-
Notifications
You must be signed in to change notification settings - Fork 27
/
ruleutils_13.c
7844 lines (7002 loc) · 225 KB
/
ruleutils_13.c
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
/*-------------------------------------------------------------------------
*
* ruleutils_13.c
* Functions to convert stored expressions/querytrees back to
* source text
*
* Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group
* Portions Copyright (c) 1994, Regents of the University of California
*
*
* Part of src/backend/utils/adt/ruleutils.c in PostgreSQL 13 core
*
*-------------------------------------------------------------------------
*/
#include "postgres.h"
#include "access/relation.h"
#include "catalog/pg_aggregate.h"
#include "catalog/pg_opclass.h"
#include "catalog/pg_operator.h"
#include "catalog/pg_proc.h"
#include "commands/defrem.h"
#include "common/keywords.h"
#include "funcapi.h"
#include "mb/pg_wchar.h"
#include "miscadmin.h"
#include "nodes/nodeFuncs.h"
#include "nodes/pathnodes.h"
#include "optimizer/optimizer.h"
#include "parser/parse_agg.h"
#include "parser/parse_func.h"
#include "parser/parse_oper.h"
#include "parser/parse_relation.h"
#include "parser/parser.h"
#include "parser/parsetree.h"
#include "rewrite/rewriteHandler.h"
#include "utils/builtins.h"
#include "utils/fmgroids.h"
#include "utils/hsearch.h"
#include "utils/lsyscache.h"
#include "utils/rel.h"
#include "utils/ruleutils.h"
#include "utils/syscache.h"
#include "utils/typcache.h"
#include "utils/xml.h"
/* ----------
* Pretty formatting constants
* ----------
*/
/* Indent counts */
#define PRETTYINDENT_STD 8
#define PRETTYINDENT_JOIN 4
#define PRETTYINDENT_VAR 4
#define PRETTYINDENT_LIMIT 40 /* wrap limit */
/* Pretty flags */
#define PRETTYFLAG_PAREN 0x0001
#define PRETTYFLAG_INDENT 0x0002
#define PRETTYFLAG_SCHEMA 0x0004
/* Default line length for pretty-print wrapping: 0 means wrap always */
#define WRAP_COLUMN_DEFAULT 0
/* macros to test if pretty action needed */
#define PRETTY_PAREN(context) ((context)->prettyFlags & PRETTYFLAG_PAREN)
#define PRETTY_INDENT(context) ((context)->prettyFlags & PRETTYFLAG_INDENT)
#define PRETTY_SCHEMA(context) ((context)->prettyFlags & PRETTYFLAG_SCHEMA)
/* ----------
* Local data types
* ----------
*/
/* Context info needed for invoking a recursive querytree display routine */
typedef struct
{
StringInfo buf; /* output buffer to append to */
List *namespaces; /* List of deparse_namespace nodes */
List *windowClause; /* Current query level's WINDOW clause */
List *windowTList; /* targetlist for resolving WINDOW clause */
int prettyFlags; /* enabling of pretty-print functions */
int wrapColumn; /* max line length, or -1 for no limit */
int indentLevel; /* current indent level for pretty-print */
bool varprefix; /* true to print prefixes on Vars */
ParseExprKind special_exprkind; /* set only for exprkinds needing special
* handling */
Bitmapset *appendparents; /* if not null, map child Vars of these relids
* back to the parent rel */
} deparse_context;
/*
* Each level of query context around a subtree needs a level of Var namespace.
* A Var having varlevelsup=N refers to the N'th item (counting from 0) in
* the current context's namespaces list.
*
* rtable is the list of actual RTEs from the Query or PlannedStmt.
* rtable_names holds the alias name to be used for each RTE (either a C
* string, or NULL for nameless RTEs such as unnamed joins).
* rtable_columns holds the column alias names to be used for each RTE.
*
* subplans is a list of Plan trees for SubPlans and CTEs (it's only used
* in the PlannedStmt case).
* ctes is a list of CommonTableExpr nodes (only used in the Query case).
* appendrels, if not null (it's only used in the PlannedStmt case), is an
* array of AppendRelInfo nodes, indexed by child relid. We use that to map
* child-table Vars to their inheritance parents.
*
* In some cases we need to make names of merged JOIN USING columns unique
* across the whole query, not only per-RTE. If so, unique_using is true
* and using_names is a list of C strings representing names already assigned
* to USING columns.
