|
|
|
|
missing_ok = PG_GETARG_BOOL(1);
|
|
|
|
|
if (!PG_ARGISNULL(2))
|
|
|
|
|
include_dot_dirs = PG_GETARG_BOOL(2);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
funcctx = SRF_FIRSTCALL_INIT();
|
|
|
|
|
oldcontext = MemoryContextSwitchTo(funcctx->multi_call_memory_ctx);
|
|
|
|
|
|
|
|
|
|
fctx = palloc(sizeof(directory_fctx));
|
|
|
|
|
fctx->location = convert_and_check_filename(PG_GETARG_TEXT_PP(0));
|
|
|
|
|
|
|
|
|
|
fctx->include_dot_dirs = include_dot_dirs;
|
|
|
|
|
fctx->dirdesc = AllocateDir(fctx->location);
|
|
|
|
|
|
|
|
|
|
if (!fctx->dirdesc)
|
|
|
|
|
{
|
|
|
|
|
if (missing_ok && errno == ENOENT)
|
|
|
|
|
{
|
|
|
|
|
MemoryContextSwitchTo(oldcontext);
|
|
|
|
|
SRF_RETURN_DONE(funcctx);
|
|
|
|
|
}
|
|
|
|
|
else
|
|
|
|
|
ereport(ERROR,
|
|
|
|
|
(errcode_for_file_access(),
|
|
|
|
|
errmsg("could not open directory \"%s\": %m",
|
|
|
|
|
fctx->location)));
|
|
|
|
|
}
|
|
|
|
|
funcctx->user_fctx = fctx;
|
|
|
|
|
MemoryContextSwitchTo(oldcontext);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
funcctx = SRF_PERCALL_SETUP();
|
|
|
|
|
fctx = (directory_fctx *) funcctx->user_fctx;
|
|
|
|
|
|
|
|
|
|
while ((de = ReadDir(fctx->dirdesc, fctx->location)) != NULL)
|
|
|
|
|
{
|
|
|
|
|
if (!fctx->include_dot_dirs &&
|
|
|
|
|
(strcmp(de->d_name, ".") == 0 ||
|
|
|
|
|
strcmp(de->d_name, "..") == 0))
|
|
|
|
|
continue;
|
|
|
|
|
|
|
|
|
|
SRF_RETURN_NEXT(funcctx, CStringGetTextDatum(de->d_name));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
FreeDir(fctx->dirdesc);
|
|
|
|
|
|
|
|
|
|
SRF_RETURN_DONE(funcctx);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* List a directory (1 argument version)
|
|
|
|
|
*
|
|
|
|
|
* note: this wrapper is necessary to pass the sanity check in opr_sanity,
|
|
|
|
|
* which checks that all built-in functions that share the implementing C
|
|
|
|
|
* function take the same number of arguments.
|
|
|
|
|
*/
|
|
|
|
|
Datum
|
|
|
|
|
pg_ls_dir_1arg(PG_FUNCTION_ARGS)
|
|
|
|
|
{
|
|
|
|
|
return pg_ls_dir(fcinfo);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/* Generic function to return a directory listing of files */
|
|
|
|
|
static Datum
|
|
|
|
|
pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir)
|
|
|
|
|
{
|
|
|
|
|
FuncCallContext *funcctx;
|
|
|
|
|
struct dirent *de;
|
|
|
|
|
directory_fctx *fctx;
|
|
|
|
|
|
|
|
|
|
if (SRF_IS_FIRSTCALL())
|
|
|
|
|
{
|
|
|
|
|
MemoryContext oldcontext;
|
|
|
|
|
TupleDesc tupdesc;
|
|
|
|
|
|
|
|
|
|
funcctx = SRF_FIRSTCALL_INIT();
|
|
|
|
|
oldcontext = MemoryContextSwitchTo(funcctx->multi_call_memory_ctx);
|
|
|
|
|
|
|
|
|
|
fctx = palloc(sizeof(directory_fctx));
|
|
|
|
|
|
|
|
|
|
tupdesc = CreateTemplateTupleDesc(3, false);
|
|
|
|
|
TupleDescInitEntry(tupdesc, (AttrNumber) 1, "name",
|
|
|
|
|
TEXTOID, -1, 0);
|
|
|
|
|
TupleDescInitEntry(tupdesc, (AttrNumber) 2, "size",
|
|
|
|
|
INT8OID, -1, 0);
|
|
|
|
|
TupleDescInitEntry(tupdesc, (AttrNumber) 3, "modification",
|
|
|
|
|
TIMESTAMPTZOID, -1, 0);
|
|
|
|
|
funcctx->tuple_desc = BlessTupleDesc(tupdesc);
|
|
|
|
|
|
|
|
|
|
fctx->location = pstrdup(dir);
|
|
|
|
|
fctx->dirdesc = AllocateDir(fctx->location);
|
|
|
|
|
|
|
|
|
|
if (!fctx->dirdesc)
|
|
|
|
|
ereport(ERROR,
|
|
|
|
|
(errcode_for_file_access(),
|
Clean up assorted messiness around AllocateDir() usage.
This patch fixes a couple of low-probability bugs that could lead to
reporting an irrelevant errno value (and hence possibly a wrong SQLSTATE)
concerning directory-open or file-open failures. It also fixes places
where we took shortcuts in reporting such errors, either by using elog
instead of ereport or by using ereport but forgetting to specify an
errcode. And it eliminates a lot of just plain redundant error-handling
code.
