Automatically generate node support functions

BABELFISH-CONFLICT: see Postgres community repo for original commit Add a script to automatically generate the node support functions (copy, equal, out, and read, as well as the node tags enum) from the struct definitions. For each of the four node support files, it creates two include files, e.g., copyfuncs.funcs.c and copyfuncs.switch.c, to include in the main file. All the scaffolding of the main file stays in place. I have tried to mostly make the coverage of the output match what is currently there. For example, one could now do out/read coverage of utility statement nodes, but I have manually excluded those for now. The reason is mainly that it's easier to diff the before and after, and adding a bunch of stuff like this might require a separate analysis and review. Subtyping (TidScan -> Scan) is supported. For the hard cases, you can just write a manual function and exclude generating one. For the not so hard cases, there is a way of annotating struct fields to get special behaviors. For example, pg_node_attr(equal_ignore) has the field ignored in equal functions. (In this patch, I have only ifdef'ed out the code to could be removed, mainly so that it won't constantly have merge conflicts. It will be deleted in a separate patch. All the code comments that are worth keeping from those sections have already been moved to the header files where the structs are defined.) Reviewed-by: Tom Lane <[email protected]> Discussion: https://www.postgresql.org/message-id/flat/c1097590-a6a4-486a-64b1-e1f9cc0533ce%40enterprisedb.com (cherry picked from commit 964d01ae90c314eb31132c2e7712d5d9fc237331)
amazon-aurora · Nov 29, 2023 · 47188d3 · 47188d3
1 parent 339758a
commit 47188d3
Show file tree

Hide file tree

Showing 23 changed files with 1,628 additions and 254 deletions.
diff --git a/src/backend/Makefile b/src/backend/Makefile
@@ -143,11 +143,15 @@ storage/lmgr/lwlocknames.h: storage/lmgr/generate-lwlocknames.pl storage/lmgr/lw
 submake-catalog-headers:
 	$(MAKE) -C catalog distprep generated-header-symlinks
 
+# run this unconditionally to avoid needing to know its dependencies here:
+submake-nodes-headers:
+	$(MAKE) -C nodes distprep generated-header-symlinks
+
 # run this unconditionally to avoid needing to know its dependencies here:
 submake-utils-headers:
 	$(MAKE) -C utils distprep generated-header-symlinks
 
-.PHONY: submake-catalog-headers submake-utils-headers
+.PHONY: submake-catalog-headers submake-nodes-headers submake-utils-headers
 
 # Make symlinks for these headers in the include directory. That way
 # we can cut down on the -I options. Also, a symlink is automatically
@@ -162,7 +166,7 @@ submake-utils-headers:
 
 .PHONY: generated-headers
 
-generated-headers: $(top_builddir)/src/include/parser/gram.h $(top_builddir)/src/include/storage/lwlocknames.h submake-catalog-headers submake-utils-headers
+generated-headers: $(top_builddir)/src/include/parser/gram.h $(top_builddir)/src/include/storage/lwlocknames.h submake-catalog-headers submake-nodes-headers submake-utils-headers
 
 $(top_builddir)/src/include/parser/gram.h: parser/gram.h
 	prereqdir=`cd '$(dir $<)' >/dev/null && pwd` && \
@@ -185,6 +189,7 @@ distprep:
 	$(MAKE) -C parser	gram.c gram.h scan.c
 	$(MAKE) -C bootstrap	bootparse.c bootscanner.c
 	$(MAKE) -C catalog	distprep
+	$(MAKE) -C nodes	distprep
 	$(MAKE) -C replication	repl_gram.c repl_scanner.c syncrep_gram.c syncrep_scanner.c
 	$(MAKE) -C storage/lmgr	lwlocknames.h lwlocknames.c
 	$(MAKE) -C utils	distprep
@@ -297,6 +302,7 @@ distclean: clean
 
 maintainer-clean: distclean
 	$(MAKE) -C catalog $@
+	$(MAKE) -C nodes $@
 	$(MAKE) -C utils $@
 	rm -f bootstrap/bootparse.c \
 	      bootstrap/bootscanner.c \