*
* When deparsing plan trees, there is always just a single item in the
* deparse_namespace list (since a plan tree never contains Vars with
* varlevelsup > 0). We store the Plan node that is the immediate
* parent of the expression to be deparsed, as well as a list of that
* Plan's ancestors. In addition, we store its outer and inner subplan nodes,
* as well as their targetlists, and the index tlist if the current plan node
* might contain INDEX_VAR Vars. (These fields could be derived on-the-fly
* from the current Plan node, but it seems notationally clearer to set them
* up as separate fields.)
*/
typedef struct
{
List *rtable; /* List of RangeTblEntry nodes */
List *rtable_names; /* Parallel list of names for RTEs */
List *rtable_columns; /* Parallel list of deparse_columns structs */
List *subplans; /* List of Plan trees for SubPlans */
List *ctes; /* List of CommonTableExpr nodes */
AppendRelInfo **appendrels; /* Array of AppendRelInfo nodes, or NULL */
/* Workspace for column alias assignment: */
bool unique_using; /* Are we making USING names globally unique */
List *using_names; /* List of assigned names for USING columns */
/* Remaining fields are used only when deparsing a Plan tree: */
Plan *plan; /* immediate parent of current expression */
List *ancestors; /* ancestors of plan */
Plan *outer_plan; /* outer subnode, or NULL if none */
Plan *inner_plan; /* inner subnode, or NULL if none */
List *outer_tlist; /* referent for OUTER_VAR Vars */
List *inner_tlist; /* referent for INNER_VAR Vars */
List *index_tlist; /* referent for INDEX_VAR Vars */
} deparse_namespace;
/*
* Per-relation data about column alias names.
*
* Selecting aliases is unreasonably complicated because of the need to dump
* rules/views whose underlying tables may have had columns added, deleted, or
* renamed since the query was parsed. We must nonetheless print the rule/view
* in a form that can be reloaded and will produce the same results as before.
*
* For each RTE used in the query, we must assign column aliases that are
* unique within that RTE. SQL does not require this of the original query,
* but due to factors such as *-expansion we need to be able to uniquely
* reference every column in a decompiled query. As long as we qualify all
* column references, per-RTE uniqueness is sufficient for that.
*
* However, we can't ensure per-column name uniqueness for unnamed join RTEs,
* since they just inherit column names from their input RTEs, and we can't
* rename the columns at the join level. Most of the time this isn't an issue
* because we don't need to reference the join's output columns as such; we
* can reference the input columns instead. That approach can fail for merged
* JOIN USING columns, however, so when we have one of those in an unnamed
* join, we have to make that column's alias globally unique across the whole
* query to ensure it can be referenced unambiguously.
*
* Another problem is that a JOIN USING clause requires the columns to be
* merged to have the same aliases in both input RTEs, and that no other
* columns in those RTEs or their children conflict with the USING names.
* To handle that, we do USING-column alias assignment in a recursive
* traversal of the query's jointree. When descending through a JOIN with
* USING, we preassign the USING column names to the child columns, overriding
* other rules for column alias assignment. We also mark each RTE with a list
* of all USING column names selected for joins containing that RTE, so that
* when we assign other columns' aliases later, we can avoid conflicts.
*
* Another problem is that if a JOIN's input tables have had columns added or
* deleted since the query was parsed, we must generate a column alias list
* for the join that matches the current set of input columns --- otherwise, a
* change in the number of columns in the left input would throw off matching
* of aliases to columns of the right input. Thus, positions in the printable
* column alias list are not necessarily one-for-one with varattnos of the
* JOIN, so we need a separate new_colnames[] array for printing purposes.
*/
typedef struct
{
/*
* colnames is an array containing column aliases to use for columns that
* existed when the query was parsed. Dropped columns have NULL entries.
* This array can be directly indexed by varattno to get a Var's name.
*
* Non-NULL entries are guaranteed unique within the RTE, *except* when
* this is for an unnamed JOIN RTE. In that case we merely copy up names
* from the two input RTEs.
*
* During the recursive descent in set_using_names(), forcible assignment
* of a child RTE's column name is represented by pre-setting that element
* of the child's colnames array. So at that stage, NULL entries in this
* array just mean that no name has been preassigned, not necessarily that
* the column is dropped.
*/
int num_cols; /* length of colnames[] array */
char **colnames; /* array of C strings and NULLs */
/*
* new_colnames is an array containing column aliases to use for columns
* that would exist if the query was re-parsed against the current
* definitions of its base tables. This is what to print as the column
* alias list for the RTE. This array does not include dropped columns,
* but it will include columns added since original parsing. Indexes in
* it therefore have little to do with current varattno values. As above,
* entries are unique unless this is for an unnamed JOIN RTE. (In such an
* RTE, we never actually print this array, but we must compute it anyway
* for possible use in computing column names of upper joins.) The
* parallel array is_new_col marks which of these columns are new since
* original parsing. Entries with is_new_col false must match the
* non-NULL colnames entries one-for-one.
