pg_query 1.1.0 → 2.0.1

data/ext/pg_query/src_backend_utils_adt_datum.c

@@ -0,0 +1,326 @@
+/*--------------------------------------------------------------------
+ * Symbols referenced in this file:
+ * - datumCopy
+ * - datumGetSize
+ * - datumIsEqual
+ *--------------------------------------------------------------------
+ */
+
+/*-------------------------------------------------------------------------
+ *
+ * datum.c
+ *	  POSTGRES Datum (abstract data type) manipulation routines.
+ *
+ * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1994, Regents of the University of California
+ *
+ *
+ * IDENTIFICATION
+ *	  src/backend/utils/adt/datum.c
+ *
+ *-------------------------------------------------------------------------
+ */
+
+/*
+ * In the implementation of these routines we assume the following:
+ *
+ * A) if a type is "byVal" then all the information is stored in the
+ * Datum itself (i.e. no pointers involved!). In this case the
+ * length of the type is always greater than zero and not more than
+ * "sizeof(Datum)"
+ *
+ * B) if a type is not "byVal" and it has a fixed length (typlen > 0),
+ * then the "Datum" always contains a pointer to a stream of bytes.
+ * The number of significant bytes are always equal to the typlen.
+ *
+ * C) if a type is not "byVal" and has typlen == -1,
+ * then the "Datum" always points to a "struct varlena".
+ * This varlena structure has information about the actual length of this
+ * particular instance of the type and about its value.
+ *
+ * D) if a type is not "byVal" and has typlen == -2,
+ * then the "Datum" always points to a null-terminated C string.
+ *
+ * Note that we do not treat "toasted" datums specially; therefore what
+ * will be copied or compared is the compressed data or toast reference.
+ * An exception is made for datumCopy() of an expanded object, however,
+ * because most callers expect to get a simple contiguous (and pfree'able)
+ * result from datumCopy().  See also datumTransfer().
+ */
+
+#include "postgres.h"
+
+#include "access/detoast.h"
+#include "fmgr.h"
+#include "utils/builtins.h"
+#include "utils/datum.h"
+#include "utils/expandeddatum.h"
+
+
+/*-------------------------------------------------------------------------
+ * datumGetSize
+ *
+ * Find the "real" size of a datum, given the datum value,
+ * whether it is a "by value", and the declared type length.
+ * (For TOAST pointer datums, this is the size of the pointer datum.)
+ *
+ * This is essentially an out-of-line version of the att_addlength_datum()
+ * macro in access/tupmacs.h.  We do a tad more error checking though.
+ *-------------------------------------------------------------------------
+ */
+Size
+datumGetSize(Datum value, bool typByVal, int typLen)
+{
+	Size		size;
+
+	if (typByVal)
+	{
+		/* Pass-by-value types are always fixed-length */
+		Assert(typLen > 0 && typLen <= sizeof(Datum));
+		size = (Size) typLen;
+	}
+	else
+	{
+		if (typLen > 0)
+		{
+			/* Fixed-length pass-by-ref type */
+			size = (Size) typLen;
+		}
+		else if (typLen == -1)
+		{
+			/* It is a varlena datatype */
+			struct varlena *s = (struct varlena *) DatumGetPointer(value);
+
+			if (!PointerIsValid(s))
+				ereport(ERROR,
+						(errcode(ERRCODE_DATA_EXCEPTION),
+						 errmsg("invalid Datum pointer")));
+
+			size = (Size) VARSIZE_ANY(s);
+		}
+		else if (typLen == -2)
+		{
+			/* It is a cstring datatype */
+			char	   *s = (char *) DatumGetPointer(value);
+
+			if (!PointerIsValid(s))
+				ereport(ERROR,
+						(errcode(ERRCODE_DATA_EXCEPTION),
+						 errmsg("invalid Datum pointer")));
+
+			size = (Size) (strlen(s) + 1);
+		}
+		else
+		{
+			elog(ERROR, "invalid typLen: %d", typLen);
+			size = 0;			/* keep compiler quiet */
+		}
+	}
+
+	return size;
+}
+
+/*-------------------------------------------------------------------------
+ * datumCopy
+ *
+ * Make a copy of a non-NULL datum.
+ *
+ * If the datatype is pass-by-reference, memory is obtained with palloc().
+ *
+ * If the value is a reference to an expanded object, we flatten into memory
+ * obtained with palloc().  We need to copy because one of the main uses of
+ * this function is to copy a datum out of a transient memory context that's
+ * about to be destroyed, and the expanded object is probably in a child
+ * context that will also go away.  Moreover, many callers assume that the
+ * result is a single pfree-able chunk.
