From e3adc14a91c3ae80281b2d34855d98efdc7ecd7b Mon Sep 17 00:00:00 2001 From: Justin Pryzby Date: Mon, 9 Mar 2020 22:40:24 -0500 Subject: [PATCH v25 04/11] Add pg_ls_dir_metadata to list a dir with file metadata.. Generalize pg_ls_dir_files and retire pg_ls_dir Need catversion bumped? --- doc/src/sgml/func.sgml | 21 ++ src/backend/catalog/system_views.sql | 1 + src/backend/utils/adt/genfile.c | 231 +++++++++++-------- src/include/catalog/pg_proc.dat | 12 + src/test/regress/expected/misc_functions.out | 24 ++ src/test/regress/input/tablespace.source | 5 + src/test/regress/output/tablespace.source | 8 + src/test/regress/sql/misc_functions.sql | 11 + 8 files changed, 221 insertions(+), 92 deletions(-) diff --git a/doc/src/sgml/func.sgml b/doc/src/sgml/func.sgml index df29af6371..226923a134 100644 --- a/doc/src/sgml/func.sgml +++ b/doc/src/sgml/func.sgml @@ -25750,6 +25750,27 @@ SELECT pg_size_pretty(sum(pg_relation_size(relid))) AS total_size + + + + pg_ls_dir_metadata + + pg_ls_dir_metadata ( dirname text + , missing_ok boolean, + include_dot_dirs boolean ) + setof record + ( filename text, + size bigint, + modification timestamp with time zone ) + + + For each file in the specified directory, list the file and its + metadata. + Restricted to superusers by default, but other users can be granted + EXECUTE to run the function. + + + diff --git a/src/backend/catalog/system_views.sql b/src/backend/catalog/system_views.sql index b140c210bc..93d4f1e4a6 100644 --- a/src/backend/catalog/system_views.sql +++ b/src/backend/catalog/system_views.sql @@ -1506,6 +1506,7 @@ REVOKE EXECUTE ON FUNCTION pg_stat_file(text,boolean) FROM public; REVOKE EXECUTE ON FUNCTION pg_ls_dir(text) FROM public; REVOKE EXECUTE ON FUNCTION pg_ls_dir(text,boolean,boolean) FROM public; +REVOKE EXECUTE ON FUNCTION pg_ls_dir_metadata(text,boolean,boolean) FROM public; -- -- We also set up some things as accessible to standard roles. diff --git a/src/backend/utils/adt/genfile.c b/src/backend/utils/adt/genfile.c index 9f4927220b..7351615f8a 100644 --- a/src/backend/utils/adt/genfile.c +++ b/src/backend/utils/adt/genfile.c @@ -36,6 +36,21 @@ #include "utils/syscache.h" #include "utils/timestamp.h" +static Datum pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, int flags); + +#define LS_DIR_ISDIR (1<<0) /* Show column: isdir */ +#define LS_DIR_METADATA (1<<1) /* Show columns: mtime, size */ +#define LS_DIR_MISSING_OK (1<<2) /* Ignore ENOENT if the toplevel dir is missing */ +#define LS_DIR_SKIP_DOT_DIRS (1<<3) /* Do not show . or .. */ +#define LS_DIR_SKIP_HIDDEN (1<<4) /* Do not show anything begining with . */ +#define LS_DIR_SKIP_DIRS (1<<5) /* Do not show directories */ +#define LS_DIR_SKIP_SPECIAL (1<<6) /* Do not show special file types */ + +/* + * Shortcut for the historic behavior of the pg_ls_* functions (not including + * pg_ls_dir, which skips different files and doesn't show metadata). + */ +#define LS_DIR_HISTORIC (LS_DIR_SKIP_DIRS | LS_DIR_SKIP_HIDDEN | LS_DIR_SKIP_SPECIAL | LS_DIR_METADATA) /* * Convert a "text" filename argument to C string, and check it's allowable. @@ -449,6 +464,11 @@ pg_stat_file(PG_FUNCTION_ARGS) values[4] = TimestampTzGetDatum(time_t_to_timestamptz(fst.st_ctime)); #endif values[5] = BoolGetDatum(S_ISDIR(fst.st_mode)); +#ifdef WIN32 + /* Links should have isdir=false */ + if (pgwin32_is_junction(filename)) + values[5] = BoolGetDatum(false); +#endif