*/
int num_new_cols; /* length of new_colnames[] array */
char **new_colnames; /* array of C strings */
bool *is_new_col; /* array of bool flags */
/* This flag tells whether we should actually print a column alias list */
bool printaliases;
/* This list has all names used as USING names in joins above this RTE */
List *parentUsing; /* names assigned to parent merged columns */
/*
* If this struct is for a JOIN RTE, we fill these fields during the
* set_using_names() pass to describe its relationship to its child RTEs.
*
* leftattnos and rightattnos are arrays with one entry per existing
* output column of the join (hence, indexable by join varattno). For a
* simple reference to a column of the left child, leftattnos[i] is the
* child RTE's attno and rightattnos[i] is zero; and conversely for a
* column of the right child. But for merged columns produced by JOIN
* USING/NATURAL JOIN, both leftattnos[i] and rightattnos[i] are nonzero.
* Note that a simple reference might be to a child RTE column that's been
* dropped; but that's OK since the column could not be used in the query.
*
* If it's a JOIN USING, usingNames holds the alias names selected for the
* merged columns (these might be different from the original USING list,
* if we had to modify names to achieve uniqueness).
*/
int leftrti; /* rangetable index of left child */
int rightrti; /* rangetable index of right child */
int *leftattnos; /* left-child varattnos of join cols, or 0 */
int *rightattnos; /* right-child varattnos of join cols, or 0 */
List *usingNames; /* names assigned to merged columns */
} deparse_columns;
/* This macro is analogous to rt_fetch(), but for deparse_columns structs */
#define deparse_columns_fetch(rangetable_index, dpns) \
((deparse_columns *) list_nth((dpns)->rtable_columns, (rangetable_index)-1))
/*
* Entry in set_rtable_names' hash table
*/
typedef struct
{
char name[NAMEDATALEN]; /* Hash key --- must be first */
int counter; /* Largest addition used so far for name */
} NameHashEntry;
/* Callback signature for resolve_special_varno() */
typedef void (*rsv_callback) (Node *node, deparse_context *context,
void *callback_arg);
/* ----------
* Local functions
*
* Most of these functions used to use fixed-size buffers to build their
* results. Now, they take an (already initialized) StringInfo object
* as a parameter, and append their text output to its contents.
* ----------
*/
static void set_rtable_names(deparse_namespace *dpns, List *parent_namespaces,
Bitmapset *rels_used);
static void set_deparse_for_query(deparse_namespace *dpns, Query *query,
List *parent_namespaces);
static bool has_dangerous_join_using(deparse_namespace *dpns, Node *jtnode);
static void set_using_names(deparse_namespace *dpns, Node *jtnode,
List *parentUsing);
static void set_relation_column_names(deparse_namespace *dpns,
RangeTblEntry *rte,
deparse_columns *colinfo);
static void set_join_column_names(deparse_namespace *dpns, RangeTblEntry *rte,
deparse_columns *colinfo);
static bool colname_is_unique(const char *colname, deparse_namespace *dpns,
deparse_columns *colinfo);
static char *make_colname_unique(char *colname, deparse_namespace *dpns,
deparse_columns *colinfo);
static void expand_colnames_array_to(deparse_columns *colinfo, int n);
static void identify_join_columns(JoinExpr *j, RangeTblEntry *jrte,
deparse_columns *colinfo);
static char *get_rtable_name(int rtindex, deparse_context *context);
static void set_deparse_plan(deparse_namespace *dpns, Plan *plan);
static void push_child_plan(deparse_namespace *dpns, Plan *plan,
deparse_namespace *save_dpns);
static void pop_child_plan(deparse_namespace *dpns,
deparse_namespace *save_dpns);
static void push_ancestor_plan(deparse_namespace *dpns, ListCell *ancestor_cell,
deparse_namespace *save_dpns);
static void pop_ancestor_plan(deparse_namespace *dpns,
deparse_namespace *save_dpns);
static void get_query_def(Query *query, StringInfo buf, List *parentnamespace,
TupleDesc resultDesc, bool colNamesVisible,
int prettyFlags, int wrapColumn, int startIndent);
static void get_values_def(List *values_lists, deparse_context *context);
static void get_with_clause(Query *query, deparse_context *context);
static void get_select_query_def(Query *query, deparse_context *context,
TupleDesc resultDesc, bool colNamesVisible);
static void get_insert_query_def(Query *query, deparse_context *context,
bool colNamesVisible);
static void get_update_query_def(Query *query, deparse_context *context,
bool colNamesVisible);
static void get_update_query_targetlist_def(Query *query, List *targetList,
deparse_context *context,