+ *-------------------------------------------------------------------------
+ */
+Datum
+datumCopy(Datum value, bool typByVal, int typLen)
+{
+	Datum		res;
+
+	if (typByVal)
+		res = value;
+	else if (typLen == -1)
+	{
+		/* It is a varlena datatype */
+		struct varlena *vl = (struct varlena *) DatumGetPointer(value);
+
+		if (VARATT_IS_EXTERNAL_EXPANDED(vl))
+		{
+			/* Flatten into the caller's memory context */
+			ExpandedObjectHeader *eoh = DatumGetEOHP(value);
+			Size		resultsize;
+			char	   *resultptr;
+
+			resultsize = EOH_get_flat_size(eoh);
+			resultptr = (char *) palloc(resultsize);
+			EOH_flatten_into(eoh, (void *) resultptr, resultsize);
+			res = PointerGetDatum(resultptr);
+		}
+		else
+		{
+			/* Otherwise, just copy the varlena datum verbatim */
+			Size		realSize;
+			char	   *resultptr;
+
+			realSize = (Size) VARSIZE_ANY(vl);
+			resultptr = (char *) palloc(realSize);
+			memcpy(resultptr, vl, realSize);
+			res = PointerGetDatum(resultptr);
+		}
+	}
+	else
+	{
+		/* Pass by reference, but not varlena, so not toasted */
+		Size		realSize;
+		char	   *resultptr;
+
+		realSize = datumGetSize(value, typByVal, typLen);
+
+		resultptr = (char *) palloc(realSize);
+		memcpy(resultptr, DatumGetPointer(value), realSize);
+		res = PointerGetDatum(resultptr);
+	}
+	return res;
+}
+
+/*-------------------------------------------------------------------------
+ * datumTransfer
+ *
+ * Transfer a non-NULL datum into the current memory context.
+ *
+ * This is equivalent to datumCopy() except when the datum is a read-write
+ * pointer to an expanded object.  In that case we merely reparent the object
+ * into the current context, and return its standard R/W pointer (in case the
+ * given one is a transient pointer of shorter lifespan).
+ *-------------------------------------------------------------------------
+ */
+
+
+/*-------------------------------------------------------------------------
+ * datumIsEqual
+ *
+ * Return true if two datums are equal, false otherwise
+ *
+ * NOTE: XXX!
+ * We just compare the bytes of the two values, one by one.
+ * This routine will return false if there are 2 different
+ * representations of the same value (something along the lines
+ * of say the representation of zero in one's complement arithmetic).
+ * Also, it will probably not give the answer you want if either
+ * datum has been "toasted".
+ *
+ * Do not try to make this any smarter than it currently is with respect
+ * to "toasted" datums, because some of the callers could be working in the
+ * context of an aborted transaction.
+ *-------------------------------------------------------------------------
+ */
+bool
+datumIsEqual(Datum value1, Datum value2, bool typByVal, int typLen)
+{
+	bool		res;
+
+	if (typByVal)
+	{
+		/*
+		 * just compare the two datums. NOTE: just comparing "len" bytes will
+		 * not do the work, because we do not know how these bytes are aligned
+		 * inside the "Datum".  We assume instead that any given datatype is
+		 * consistent about how it fills extraneous bits in the Datum.
+		 */
+		res = (value1 == value2);
+	}
+	else
+	{
+		Size		size1,
+					size2;
+		char	   *s1,
+				   *s2;
+
+		/*
+		 * Compare the bytes pointed by the pointers stored in the datums.
+		 */
+		size1 = datumGetSize(value1, typByVal, typLen);
+		size2 = datumGetSize(value2, typByVal, typLen);
+		if (size1 != size2)
+			return false;
+		s1 = (char *) DatumGetPointer(value1);
+		s2 = (char *) DatumGetPointer(value2);
+		res = (memcmp(s1, s2, size1) == 0);
+	}
+	return res;
+}
+
+/*-------------------------------------------------------------------------
+ * datum_image_eq
+ *
+ * Compares two datums for identical contents, based on byte images.  Return
+ * true if the two datums are equal, false otherwise.
+ *-------------------------------------------------------------------------
+ */
+
+
+/*-------------------------------------------------------------------------
+ * btequalimage
+ *
+ * Generic "equalimage" support function.
+ *
+ * B-Tree operator classes whose equality function could safely be replaced by
+ * datum_image_eq() in all cases can use this as their "equalimage" support
+ * function.
+ *
+ * Currently, we unconditionally assume that any B-Tree operator class that
+ * registers btequalimage as its support function 4 must be able to safely use
+ * optimizations like deduplication (i.e. we return true unconditionally).  If
+ * it ever proved necessary to rescind support for an operator class, we could
+ * do that in a targeted fashion by doing something with the opcintype
+ * argument.
+ *-------------------------------------------------------------------------
+ */
+
+
+/*-------------------------------------------------------------------------
+ * datumEstimateSpace
+ *
+ * Compute the amount of space that datumSerialize will require for a
+ * particular Datum.