tuple = heap_form_tuple(tupdesc, values, isnull); @@ -476,79 +496,9 @@ pg_stat_file_1arg(PG_FUNCTION_ARGS) Datum pg_ls_dir(PG_FUNCTION_ARGS) { - ReturnSetInfo *rsinfo = (ReturnSetInfo *) fcinfo->resultinfo; - char *location; - bool missing_ok = false; - bool include_dot_dirs = false; - bool randomAccess; - TupleDesc tupdesc; - Tuplestorestate *tupstore; - DIR *dirdesc; - struct dirent *de; - MemoryContext oldcontext; - - location = convert_and_check_filename(PG_GETARG_TEXT_PP(0)); - - /* 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); - } - - /* check to see if caller supports us returning a tuplestore */ - if (rsinfo == NULL || !IsA(rsinfo, ReturnSetInfo)) - ereport(ERROR, - (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), - errmsg("set-valued function called in context that cannot accept a set"))); - if (!(rsinfo->allowedModes & SFRM_Materialize)) - ereport(ERROR, - (errcode(ERRCODE_SYNTAX_ERROR), - errmsg("materialize mode required, but it is not allowed in this context"))); - - /* The tupdesc and tuplestore must be created in ecxt_per_query_memory */ - oldcontext = MemoryContextSwitchTo(rsinfo->econtext->ecxt_per_query_memory); - - tupdesc = CreateTemplateTupleDesc(1); - TupleDescInitEntry(tupdesc, (AttrNumber) 1, "pg_ls_dir", TEXTOID, -1, 0); - - randomAccess = (rsinfo->allowedModes & SFRM_Materialize_Random) != 0; - tupstore = tuplestore_begin_heap(randomAccess, false, work_mem); - rsinfo->returnMode = SFRM_Materialize; - rsinfo->setResult = tupstore; - rsinfo->setDesc = tupdesc; - - MemoryContextSwitchTo(oldcontext); - - dirdesc = AllocateDir(location); - if (!dirdesc) - { - /* Return empty tuplestore if appropriate */ - if (missing_ok && errno == ENOENT) - return (Datum) 0; - /* Otherwise, we can let ReadDir() throw the error */ - } - - while ((de = ReadDir(dirdesc, location)) != NULL) - { - Datum values[1]; - bool nulls[1]; - - if (!include_dot_dirs && - (strcmp(de->d_name, ".") == 0 || - strcmp(de->d_name, "..") == 0)) - continue; - - values[0] = CStringGetTextDatum(de->d_name); - nulls[0] = false; - - tuplestore_putvalues(tupstore, tupdesc, values, nulls); - } - - FreeDir(dirdesc); - return (Datum) 0; + text *filename_t = PG_GETARG_TEXT_PP(0); + char *filename = convert_and_check_filename(filename_t); + return pg_ls_dir_files(fcinfo, filename, LS_DIR_SKIP_DOT_DIRS); } /* @@ -561,17 +511,19 @@ pg_ls_dir(PG_FUNCTION_ARGS) Datum pg_ls_dir_1arg(PG_FUNCTION_ARGS) { - return pg_ls_dir(fcinfo); + text *filename_t = PG_GETARG_TEXT_PP(0); + char *filename = convert_and_check_filename(filename_t); + return pg_ls_dir_files(fcinfo, filename, LS_DIR_SKIP_DOT_DIRS); } /* * Generic function to return a directory listing of files. * - * If the directory isn't there, silently return an empty set if missing_ok. + * If the directory isn't there, silently return an empty set if MISSING_OK. * Other unreadable-directory cases throw an error. */ static Datum -pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) +pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, int flags) { ReturnSetInfo *rsinfo = (ReturnSetInfo *) fcinfo->resultinfo; bool randomAccess; @@ -580,6 +532,32 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) DIR *dirdesc; struct dirent *de; MemoryContext oldcontext; + TypeFuncClass tuptype ; + + /* isdir depends on metadata */ + Assert(!(flags&LS_DIR_ISDIR) || (flags&LS_DIR_METADATA)); + /* Unreasonable to show isdir and skip dirs */ + Assert(!