RangeTblEntry *rte);
static void get_delete_query_def(Query *query, deparse_context *context,
bool colNamesVisible);
static void get_utility_query_def(Query *query, deparse_context *context);
static void get_basic_select_query(Query *query, deparse_context *context,
TupleDesc resultDesc, bool colNamesVisible);
static void get_target_list(List *targetList, deparse_context *context,
TupleDesc resultDesc, bool colNamesVisible);
static void get_setop_query(Node *setOp, Query *query,
deparse_context *context,
TupleDesc resultDesc, bool colNamesVisible);
static Node *get_rule_sortgroupclause(Index ref, List *tlist,
bool force_colno,
deparse_context *context);
static void get_rule_groupingset(GroupingSet *gset, List *targetlist,
bool omit_parens, deparse_context *context);
static void get_rule_orderby(List *orderList, List *targetList,
bool force_colno, deparse_context *context);
static void get_rule_windowclause(Query *query, deparse_context *context);
static void get_rule_windowspec(WindowClause *wc, List *targetList,
deparse_context *context);
static char *get_variable(Var *var, int levelsup, bool istoplevel,
deparse_context *context);
static void get_special_variable(Node *node, deparse_context *context,
void *callback_arg);
static void resolve_special_varno(Node *node, deparse_context *context,
rsv_callback callback, void *callback_arg);
static Node *find_param_referent(Param *param, deparse_context *context,
deparse_namespace **dpns_p, ListCell **ancestor_cell_p);
static void get_parameter(Param *param, deparse_context *context);
static const char *get_simple_binary_op_name(OpExpr *expr);
static bool isSimpleNode(Node *node, Node *parentNode, int prettyFlags);
static void appendContextKeyword(deparse_context *context, const char *str,
int indentBefore, int indentAfter, int indentPlus);
static void removeStringInfoSpaces(StringInfo str);
static void get_rule_expr(Node *node, deparse_context *context,
bool showimplicit);
static void get_rule_expr_toplevel(Node *node, deparse_context *context,
bool showimplicit);
static void get_rule_list_toplevel(List *lst, deparse_context *context,
bool showimplicit);
static void get_rule_expr_funccall(Node *node, deparse_context *context,
bool showimplicit);
static bool looks_like_function(Node *node);
static void get_oper_expr(OpExpr *expr, deparse_context *context);
static void get_func_expr(FuncExpr *expr, deparse_context *context,
bool showimplicit);
static void get_agg_expr(Aggref *aggref, deparse_context *context,
Aggref *original_aggref);
static void get_agg_combine_expr(Node *node, deparse_context *context,
void *callback_arg);
static void get_windowfunc_expr(WindowFunc *wfunc, deparse_context *context);
static void get_coercion_expr(Node *arg, deparse_context *context,
Oid resulttype, int32 resulttypmod,
Node *parentNode);
static void get_const_expr(Const *constval, deparse_context *context,
int showtype);
static void get_const_collation(Const *constval, deparse_context *context);
static void simple_quote_literal(StringInfo buf, const char *val);
static void get_sublink_expr(SubLink *sublink, deparse_context *context);
static void get_tablefunc(TableFunc *tf, deparse_context *context,
bool showimplicit);
static void get_from_clause(Query *query, const char *prefix,
deparse_context *context);
static void get_from_clause_item(Node *jtnode, Query *query,
deparse_context *context);
static void get_column_alias_list(deparse_columns *colinfo,
deparse_context *context);
static void get_from_clause_coldeflist(RangeTblFunction *rtfunc,
deparse_columns *colinfo,
deparse_context *context);
static void get_tablesample_def(TableSampleClause *tablesample,
deparse_context *context);
static void get_opclass_name(Oid opclass, Oid actual_datatype,
StringInfo buf);
static Node *processIndirection(Node *node, deparse_context *context);
static void printSubscripts(SubscriptingRef *sbsref, deparse_context *context);
static char *get_relation_name(Oid relid);
static char *generate_relation_name(Oid relid, List *namespaces);
static char *generate_function_name(Oid funcid, int nargs,
List *argnames, Oid *argtypes,
bool has_variadic, bool *use_variadic_p,
ParseExprKind special_exprkind);
static char *generate_operator_name(Oid operid, Oid arg1, Oid arg2);
#define only_marker(rte) ((rte)->inh ? "" : "ONLY ")
/*
* set_rtable_names: select RTE aliases to be used in printing a query
*
* We fill in dpns->rtable_names with a list of names that is one-for-one with
* the already-filled dpns->rtable list. Each RTE name is unique among those
* in the new namespace plus any ancestor namespaces listed in
* parent_namespaces.