+ *-------------------------------------------------------------------------
+ */
+
+
+/*-------------------------------------------------------------------------
+ * datumSerialize
+ *
+ * Serialize a possibly-NULL datum into caller-provided storage.
+ *
+ * Note: "expanded" objects are flattened so as to produce a self-contained
+ * representation, but other sorts of toast pointers are transferred as-is.
+ * This is because the intended use of this function is to pass the value
+ * to another process within the same database server.  The other process
+ * could not access an "expanded" object within this process's memory, but
+ * we assume it can dereference the same TOAST pointers this one can.
+ *
+ * The format is as follows: first, we write a 4-byte header word, which
+ * is either the length of a pass-by-reference datum, -1 for a
+ * pass-by-value datum, or -2 for a NULL.  If the value is NULL, nothing
+ * further is written.  If it is pass-by-value, sizeof(Datum) bytes
+ * follow.  Otherwise, the number of bytes indicated by the header word
+ * follow.  The caller is responsible for ensuring that there is enough
+ * storage to store the number of bytes that will be written; use
+ * datumEstimateSpace() to find out how many will be needed.
+ * *start_address is updated to point to the byte immediately following
+ * those written.
+ *-------------------------------------------------------------------------
+ */
+
+
+/*-------------------------------------------------------------------------
+ * datumRestore
+ *
+ * Restore a possibly-NULL datum previously serialized by datumSerialize.
+ * *start_address is updated according to the number of bytes consumed.
+ *-------------------------------------------------------------------------
+ */
+

data/ext/pg_query/src_backend_utils_adt_expandeddatum.c

@@ -0,0 +1,98 @@
+/*--------------------------------------------------------------------
+ * Symbols referenced in this file:
+ * - DatumGetEOHP
+ * - EOH_get_flat_size
+ * - EOH_flatten_into
+ *--------------------------------------------------------------------
+ */
+
+/*-------------------------------------------------------------------------
+ *
+ * expandeddatum.c
+ *	  Support functions for "expanded" value representations.
+ *
+ * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1994, Regents of the University of California
+ *
+ *
+ * IDENTIFICATION
+ *	  src/backend/utils/adt/expandeddatum.c
+ *
+ *-------------------------------------------------------------------------
+ */
+#include "postgres.h"
+
+#include "utils/expandeddatum.h"
+#include "utils/memutils.h"
+
+/*
+ * DatumGetEOHP
+ *
+ * Given a Datum that is an expanded-object reference, extract the pointer.
+ *
+ * This is a bit tedious since the pointer may not be properly aligned;
+ * compare VARATT_EXTERNAL_GET_POINTER().
+ */
+ExpandedObjectHeader *
+DatumGetEOHP(Datum d)
+{
+	varattrib_1b_e *datum = (varattrib_1b_e *) DatumGetPointer(d);
+	varatt_expanded ptr;
+
+	Assert(VARATT_IS_EXTERNAL_EXPANDED(datum));
+	memcpy(&ptr, VARDATA_EXTERNAL(datum), sizeof(ptr));
+	Assert(VARATT_IS_EXPANDED_HEADER(ptr.eohptr));
+	return ptr.eohptr;
+}
+
+/*
+ * EOH_init_header
+ *
+ * Initialize the common header of an expanded object.
+ *
+ * The main thing this encapsulates is initializing the TOAST pointers.
+ */
+
+
+/*
+ * EOH_get_flat_size
+ * EOH_flatten_into
+ *
+ * Convenience functions for invoking the "methods" of an expanded object.
+ */
+
+Size
+EOH_get_flat_size(ExpandedObjectHeader *eohptr)
+{
+	return eohptr->eoh_methods->get_flat_size(eohptr);
+}
+
+void
+EOH_flatten_into(ExpandedObjectHeader *eohptr,
+				 void *result, Size allocated_size)
+{
+	eohptr->eoh_methods->flatten_into(eohptr, result, allocated_size);
+}
+
+/*
+ * If the Datum represents a R/W expanded object, change it to R/O.
+ * Otherwise return the original Datum.
+ *
+ * Caller must ensure that the datum is a non-null varlena value.  Typically
+ * this is invoked via MakeExpandedObjectReadOnly(), which checks that.
+ */
+
+
+/*
+ * Transfer ownership of an expanded object to a new parent memory context.
+ * The object must be referenced by a R/W pointer, and what we return is
+ * always its "standard" R/W pointer, which is certain to have the same
+ * lifespan as the object itself.  (The passed-in pointer might not, and
+ * in any case wouldn't provide a unique identifier if it's not that one.)
+ */
+
+
+/*
+ * Delete an expanded object (must be referenced by a R/W pointer).
