rem0rec.c

这是linux下运行的mysql软件包,可用于linux 下安装 php + mysql + apach 的网络配置

/************************************************************************
Record manager

(c) 1994-2001 Innobase Oy

Created 5/30/1994 Heikki Tuuri
*************************************************************************/

#include "rem0rec.h"

#ifdef UNIV_NONINL
#include "rem0rec.ic"
#endif

#include "mtr0mtr.h"
#include "mtr0log.h"

/*			PHYSICAL RECORD (OLD STYLE)
			===========================

The physical record, which is the data type of all the records
found in index pages of the database, has the following format
(lower addresses and more significant bits inside a byte are below
represented on a higher text line):

| offset of the end of the last field of data, the most significant
  bit is set to 1 if and only if the field is SQL-null,
  if the offset is 2-byte, then the second most significant
  bit is set to 1 if the field is stored on another page:
  mostly this will occur in the case of big BLOB fields |
... 
| offset of the end of the first field of data + the SQL-null bit |
| 4 bits used to delete mark a record, and mark a predefined
  minimum record in alphabetical order |
| 4 bits giving the number of records owned by this record
  (this term is explained in page0page.h) |
| 13 bits giving the order number of this record in the
  heap of the index page |
| 10 bits giving the number of fields in this record |
| 1 bit which is set to 1 if the offsets above are given in
  one byte format, 0 if in two byte format |
| two bytes giving an absolute pointer to the next record in the page |
ORIGIN of the record
| first field of data | 
... 
| last field of data |

The origin of the record is the start address of the first field 
of data. The offsets are given relative to the origin. 
The offsets of the data fields are stored in an inverted
order because then the offset of the first fields are near the 
origin, giving maybe a better processor cache hit rate in searches.

The offsets of the data fields are given as one-byte 
(if there are less than 127 bytes of data in the record) 
or two-byte unsigned integers. The most significant bit
is not part of the offset, instead it indicates the SQL-null
if the bit is set to 1. */

/*			PHYSICAL RECORD (NEW STYLE)
			===========================

The physical record, which is the data type of all the records
found in index pages of the database, has the following format
(lower addresses and more significant bits inside a byte are below
represented on a higher text line):

| length of the last non-null variable-length field of data:
  if the maximum length is 255, one byte; otherwise,
  0xxxxxxx (one byte, length=0..127), or 1exxxxxxxxxxxxxx (two bytes,
  length=128..16383, extern storage flag) |
...
| length of first variable-length field of data |
| SQL-null flags (1 bit per nullable field), padded to full bytes |
| 4 bits used to delete mark a record, and mark a predefined
  minimum record in alphabetical order |
| 4 bits giving the number of records owned by this record
  (this term is explained in page0page.h) |
| 13 bits giving the order number of this record in the
  heap of the index page |
| 3 bits record type: 000=conventional, 001=node pointer (inside B-tree),
  010=infimum, 011=supremum, 1xx=reserved |
| two bytes giving a relative pointer to the next record in the page |
ORIGIN of the record
| first field of data |
...
| last field of data |

The origin of the record is the start address of the first field
of data. The offsets are given relative to the origin.
The offsets of the data fields are stored in an inverted
order because then the offset of the first fields are near the
origin, giving maybe a better processor cache hit rate in searches.

The offsets of the data fields are given as one-byte
(if there are less than 127 bytes of data in the record)
or two-byte unsigned integers. The most significant bit
is not part of the offset, instead it indicates the SQL-null
if the bit is set to 1. */

/* CANONICAL COORDINATES. A record can be seen as a single
string of 'characters' in the following way: catenate the bytes
in each field, in the order of fields. An SQL-null field
is taken to be an empty sequence of bytes. Then after
the position of each field insert in the string 
the 'character' <FIELD-END>, except that after an SQL-null field
insert <NULL-FIELD-END>. Now the ordinal position of each
byte in this canonical string is its canonical coordinate.
So, for the record ("AA", SQL-NULL, "BB", ""), the canonical
string is "AA<FIELD_END><NULL-FIELD-END>BB<FIELD-END><FIELD-END>".
We identify prefixes (= initial segments) of a record
with prefixes of the canonical string. The canonical
length of the prefix is the length of the corresponding
prefix of the canonical string. The canonical length of
a record is the length of its canonical string.

For example, the maximal common prefix of records
("AA", SQL-NULL, "BB", "C") and ("AA", SQL-NULL, "B", "C")
is "AA<FIELD-END><NULL-FIELD-END>B", and its canonical
length is 5.