*
* If rels_used isn't NULL, only RTE indexes listed in it are given aliases.
*
* Note that this function is only concerned with relation names, not column
* names.
*/
static void
set_rtable_names(deparse_namespace *dpns, List *parent_namespaces,
Bitmapset *rels_used)
{
HASHCTL hash_ctl;
HTAB *names_hash;
NameHashEntry *hentry;
bool found;
int rtindex;
ListCell *lc;
dpns->rtable_names = NIL;
/* nothing more to do if empty rtable */
if (dpns->rtable == NIL)
return;
/*
* We use a hash table to hold known names, so that this process is O(N)
* not O(N^2) for N names.
*/
MemSet(&hash_ctl, 0, sizeof(hash_ctl));
hash_ctl.keysize = NAMEDATALEN;
hash_ctl.entrysize = sizeof(NameHashEntry);
hash_ctl.hcxt = CurrentMemoryContext;
names_hash = hash_create("set_rtable_names names",
list_length(dpns->rtable),
&hash_ctl,
HASH_ELEM | HASH_CONTEXT);
/* Preload the hash table with names appearing in parent_namespaces */
foreach(lc, parent_namespaces)
{
deparse_namespace *olddpns = (deparse_namespace *) lfirst(lc);
ListCell *lc2;
foreach(lc2, olddpns->rtable_names)
{
char *oldname = (char *) lfirst(lc2);
if (oldname == NULL)
continue;
hentry = (NameHashEntry *) hash_search(names_hash,
oldname,
HASH_ENTER,
&found);
/* we do not complain about duplicate names in parent namespaces */
hentry->counter = 0;
}
}
/* Now we can scan the rtable */
rtindex = 1;
foreach(lc, dpns->rtable)
{
RangeTblEntry *rte = (RangeTblEntry *) lfirst(lc);
char *refname;
/* Just in case this takes an unreasonable amount of time ... */
CHECK_FOR_INTERRUPTS();
if (rels_used && !bms_is_member(rtindex, rels_used))
{
/* Ignore unreferenced RTE */
refname = NULL;
}
else if (rte->alias)
{
/* If RTE has a user-defined alias, prefer that */
refname = rte->alias->aliasname;
}
else if (rte->rtekind == RTE_RELATION)
{
/* Use the current actual name of the relation */
refname = get_rel_name(rte->relid);
}
else if (rte->rtekind == RTE_JOIN)
{
/* Unnamed join has no refname */
refname = NULL;
}
else
{
/* Otherwise use whatever the parser assigned */
refname = rte->eref->aliasname;
}
/*
* If the selected name isn't unique, append digits to make it so, and
* make a new hash entry for it once we've got a unique name. For a
* very long input name, we might have to truncate to stay within
* NAMEDATALEN.
*/
if (refname)
{
hentry = (NameHashEntry *) hash_search(names_hash,
refname,
HASH_ENTER,
&found);
if (found)
{
/* Name already in use, must choose a new one */
int refnamelen = strlen(refname);
char *modname = (char *) palloc(refnamelen + 16);
NameHashEntry *hentry2;
do
{
hentry->counter++;
for (;;)
{
/*
* We avoid using %.*s here because it can misbehave
* if the data is not valid in what libc thinks is the
* prevailing encoding.
*/
memcpy(modname, refname, refnamelen);
sprintf(modname + refnamelen, "_%d", hentry->counter);
if (strlen(modname) < NAMEDATALEN)
break;
/* drop chars from refname to keep all the digits */
refnamelen = pg_mbcliplen(refname, refnamelen,
refnamelen - 1);
}
hentry2 = (NameHashEntry *) hash_search(names_hash,
modname,
HASH_ENTER,
&found);
} while (found);
hentry2->counter = 0; /* init new hash entry */
refname = modname;
}
else
{
/* Name not previously used, need only initialize hentry */
hentry->counter = 0;
}
}
dpns->rtable_names = lappend(dpns->rtable_names, refname);
rtindex++;
}
hash_destroy(names_hash);
}
/*
* set_deparse_for_query: set up deparse_namespace for deparsing a Query tree
*
* For convenience, this is defined to initialize the deparse_namespace struct
* from scratch.