diff --git a/src/backend/nodes/.gitignore b/src/backend/nodes/.gitignore
@@ -0,0 +1,4 @@
+/node-support-stamp
+/nodetags.h
+/*funcs.funcs.c
+/*funcs.switch.c
diff --git a/src/backend/nodes/Makefile b/src/backend/nodes/Makefile
@@ -30,3 +30,62 @@ OBJS = \
 	value.o
 
 include $(top_srcdir)/src/backend/common.mk
+
+node_headers = \
+	nodes/nodes.h \
+	nodes/execnodes.h \
+	nodes/plannodes.h \
+	nodes/primnodes.h \
+	nodes/pathnodes.h \
+	nodes/extensible.h \
+	nodes/parsenodes.h \
+	nodes/replnodes.h \
+	nodes/value.h \
+	commands/trigger.h \
+	commands/event_trigger.h \
+	foreign/fdwapi.h \
+	access/amapi.h \
+	access/tableam.h \
+	access/tsmapi.h \
+	utils/rel.h \
+	nodes/supportnodes.h \
+	executor/tuptable.h \
+	nodes/lockoptions.h \
+	access/sdir.h
+
+# see also catalog/Makefile for an explanation of these make rules
+
+all: distprep generated-header-symlinks
+
+distprep: node-support-stamp
+
+.PHONY: generated-header-symlinks
+
+generated-header-symlinks: $(top_builddir)/src/include/nodes/header-stamp
+
+# node-support-stamp records the last time we ran gen_node_support.pl.
+# We don't rely on the timestamps of the individual output files,
+# because the Perl script won't update them if they didn't change (to
+# avoid unnecessary recompiles).
+node-support-stamp: gen_node_support.pl $(addprefix $(top_srcdir)/src/include/,$(node_headers))
+	$(PERL) $^
+	touch $@
+
+# These generated headers must be symlinked into builddir/src/include/,
+# using absolute links for the reasons explained in src/backend/Makefile.
+# We use header-stamp to record that we've done this because the symlinks
+# themselves may appear older than node-support-stamp.
+$(top_builddir)/src/include/nodes/header-stamp: node-support-stamp
+	prereqdir=`cd '$(dir $<)' >/dev/null && pwd` && \
+	cd '$(dir $@)' && for file in nodetags.h; do \
+	  rm -f $$file && $(LN_S) "$$prereqdir/$$file" . ; \
+	done
+	touch $@
+
+copyfuncs.o: copyfuncs.c copyfuncs.funcs.c copyfuncs.switch.c | node-support-stamp
+equalfuncs.o: equalfuncs.c equalfuncs.funcs.c equalfuncs.switch.c | node-support-stamp
+outfuncs.o: outfuncs.c outfuncs.funcs.c outfuncs.switch.c | node-support-stamp
+readfuncs.o:  readfuncs.c readfuncs.funcs.c readfuncs.switch.c | node-support-stamp
+
+maintainer-clean: clean
+	rm -f node-support-stamp $(addsuffix funcs.funcs.c,copy equal out read) $(addsuffix funcs.switch.c,copy equal out read) nodetags.h
diff --git a/src/backend/nodes/README b/src/backend/nodes/README
@@ -3,26 +3,34 @@ src/backend/nodes/README
 Node Structures
 ===============
 
-Andrew Yu (11/94)
-
 Introduction
 ------------
 
-The current node structures are plain old C structures. "Inheritance" is
-achieved by convention. No additional functions will be generated. Functions
-that manipulate node structures reside in this directory.
+The node structures are plain old C structures with the first field
+being of type NodeTag.  "Inheritance" is achieved by convention:
+the first field can alternatively be of another node type.
+
+Utility functions for manipulating node structures reside in this
+directory.  Some support functions are automatically generated by the
+gen_node_support.pl script, other functions are maintained manually.
+To control the automatic generation of support functions, node types
+and node fields can be annotated with pg_node_attr() specifications;
+see further documentation in src/include/nodes/nodes.h.
 