(flags&LS_DIR_ISDIR) || !(flags&LS_DIR_SKIP_DIRS)); + + /* check the optional arguments */ + if (PG_NARGS() == 3) + { + if (!PG_ARGISNULL(1)) + { + if (PG_GETARG_BOOL(1)) + flags |= LS_DIR_MISSING_OK; + else + flags &= ~LS_DIR_MISSING_OK; + } + + if (!PG_ARGISNULL(2)) + { + if (PG_GETARG_BOOL(2)) + flags &= ~LS_DIR_SKIP_DOT_DIRS; + else + flags |= LS_DIR_SKIP_DOT_DIRS; + } + } /* check to see if caller supports us returning a tuplestore */ if (rsinfo == NULL || !IsA(rsinfo, ReturnSetInfo)) @@ -594,8 +572,20 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) /* The tupdesc and tuplestore must be created in ecxt_per_query_memory */ oldcontext = MemoryContextSwitchTo(rsinfo->econtext->ecxt_per_query_memory); - if (get_call_result_type(fcinfo, NULL, &tupdesc) != TYPEFUNC_COMPOSITE) - elog(ERROR, "return type must be a row type"); + tuptype = get_call_result_type(fcinfo, NULL, &tupdesc); + if (flags & LS_DIR_METADATA) + { + if (tuptype != TYPEFUNC_COMPOSITE) + elog(ERROR, "return type must be a row type"); + } + else + { + /* pg_ls_dir returns a simple scalar */ + if (tuptype != TYPEFUNC_SCALAR) + elog(ERROR, "return type must be a scalar type"); + tupdesc = CreateTemplateTupleDesc(1); + TupleDescInitEntry(tupdesc, (AttrNumber) 1, "column", TEXTOID, -1, 0); + } randomAccess = (rsinfo->allowedModes & SFRM_Materialize_Random) != 0; tupstore = tuplestore_begin_heap(randomAccess, false, work_mem); @@ -614,20 +604,27 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) if (!dirdesc) { /* Return empty tuplestore if appropriate */ - if (missing_ok && errno == ENOENT) + if (flags & LS_DIR_MISSING_OK && errno == ENOENT) return (Datum) 0; /* Otherwise, we can let ReadDir() throw the error */ } while ((de = ReadDir(dirdesc, dir)) != NULL) { - Datum values[3]; - bool nulls[3]; + Datum values[4]; + bool nulls[4]; char path[MAXPGPATH * 2]; struct stat attrib; - /* Skip hidden files */ - if (de->d_name[0] == '.') + /* Skip dot dirs? */ + if (flags & LS_DIR_SKIP_DOT_DIRS && + (strcmp(de->d_name, ".") == 0 || + strcmp(de->d_name, "..") == 0)) + continue; + + /* Skip hidden files? */ + if (flags & LS_DIR_SKIP_HIDDEN && + de->d_name[0] == '.') continue; /* Get the file info */ @@ -642,13 +639,34 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) errmsg("could not stat file \"%s\": %m", path))); } - /* Ignore anything but regular files */ - if (!S_ISREG(attrib.st_mode)) - continue; + /* Skip dirs or special files? */ + if (S_ISDIR(attrib.st_mode)) + { + if (flags & LS_DIR_SKIP_DIRS) + continue; + } + else if (!S_ISREG(attrib.st_mode)) + { + if (flags & LS_DIR_SKIP_SPECIAL) + continue; + } values[0] = CStringGetTextDatum(de->d_name); - values[1] = Int64GetDatum((int64) attrib.st_size); - values[2] = TimestampTzGetDatum(time_t_to_timestamptz(attrib.st_mtime)); + if (flags & LS_DIR_METADATA) + { + values[1] = Int64GetDatum((int64) attrib.st_size); + values[2] = TimestampTzGetDatum(time_t_to_timestamptz(attrib.st_mtime)); + if (flags & LS_DIR_ISDIR) + { + values[3] = BoolGetDatum(S_ISDIR(attrib.st_mode)); +#ifdef WIN32 + /* Links should have isdir=false */ + if (pgwin32_is_junction(path)) + values[3] = BoolGetDatum(false); +#endif + } + } + memset(nulls, 0, sizeof(nulls)); tuplestore_putvalues(tupstore, tupdesc, values, nulls); @@ -662,14 +680,14 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) Datum