*/
static void
set_deparse_for_query(deparse_namespace *dpns, Query *query,
List *parent_namespaces)
{
ListCell *lc;
ListCell *lc2;
/* Initialize *dpns and fill rtable/ctes links */
memset(dpns, 0, sizeof(deparse_namespace));
dpns->rtable = query->rtable;
dpns->subplans = NIL;
dpns->ctes = query->cteList;
dpns->appendrels = NULL;
/* Assign a unique relation alias to each RTE */
set_rtable_names(dpns, parent_namespaces, NULL);
/* Initialize dpns->rtable_columns to contain zeroed structs */
dpns->rtable_columns = NIL;
while (list_length(dpns->rtable_columns) < list_length(dpns->rtable))
dpns->rtable_columns = lappend(dpns->rtable_columns,
palloc0(sizeof(deparse_columns)));
/* If it's a utility query, it won't have a jointree */
if (query->jointree)
{
/* Detect whether global uniqueness of USING names is needed */
dpns->unique_using =
has_dangerous_join_using(dpns, (Node *) query->jointree);
/*
* Select names for columns merged by USING, via a recursive pass over
* the query jointree.
*/
set_using_names(dpns, (Node *) query->jointree, NIL);
}
/*
* Now assign remaining column aliases for each RTE. We do this in a
* linear scan of the rtable, so as to process RTEs whether or not they
* are in the jointree (we mustn't miss NEW.*, INSERT target relations,
* etc). JOIN RTEs must be processed after their children, but this is
* okay because they appear later in the rtable list than their children
* (cf Asserts in identify_join_columns()).
*/
forboth(lc, dpns->rtable, lc2, dpns->rtable_columns)
{
RangeTblEntry *rte = (RangeTblEntry *) lfirst(lc);
deparse_columns *colinfo = (deparse_columns *) lfirst(lc2);
if (rte->rtekind == RTE_JOIN)
set_join_column_names(dpns, rte, colinfo);
else
set_relation_column_names(dpns, rte, colinfo);
}
}
/*
* has_dangerous_join_using: search jointree for unnamed JOIN USING
*
* Merged columns of a JOIN USING may act differently from either of the input
* columns, either because they are merged with COALESCE (in a FULL JOIN) or
* because an implicit coercion of the underlying input column is required.
* In such a case the column must be referenced as a column of the JOIN not as
* a column of either input. And this is problematic if the join is unnamed
* (alias-less): we cannot qualify the column's name with an RTE name, since
* there is none. (Forcibly assigning an alias to the join is not a solution,
* since that will prevent legal references to tables below the join.)
* To ensure that every column in the query is unambiguously referenceable,
* we must assign such merged columns names that are globally unique across
* the whole query, aliasing other columns out of the way as necessary.
*
* Because the ensuing re-aliasing is fairly damaging to the readability of
* the query, we don't do this unless we have to. So, we must pre-scan
* the join tree to see if we have to, before starting set_using_names().
*/
static bool
has_dangerous_join_using(deparse_namespace *dpns, Node *jtnode)
{
if (IsA(jtnode, RangeTblRef))
{
/* nothing to do here */
}
else if (IsA(jtnode, FromExpr))
{
FromExpr *f = (FromExpr *) jtnode;
ListCell *lc;
foreach(lc, f->fromlist)
{
if (has_dangerous_join_using(dpns, (Node *) lfirst(lc)))
return true;
}
}
else if (IsA(jtnode, JoinExpr))
{
JoinExpr *j = (JoinExpr *) jtnode;
/* Is it an unnamed JOIN with USING? */
if (j->alias == NULL && j->usingClause)
{
/*
* Yes, so check each join alias var to see if any of them are not
* simple references to underlying columns. If so, we have a
* dangerous situation and must pick unique aliases.
*/
RangeTblEntry *jrte = rt_fetch(j->rtindex, dpns->rtable);
/* We need only examine the merged columns */
for (int i = 0; i < jrte->joinmergedcols; i++)
{
Node *aliasvar = list_nth(jrte->joinaliasvars, i);
if (!IsA(aliasvar, Var))
return true;
}
}
/* Nope, but inspect children */
if (has_dangerous_join_using(dpns, j->larg))
return true;
if (has_dangerous_join_using(dpns, j->rarg))
return true;
}
else
elog(ERROR, "unrecognized node type: %d",
(int) nodeTag(jtnode));
return false;
}
/*
* set_using_names: select column aliases to be used for merged USING columns
*
* We do this during a recursive descent of the query jointree.
* dpns->unique_using must already be set to determine the global strategy.
*
* Column alias info is saved in the dpns->rtable_columns list, which is
* assumed to be filled with pre-zeroed deparse_columns structs.
*
* parentUsing is a list of all USING aliases assigned in parent joins of
* the current jointree node. (The passed-in list must not be modified.)