 
 FILES IN THIS DIRECTORY (src/backend/nodes/)
 
     General-purpose node manipulation functions:
-	copyfuncs.c	- copy a node tree
-	equalfuncs.c	- compare two node trees
-	outfuncs.c	- convert a node tree to text representation
-	readfuncs.c	- convert text representation back to a node tree
+	copyfuncs.c	- copy a node tree (*)
+	equalfuncs.c	- compare two node trees (*)
+	outfuncs.c	- convert a node tree to text representation (*)
+	readfuncs.c	- convert text representation back to a node tree (*)
 	makefuncs.c	- creator functions for some common node types
 	nodeFuncs.c	- some other general-purpose manipulation functions
 
+    (*) - Most functions in these files are generated by
+    gen_node_support.pl and #include'd there.
+
     Specialized manipulation functions:
 	bitmapset.c	- Bitmapset support
 	list.c		- generic list support
@@ -33,7 +41,7 @@ FILES IN THIS DIRECTORY (src/backend/nodes/)
 FILES IN src/include/nodes/
 
     Node definitions:
-	nodes.h		- define node tags (NodeTag)
+	nodes.h		- define node tags (NodeTag) (*)
 	primnodes.h	- primitive nodes
 	parsenodes.h	- parse tree nodes
 	pathnodes.h	- path tree nodes and planner internal structures
@@ -42,39 +50,39 @@ FILES IN src/include/nodes/
 	memnodes.h	- memory nodes
 	pg_list.h	- generic list
 
+    (*) - Also #include's files generated by gen_node_support.pl.
+
 
 Steps to Add a Node
 -------------------
 
 Suppose you want to define a node Foo:
 
-1. Add a tag (T_Foo) to the enum NodeTag in nodes.h.  (If you insert the
-   tag in a way that moves the numbers associated with existing tags,
-   you'll need to recompile the whole tree after doing this.  It doesn't
-   force initdb though, because the numbers never go to disk.)
-2. Add the structure definition to the appropriate include/nodes/???.h file.
+1. Add the structure definition to the appropriate include/nodes/???.h file.
    If you intend to inherit from, say a Plan node, put Plan as the first field
-   of your struct definition.
-3. If you intend to use copyObject, equal, nodeToString or stringToNode,
-   add an appropriate function to copyfuncs.c, equalfuncs.c, outfuncs.c
-   and readfuncs.c accordingly.  (Except for frequently used nodes, don't
-   bother writing a creator function in makefuncs.c)  The header comments
-   in those files give general rules for whether you need to add support.
-4. Add cases to the functions in nodeFuncs.c as needed.  There are many
+   of your struct definition.  (The T_Foo tag is created automatically.)
+2. Check that the generated support functions in copyfuncs.funcs.c,
+   equalfuncs.funcs.c, outfuncs.funcs.c and readfuncs.funcs.c look
+   correct.  Add attributes as necessary to control the outcome.  (For
+   some classes of node types, you don't need all four support functions.
+   Use node attributes similar to those of related node types.)
+3. Add cases to the functions in nodeFuncs.c as needed.  There are many
    other places you'll probably also need to teach about your new node
    type.  Best bet is to grep for references to one or two similar existing
    node types to find all the places to touch.
-
-
-Historical Note
----------------
-
-Prior to the current simple C structure definitions, the Node structures
-used a pseudo-inheritance system which automatically generated creator and
-accessor functions. Since every node inherited from LispValue, the whole thing
-was a mess. Here's a little anecdote:
-
-    LispValue definition -- class used to support lisp structures
-    in C.  This is here because we did not want to totally rewrite
-    planner and executor code which depended on lisp structures when
-    we ported postgres V1 from lisp to C. -cim 4/23/90
+   (Except for frequently-created nodes, don't bother writing a creator
+   function in makefuncs.c.)
+4. Consider testing your new code with COPY_PARSE_PLAN_TREES,
+   WRITE_READ_PARSE_PLAN_TREES, and RAW_EXPRESSION_COVERAGE_TEST to ensure
+   support has been added everywhere that it's necessary; see
+   pg_config_manual.h about these.
+
+Adding a new node type moves the numbers associated with existing
+tags, so you'll need to recompile the whole tree after doing this.
+(--enable-depend usually helps.)  It doesn't force initdb though,
+because the numbers never go to disk.  But altering or removing a node
+type should usually be accompanied by an initdb-forcing catalog
+version change, since the interpretation of serialized node trees
+stored in system catalogs is affected by that.  (If the node type
+never appears in stored parse trees, as for example Plan nodes do not,
+then a catversion change is not needed to change it.)
diff --git a/src/backend/nodes/copyfuncs.c b/src/backend/nodes/copyfuncs.c
@@ -23,11 +23,7 @@
 #include "postgres.h"
 