pg_ls_logdir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, Log_directory, false); + return pg_ls_dir_files(fcinfo, Log_directory, LS_DIR_HISTORIC); } /* 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, false); + return pg_ls_dir_files(fcinfo, XLOGDIR, LS_DIR_HISTORIC); } /* @@ -687,7 +705,8 @@ pg_ls_tmpdir(FunctionCallInfo fcinfo, Oid tblspc) tblspc))); TempTablespacePath(path, tblspc); - return pg_ls_dir_files(fcinfo, path, true); + return pg_ls_dir_files(fcinfo, path, + LS_DIR_HISTORIC | LS_DIR_MISSING_OK); } /* @@ -716,5 +735,33 @@ pg_ls_tmpdir_1arg(PG_FUNCTION_ARGS) Datum pg_ls_archive_statusdir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, XLOGDIR "/archive_status", true); + return pg_ls_dir_files(fcinfo, XLOGDIR "/archive_status", + LS_DIR_HISTORIC | LS_DIR_MISSING_OK); +} + +/* + * Return the list of files and metadata in an arbitrary directory. + */ +Datum +pg_ls_dir_metadata(PG_FUNCTION_ARGS) +{ + char *dirname = convert_and_check_filename(PG_GETARG_TEXT_PP(0)); + + return pg_ls_dir_files(fcinfo, dirname, + LS_DIR_METADATA | LS_DIR_SKIP_SPECIAL | LS_DIR_ISDIR); +} + +/* + * Return the list of files and metadata in an arbitrary directory. + * 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_metadata_1arg(PG_FUNCTION_ARGS) +{ + char *dirname = convert_and_check_filename(PG_GETARG_TEXT_PP(0)); + + return pg_ls_dir_files(fcinfo, dirname, + LS_DIR_METADATA | LS_DIR_SKIP_SPECIAL | LS_DIR_ISDIR); } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index fc2202b843..8e88c549d9 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -10976,6 +10976,18 @@ proallargtypes => '{oid,text,int8,timestamptz}', proargmodes => '{i,o,o,o}', proargnames => '{tablespace,name,size,modification}', prosrc => 'pg_ls_tmpdir_1arg' }, +{ oid => '9979', descr => 'list directory with metadata', + proname => 'pg_ls_dir_metadata', procost => '10', prorows => '20', proretset => 't', + provolatile => 'v', prorettype => 'record', proargtypes => 'text bool bool', + proallargtypes => '{text,bool,bool,text,int8,timestamptz,bool}', proargmodes => '{i,i,i,o,o,o,o}', + proargnames => '{dirname,missing_ok,include_dot_dirs,filename,size,modification,isdir}', + prosrc => 'pg_ls_dir_metadata' }, +{ oid => '9980', descr => 'list directory with metadata', + proname => 'pg_ls_dir_metadata', procost => '10', prorows => '20', proretset => 't', + provolatile => 'v', prorettype => 'record', proargtypes => 'text', + proallargtypes => '{text,text,int8,timestamptz,bool}', proargmodes => '{i,o,o,o,o}', + proargnames => '{dirname,filename,size,modification,isdir}', + prosrc => 'pg_ls_dir_metadata_1arg' }, # hash partitioning constraint function { oid => '5028', descr => 'hash partition CHECK constraint', diff --git a/src/test/regress/expected/misc_functions.out b/src/test/regress/expected/misc_functions.out index edbfd9abc1..fd7c3c791f 100644 --- a/src/test/regress/expected/misc_functions.out +++ b/src/test/regress/expected/misc_functions.out @@ -225,6 +225,30 @@ select * from pg_stat_file('.') limit 0; ------+--------+--------------+--------+----------+------- (0 rows) +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +select * from pg_ls_tmpdir() where name='Does not exist'; + name | size | modification +------+------+-------------- +(0 rows) + +select filename, isdir from pg_ls_dir_metadata('.') where filename='.'; + filename | isdir +----------+------- + . | t +(1 row) + +select filename, isdir from pg_ls_dir_metadata('.', false, false) where filename='.'; -- include_dot_dirs=false + filename | isdir +----------+------- +(0 rows) + +-- Check that expected columns are present +select * from pg_ls_dir_metadata('.') limit 0; + filename | size | modification | isdir +----------+------+--------------+------- +(0 rows) + -- -- Test adding a support function to a subject function -- diff --git a/src/test/regress/input/tablespace.source b/src/test/regress/input/tablespace.source index a5f61a35dc..0b9cfe615e 100644 --- a/src/test/regress/input/tablespace.source +++ b/src/test/regress/input/tablespace.source @@ -11,6 +11,11 @@ DROP TABLESPACE regress_tblspacewith; -- create a tablespace we can use CREATE TABLESPACE regress_tblspace LOCATION '@testtablespace@'; +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +-- The query is written to ERROR if the tablespace doesn't exist, rather than silently failing to call pg_ls_tmpdir() +SELECT c.* FROM (SELECT oid FROM pg_tablespace b WHERE b.spcname='regress_tblspace' UNION SELECT 0 ORDER BY 1 DESC LIMIT 1) AS b , pg_ls_tmpdir(oid) AS c WHERE c.name='Does not exist'; + -- try setting and resetting some properties for the new tablespace ALTER TABLESPACE regress_tblspace SET (random_page_cost = 1.0, seq_page_cost = 1.1); ALTER TABLESPACE regress_tblspace SET (some_nonexistent_parameter = true); -- fail diff --git a/src/test/regress/output/tablespace.source b/src/test/regress/output/tablespace.source index 162b591b31..a42714bf40 100644 --- a/src/test/regress/output/tablespace.source +++ b/src/test/regress/output/tablespace.source @@ -13,6 +13,14 @@ SELECT spcoptions FROM pg_tablespace WHERE spcname = 'regress_tblspacewith'; DROP TABLESPACE regress_tblspacewith; -- create a tablespace we can use CREATE TABLESPACE regress_tblspace LOCATION '@testtablespace@'; +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +-- The query is written to ERROR if the tablespace doesn't exist, rather than silently failing to call pg_ls_tmpdir() +SELECT c.* FROM (SELECT oid FROM pg_tablespace b WHERE b.spcname='regress_tblspace' UNION SELECT 0 ORDER BY 1 DESC LIMIT 1) AS b , pg_ls_tmpdir(oid) AS c WHERE c.name='Does not exist'; + name | size | modification +------+------+-------------- +(0 rows) + -- try setting and resetting some properties for the new tablespace ALTER TABLESPACE regress_tblspace SET (random_page_cost = 1.0, seq_page_cost = 1.1); ALTER TABLESPACE regress_tblspace SET (some_nonexistent_parameter = true); -- fail diff --git a/src/test/regress/sql/misc_functions.sql b/src/test/regress/sql/misc_functions.sql index b32a3a4b74..64d9d70874 100644 --- a/src/test/regress/sql/misc_functions.sql +++ b/src/test/regress/sql/misc_functions.sql @@ -68,6 +68,17 @@ select pg_ls_dir('does not exist'); -- fails with missingok=false -- Check that expected columns are present select * from pg_stat_file('.') limit 0; +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +select * from pg_ls_tmpdir() where name='Does not exist'; + +select filename, isdir from pg_ls_dir_metadata('.') where filename='.'; + +select filename, isdir from pg_ls_dir_metadata('.', false, false) where filename='.'; -- include_dot_dirs=false + +-- Check that expected columns are present +select * from pg_ls_dir_metadata('.') limit 0; + -- -- Test adding a support function to a subject function -- -- 2.17.0