*/
static void
set_using_names(deparse_namespace *dpns, Node *jtnode, List *parentUsing)
{
if (IsA(jtnode, RangeTblRef))
{
/* nothing to do now */
}
else if (IsA(jtnode, FromExpr))
{
FromExpr *f = (FromExpr *) jtnode;
ListCell *lc;
foreach(lc, f->fromlist)
set_using_names(dpns, (Node *) lfirst(lc), parentUsing);
}
else if (IsA(jtnode, JoinExpr))
{
JoinExpr *j = (JoinExpr *) jtnode;
RangeTblEntry *rte = rt_fetch(j->rtindex, dpns->rtable);
deparse_columns *colinfo = deparse_columns_fetch(j->rtindex, dpns);
int *leftattnos;
int *rightattnos;
deparse_columns *leftcolinfo;
deparse_columns *rightcolinfo;
int i;
ListCell *lc;
/* Get info about the shape of the join */
identify_join_columns(j, rte, colinfo);
leftattnos = colinfo->leftattnos;
rightattnos = colinfo->rightattnos;
/* Look up the not-yet-filled-in child deparse_columns structs */
leftcolinfo = deparse_columns_fetch(colinfo->leftrti, dpns);
rightcolinfo = deparse_columns_fetch(colinfo->rightrti, dpns);
/*
* If this join is unnamed, then we cannot substitute new aliases at
* this level, so any name requirements pushed down to here must be
* pushed down again to the children.
*/
if (rte->alias == NULL)
{
for (i = 0; i < colinfo->num_cols; i++)
{
char *colname = colinfo->colnames[i];
if (colname == NULL)
continue;
/* Push down to left column, unless it's a system column */
if (leftattnos[i] > 0)
{
expand_colnames_array_to(leftcolinfo, leftattnos[i]);
leftcolinfo->colnames[leftattnos[i] - 1] = colname;
}
/* Same on the righthand side */
if (rightattnos[i] > 0)
{
expand_colnames_array_to(rightcolinfo, rightattnos[i]);
rightcolinfo->colnames[rightattnos[i] - 1] = colname;
}
}
}
/*
* If there's a USING clause, select the USING column names and push
* those names down to the children. We have two strategies:
*
* If dpns->unique_using is true, we force all USING names to be
* unique across the whole query level. In principle we'd only need
* the names of dangerous USING columns to be globally unique, but to
* safely assign all USING names in a single pass, we have to enforce
* the same uniqueness rule for all of them. However, if a USING
* column's name has been pushed down from the parent, we should use
* it as-is rather than making a uniqueness adjustment. This is
* necessary when we're at an unnamed join, and it creates no risk of
* ambiguity. Also, if there's a user-written output alias for a
* merged column, we prefer to use that rather than the input name;
* this simplifies the logic and seems likely to lead to less aliasing
* overall.
*
* If dpns->unique_using is false, we only need USING names to be
* unique within their own join RTE. We still need to honor
* pushed-down names, though.
*
* Though significantly different in results, these two strategies are
* implemented by the same code, with only the difference of whether
* to put assigned names into dpns->using_names.
*/
if (j->usingClause)
{
/* Copy the input parentUsing list so we don't modify it */
parentUsing = list_copy(parentUsing);
/* USING names must correspond to the first join output columns */
expand_colnames_array_to(colinfo, list_length(j->usingClause));
i = 0;
foreach(lc, j->usingClause)
{
char *colname = strVal(lfirst(lc));
/* Assert it's a merged column */
Assert(leftattnos[i] != 0 && rightattnos[i] != 0);
/* Adopt passed-down name if any, else select unique name */
if (colinfo->colnames[i] != NULL)
colname = colinfo->colnames[i];
else
{
/* Prefer user-written output alias if any */
if (rte->alias && i < list_length(rte->alias->colnames))
colname = strVal(list_nth(rte->alias->colnames, i));
/* Make it appropriately unique */
colname = make_colname_unique(colname, dpns, colinfo);
if (dpns->unique_using)
dpns->using_names = lappend(dpns->using_names,
colname);
/* Save it as output column name, too */
colinfo->colnames[i] = colname;
}
/* Remember selected names for use later */
colinfo->usingNames = lappend(colinfo->usingNames, colname);
parentUsing = lappend(parentUsing, colname);
/* Push down to left column, unless it's a system column */
if (leftattnos[i] > 0)
{
expand_colnames_array_to(leftcolinfo, leftattnos[i]);
leftcolinfo->colnames[leftattnos[i] - 1] = colname;
}
/* Same on the righthand side */
if (rightattnos[i] > 0)
{
expand_colnames_array_to(rightcolinfo, rightattnos[i]);
rightcolinfo->colnames[rightattnos[i] - 1] = colname;
}
i++;
}
}
/* Mark child deparse_columns structs with correct parentUsing info */
leftcolinfo->parentUsing = parentUsing;
rightcolinfo->parentUsing = parentUsing;
/* Now recursively assign USING column names in children */
set_using_names(dpns, j->larg, parentUsing);
set_using_names(dpns, j->rarg, parentUsing);
}
else
elog(ERROR, "unrecognized node type: %d",
(int) nodeTag(jtnode));
}
/*
* set_relation_column_names: select column aliases for a non-join RTE
*
* Column alias info is saved in *colinfo, which is assumed to be pre-zeroed.