 #include "miscadmin.h"
-#include "nodes/extensible.h"
-#include "nodes/pathnodes.h"
-#include "nodes/plannodes.h"
 #include "utils/datum.h"
-#include "utils/rel.h"
 
 
 /*
@@ -73,6 +69,9 @@
 	(newnode->fldname = from->fldname)
 
 
+#include "copyfuncs.funcs.c"
+
+#ifdef OBSOLETE
 /* ****************************************************************
  *					 plannodes.h copy functions
  * ****************************************************************
@@ -1432,6 +1431,7 @@ _copyVar(const Var *from)
 
 	return newnode;
 }
+#endif							/* OBSOLETE */
 
 /*
  * _copyConst
@@ -1471,6 +1471,7 @@ _copyConst(const Const *from)
 	return newnode;
 }
 
+#ifdef OBSOLETE
 /*
  * _copyParam
  */
@@ -3216,6 +3217,7 @@ _copyParamRef(const ParamRef *from)
 
 	return newnode;
 }
+#endif							/* OBSOLETE */
 
 static A_Const *
 _copyA_Const(const A_Const *from)
@@ -3259,6 +3261,7 @@ _copyA_Const(const A_Const *from)
 	return newnode;
 }
 
+#ifdef OBSOLETE
 static FuncCall *
 _copyFuncCall(const FuncCall *from)
 {
@@ -5437,6 +5440,7 @@ _copyDropSubscriptionStmt(const DropSubscriptionStmt *from)
 
 	return newnode;
 }
+#endif							/* OBSOLETE */
 
 /* ****************************************************************
  *					extensible.h copy functions
@@ -5459,6 +5463,7 @@ _copyExtensibleNode(const ExtensibleNode *from)
 	return newnode;
 }
 
+#ifdef OBSOLETE
 /* ****************************************************************
  *					value.h copy functions
  * ****************************************************************
@@ -5513,16 +5518,6 @@ _copyBitString(const BitString *from)
 	return newnode;
 }
 
-static TSQL_HexString *
-_copyTSQL_HexString(const TSQL_HexString *from)
-{
-	TSQL_HexString *newnode = makeNode(TSQL_HexString);
-
-	COPY_STRING_FIELD(hsval);
-
-	return newnode;
-}
-
 
 static ForeignKeyCacheInfo *
 _copyForeignKeyCacheInfo(const ForeignKeyCacheInfo *from)
@@ -5539,6 +5534,7 @@ _copyForeignKeyCacheInfo(const ForeignKeyCacheInfo *from)
 
 	return newnode;
 }
+#endif							/* OBSOLETE */
 
 /*
  * copyObjectImpl -- implementation of copyObject(); see nodes/nodes.h
@@ -5559,6 +5555,8 @@ copyObjectImpl(const void *from)
 
 	switch (nodeTag(from))
 	{
+#include "copyfuncs.switch.c"
+#ifdef OBSOLETE
 			/*
 			 * PLAN NODES
 			 */
@@ -5997,9 +5995,7 @@ copyObjectImpl(const void *from)
 		case T_BitString:
 			retval = _copyBitString(from);
 			break;
-		case T_TSQL_HexString:
-			retval = _copyTSQL_HexString(from);
-			break;
+#endif							/* OBSOLETE */
 
 			/*
 			 * LIST NODES
@@ -6017,6 +6013,8 @@ copyObjectImpl(const void *from)
 			retval = list_copy(from);
 			break;
 
+#ifdef OBSOLETE
+
 			/*
 			 * EXTENSIBLE NODES
 			 */
@@ -6568,6 +6566,7 @@ copyObjectImpl(const void *from)
 		case T_ForeignKeyCacheInfo:
 			retval = _copyForeignKeyCacheInfo(from);
 			break;
+#endif							/* OBSOLETE */
 
 		default:
 			elog(ERROR, "unrecognized node type: %d", (int) nodeTag(from));