In service of all this, export fd.c's formerly-static function
ReadDirExtended, so that external callers can make use of the coding
pattern
dir = AllocateDir(path);
while ((de = ReadDirExtended(dir, path, LOG)) != NULL)
if they'd like to treat directory-open failures as mere LOG conditions
rather than errors. Also fix FreeDir to be a no-op if we reach it
with dir == NULL, as such a coding pattern would cause.
Then, remove code at many call sites that was throwing an error or log
message for AllocateDir failure, as ReadDir or ReadDirExtended can handle
that job just fine. Aside from being a net code savings, this gets rid of
a lot of not-quite-up-to-snuff reports, as mentioned above. (In some
places these changes result in replacing a custom error message such as
"could not open tablespace directory" with more generic wording "could not
open directory", but it was agreed that the custom wording buys little as
long as we report the directory name.) In some other call sites where we
can't just remove code, change the error reports to be fully
project-style-compliant.
Also reorder code in restoreTwoPhaseData that was acquiring a lock
between AllocateDir and ReadDir; in the unlikely but surely not
impossible case that LWLockAcquire changes errno, AllocateDir failures
would be misreported. There is no great value in opening the directory
before acquiring TwoPhaseStateLock, so just do it in the other order.
Also fix CheckXLogRemoved to guarantee that it preserves errno,
as quite a number of call sites are implicitly assuming. (Again,
it's unlikely but I think not impossible that errno could change
during a SpinLockAcquire. If so, this function was broken for its
own purposes as well as breaking callers.)
And change a few places that were using not-per-project-style messages,
such as "could not read directory" when "could not open directory" is
more correct.
Back-patch the exporting of ReadDirExtended, in case we have occasion
to back-patch some fix that makes use of it; it's not needed right now
but surely making it global is pretty harmless. Also back-patch the
restoreTwoPhaseData and CheckXLogRemoved fixes. The rest of this is
essentially cosmetic and need not get back-patched.
Michael Paquier, with a bit of additional work by me
Discussion: https://postgr.es/m/CAB7nPqRpOCxjiirHmebEFhXVTK7V5Jvw4bz82p7Oimtsm3TyZA@mail.gmail.com
8 years ago
|
|
|
errmsg("could not open directory \"%s\": %m",
|
|
|
|
|
fctx->location)));
|
|
|
|
|
|
|
|
|
|
funcctx->user_fctx = fctx;
|
|
|
|
|
MemoryContextSwitchTo(oldcontext);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
funcctx = SRF_PERCALL_SETUP();
|
|
|
|
|
fctx = (directory_fctx *) funcctx->user_fctx;
|
|
|
|
|
|
|
|
|
|
while ((de = ReadDir(fctx->dirdesc, fctx->location)) != NULL)
|
|
|
|
|
{
|
|
|
|
|
Datum values[3];
|
|
|
|
|
bool nulls[3];
|
|
|
|
|
char path[MAXPGPATH * 2];
|
|
|
|
|
struct stat attrib;
|
|
|
|
|
HeapTuple tuple;
|
|
|
|
|
|
|
|
|
|
/* Skip hidden files */
|
|
|
|
|
if (de->d_name[0] == '.')
|
|
|
|
|
continue;
|
|
|
|
|
|
|
|
|
|
/* Get the file info */
|
|
|
|
|
snprintf(path, sizeof(path), "%s/%s", fctx->location, de->d_name);
|
|
|
|
|
if (stat(path, &attrib) < 0)
|
|
|
|
|
ereport(ERROR,
|
|
|
|
|
(errcode_for_file_access(),
|
|
|
|
|
errmsg("could not stat directory \"%s\": %m", dir)));
|
|
|
|
|
|
|
|
|
|
/* Ignore anything but regular files */
|
|
|
|
|
if (!S_ISREG(attrib.st_mode))
|
|
|
|
|
continue;
|
|
|
|
|
|
|
|
|
|
values[0] = CStringGetTextDatum(de->d_name);
|
|
|
|
|
values[1] = Int64GetDatum((int64) attrib.st_size);
|
|
|
|
|
values[2] = TimestampTzGetDatum(time_t_to_timestamptz(attrib.st_mtime));
|
|
|
|
|
memset(nulls, 0, sizeof(nulls));
|
|
|
|
|
|
|
|
|
|
tuple = heap_form_tuple(funcctx->tuple_desc, values, nulls);
|
|
|
|
|
SRF_RETURN_NEXT(funcctx, HeapTupleGetDatum(tuple));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
FreeDir(fctx->dirdesc);
|
|
|
|
|
SRF_RETURN_DONE(funcctx);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/* Function to return the list of files in the log directory */
|
|
|
|
|
Datum
|
|
|
|
|
pg_ls_logdir(PG_FUNCTION_ARGS)
|
|
|
|
|
{
|
|
|
|
|
return pg_ls_dir_files(fcinfo, Log_directory);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/* Function to return the list of files in the WAL directory */
|
|
|
|
|
Datum
|
|
|
|
|
pg_ls_waldir(PG_FUNCTION_ARGS)
|
|
|
|
|
{
|
|
|
|
|
return pg_ls_dir_files(fcinfo, XLOGDIR);
|
|
|
|
|
}
|