+ */
+

data/ext/pg_query/src_backend_utils_adt_format_type.c

@@ -0,0 +1,136 @@
+/*--------------------------------------------------------------------
+ * Symbols referenced in this file:
+ * - format_type_be
+ *--------------------------------------------------------------------
+ */
+
+/*-------------------------------------------------------------------------
+ *
+ * format_type.c
+ *	  Display type names "nicely".
+ *
+ *
+ * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1994, Regents of the University of California
+ *
+ * IDENTIFICATION
+ *	  src/backend/utils/adt/format_type.c
+ *
+ *-------------------------------------------------------------------------
+ */
+
+#include "postgres.h"
+
+#include <ctype.h>
+
+#include "access/htup_details.h"
+#include "catalog/namespace.h"
+#include "catalog/pg_type.h"
+#include "mb/pg_wchar.h"
+#include "utils/builtins.h"
+#include "utils/lsyscache.h"
+#include "utils/numeric.h"
+#include "utils/syscache.h"
+
+static char *printTypmod(const char *typname, int32 typmod, Oid typmodout);
+
+
+/*
+ * SQL function: format_type(type_oid, typemod)
+ *
+ * `type_oid' is from pg_type.oid, `typemod' is from
+ * pg_attribute.atttypmod. This function will get the type name and
+ * format it and the modifier to canonical SQL format, if the type is
+ * a standard type. Otherwise you just get pg_type.typname back,
+ * double quoted if it contains funny characters or matches a keyword.
+ *
+ * If typemod is NULL then we are formatting a type name in a context where
+ * no typemod is available, eg a function argument or result type.  This
+ * yields a slightly different result from specifying typemod = -1 in some
+ * cases.  Given typemod = -1 we feel compelled to produce an output that
+ * the parser will interpret as having typemod -1, so that pg_dump will
+ * produce CREATE TABLE commands that recreate the original state.  But
+ * given NULL typemod, we assume that the parser's interpretation of
+ * typemod doesn't matter, and so we are willing to output a slightly
+ * "prettier" representation of the same type.  For example, type = bpchar
+ * and typemod = NULL gets you "character", whereas typemod = -1 gets you
+ * "bpchar" --- the former will be interpreted as character(1) by the
+ * parser, which does not yield typemod -1.
+ *
+ * XXX encoding a meaning in typemod = NULL is ugly; it'd have been
+ * cleaner to make two functions of one and two arguments respectively.
+ * Not worth changing it now, however.
+ */
+
+
+/*
+ * format_type_extended
+ *		Generate a possibly-qualified type name.
+ *
+ * The default behavior is to only qualify if the type is not in the search
+ * path, to ignore the given typmod, and to raise an error if a non-existent
+ * type_oid is given.
+ *
+ * The following bits in 'flags' modify the behavior:
+ * - FORMAT_TYPE_TYPEMOD_GIVEN
+ *			include the typmod in the output (typmod could still be -1 though)
+ * - FORMAT_TYPE_ALLOW_INVALID
+ *			if the type OID is invalid or unknown, return ??? or such instead
+ *			of failing
+ * - FORMAT_TYPE_FORCE_QUALIFY
+ *			always schema-qualify type names, regardless of search_path
+ *
+ * Note that TYPEMOD_GIVEN is not interchangeable with "typemod == -1";
+ * see the comments above for format_type().
+ *
+ * Returns a palloc'd string.
+ */
+
+
+/*
+ * This version is for use within the backend in error messages, etc.
+ * One difference is that it will fail for an invalid type.
+ *
+ * The result is always a palloc'd string.
+ */
+char * format_type_be(Oid type_oid) { return pstrdup("-"); }
+
+
+/*
+ * This version returns a name that is always qualified (unless it's one
+ * of the SQL-keyword type names, such as TIMESTAMP WITH TIME ZONE).
+ */
+
+
+/*
+ * This version allows a nondefault typemod to be specified.
+ */
+
+
+/*
+ * Add typmod decoration to the basic type name
+ */
+
+
+
+/*
+ * type_maximum_size --- determine maximum width of a variable-width column
+ *
+ * If the max width is indeterminate, return -1.  In particular, we return
+ * -1 for any type not known to this routine.  We assume the caller has
+ * already determined that the type is a variable-width type, so it's not
+ * necessary to look up the type's pg_type tuple here.
+ *
+ * This may appear unrelated to format_type(), but in fact the two routines
+ * share knowledge of the encoding of typmod for different types, so it's
+ * convenient to keep them together.  (XXX now that most of this knowledge
+ * has been pushed out of format_type into the typmodout functions, it's
+ * interesting to wonder if it's worth trying to factor this code too...)
+ */
+
+
+
+/*
+ * oidvectortypes			- converts a vector of type OIDs to "typname" list
+ */
+