* If any colnames entries are already filled in, those override local
* choices.
*/
static void
set_relation_column_names(deparse_namespace *dpns, RangeTblEntry *rte,
deparse_columns *colinfo)
{
int ncolumns;
char **real_colnames;
bool changed_any;
int noldcolumns;
int i;
int j;
/*
* Construct an array of the current "real" column names of the RTE.
* real_colnames[] will be indexed by physical column number, with NULL
* entries for dropped columns.
*/
if (rte->rtekind == RTE_RELATION)
{
/* Relation --- look to the system catalogs for up-to-date info */
Relation rel;
TupleDesc tupdesc;
rel = relation_open(rte->relid, AccessShareLock);
tupdesc = RelationGetDescr(rel);
ncolumns = tupdesc->natts;
real_colnames = (char **) palloc(ncolumns * sizeof(char *));
for (i = 0; i < ncolumns; i++)
{
Form_pg_attribute attr = TupleDescAttr(tupdesc, i);
if (attr->attisdropped)
real_colnames[i] = NULL;
else
real_colnames[i] = pstrdup(NameStr(attr->attname));
}
relation_close(rel, AccessShareLock);
}
else
{
/* Otherwise get the column names from eref or expandRTE() */
List *colnames;
ListCell *lc;
/*
* Functions returning composites have the annoying property that some
* of the composite type's columns might have been dropped since the
* query was parsed. If possible, use expandRTE() to handle that
* case, since it has the tedious logic needed to find out about
* dropped columns. However, if we're explaining a plan, then we
* don't have rte->functions because the planner thinks that won't be
* needed later, and that breaks expandRTE(). So in that case we have
* to rely on rte->eref, which may lead us to report a dropped
* column's old name; that seems close enough for EXPLAIN's purposes.
*
* For non-RELATION, non-FUNCTION RTEs, we can just look at rte->eref,
* which should be sufficiently up-to-date: no other RTE types can
* have columns get dropped from under them after parsing.
*/
if (rte->rtekind == RTE_FUNCTION && rte->functions != NIL)
{
/* Since we're not creating Vars, rtindex etc. don't matter */
expandRTE(rte, 1, 0, -1, true /* include dropped */ ,
&colnames, NULL);
}
else
colnames = rte->eref->colnames;
ncolumns = list_length(colnames);
real_colnames = (char **) palloc(ncolumns * sizeof(char *));
i = 0;
foreach(lc, colnames)
{
/*
* If the column name we find here is an empty string, then it's a
* dropped column, so change to NULL.
*/
char *cname = strVal(lfirst(lc));
if (cname[0] == '\0')
cname = NULL;
real_colnames[i] = cname;
i++;
}
}
/*
* Ensure colinfo->colnames has a slot for each column. (It could be long
* enough already, if we pushed down a name for the last column.) Note:
* it's possible that there are now more columns than there were when the
* query was parsed, ie colnames could be longer than rte->eref->colnames.
* We must assign unique aliases to the new columns too, else there could
* be unresolved conflicts when the view/rule is reloaded.
*/
expand_colnames_array_to(colinfo, ncolumns);
Assert(colinfo->num_cols == ncolumns);
/*
* Make sufficiently large new_colnames and is_new_col arrays, too.
*
* Note: because we leave colinfo->num_new_cols zero until after the loop,
* colname_is_unique will not consult that array, which is fine because it
* would only be duplicate effort.
*/
colinfo->new_colnames = (char **) palloc(ncolumns * sizeof(char *));
colinfo->is_new_col = (bool *) palloc(ncolumns * sizeof(bool));
/*
* Scan the columns, select a unique alias for each one, and store it in
* colinfo->colnames and colinfo->new_colnames. The former array has NULL
* entries for dropped columns, the latter omits them. Also mark
* new_colnames entries as to whether they are new since parse time; this
* is the case for entries beyond the length of rte->eref->colnames.
*/
noldcolumns = list_length(rte->eref->colnames);
changed_any = false;
j = 0;