A complete-field prefix of a record is a prefix which ends at the
end of some field (containing also <FIELD-END>).
A record is a complete-field prefix of another record, if
the corresponding canonical strings have the same property. */

ulint	rec_dummy;	/* this is used to fool compiler in
			rec_validate */

/*******************************************************************
Validates the consistency of an old-style physical record. */
static
ibool
rec_validate_old(
/*=============*/
			/* out: TRUE if ok */
	rec_t*	rec);	/* in: physical record */

/**********************************************************
The following function determines the offsets to each field in the
record.  The offsets are written to a previously allocated array of
ulint, where rec_offs_n_fields(offsets) has been initialized to the
number of fields in the record.  The rest of the array will be
initialized by this function.  rec_offs_base(offsets)[0] will be set
to the extra size (if REC_OFFS_COMPACT is set, the record is in the
new format), and rec_offs_base(offsets)[1..n_fields] will be set to
offsets past the end of fields 0..n_fields, or to the beginning of
fields 1..n_fields+1.  When the high-order bit of the offset at [i+1]
is set (REC_OFFS_SQL_NULL), the field i is NULL.  When the second
high-order bit of the offset at [i+1] is set (REC_OFFS_EXTERNAL), the
field i is being stored externally. */
static
void
rec_init_offsets(
/*=============*/
				/* out: the offsets */
	rec_t*		rec,	/* in: physical record */
	dict_index_t*	index,	/* in: record descriptor */
	ulint*		offsets)/* in/out: array of offsets;
				in: n=rec_offs_n_fields(offsets) */
{
	ulint	i	= 0;
	ulint	offs;

	rec_offs_make_valid(rec, index, offsets);

	if (UNIV_LIKELY(index->table->comp)) {
		const byte*	nulls;
		const byte*	lens;
		dict_field_t*	field;
		ulint		null_mask;
		ulint		status = rec_get_status(rec);
		ulint		n_node_ptr_field = ULINT_UNDEFINED;

		switch (UNIV_EXPECT(status, REC_STATUS_ORDINARY)) {
		case REC_STATUS_INFIMUM:
		case REC_STATUS_SUPREMUM:
			/* the field is 8 bytes long */
			rec_offs_base(offsets)[0] =
				REC_N_NEW_EXTRA_BYTES | REC_OFFS_COMPACT;
			rec_offs_base(offsets)[1] = 8;
			return;
		case REC_STATUS_NODE_PTR:
			n_node_ptr_field =
				dict_index_get_n_unique_in_tree(index);
			break;
		case REC_STATUS_ORDINARY:
			break;
		}

		nulls = rec - (REC_N_NEW_EXTRA_BYTES + 1);
		lens = nulls - (index->n_nullable + 7) / 8;
		offs = 0;
		null_mask = 1;

		/* read the lengths of fields 0..n */
		do {
			ulint	len;
			if (UNIV_UNLIKELY(i == n_node_ptr_field)) {
				len = offs += 4;
				goto resolved;
			}

			field = dict_index_get_nth_field(index, i);
			if (!(dtype_get_prtype(dict_col_get_type(
						dict_field_get_col(field)))
						& DATA_NOT_NULL)) {
				/* nullable field => read the null flag */

				if (UNIV_UNLIKELY(!(byte) null_mask)) {
					nulls--;
					null_mask = 1;
				}

				if (*nulls & null_mask) {
					null_mask <<= 1;
					/* No length is stored for NULL fields.
					We do not advance offs, and we set
					the length to zero and enable the
					SQL NULL flag in offsets[]. */
					len = offs | REC_OFFS_SQL_NULL;
					goto resolved;
				}
				null_mask <<= 1;
			}

			if (UNIV_UNLIKELY(!field->fixed_len)) {
				/* Variable-length field: read the length */
				dtype_t*	type = dict_col_get_type(
						dict_field_get_col(field));
				len = *lens--;
				if (UNIV_UNLIKELY(dtype_get_len(type) > 255)
				    || UNIV_UNLIKELY(dtype_get_mtype(type)
							== DATA_BLOB)) {
					if (len & 0x80) {
						/* 1exxxxxxx xxxxxxxx */
						len <<= 8;
						len |= *lens--;

						offs += len & 0x3fff;
						if (UNIV_UNLIKELY(len
								& 0x4000)) {
							len = offs
							| REC_OFFS_EXTERNAL;
						} else {
							len = offs;
						}

						goto resolved;
					}
				}

				len = offs += len;
			} else {
				len = offs += field->fixed_len;
			}
		resolved:
			rec_offs_base(offsets)[i + 1] = len;
		} while (++i < rec_offs_n_fields(offsets));

		*rec_offs_base(offsets) =
			(rec - (lens + 1)) | REC_OFFS_COMPACT;
	} else {
		/* Old-style record: determine extra size and end offsets */
		offs = REC_N_OLD_EXTRA_BYTES;
		if (rec_get_1byte_offs_flag(rec)) {
			offs += rec_offs_n_fields(offsets);
			*rec_offs_base(offsets) = offs;
			/* Determine offsets to fields */
			do {
				offs = rec_1_get_field_end_info(rec, i);
				if (offs & REC_1BYTE_SQL_NULL_MASK) {
					offs &= ~REC_1BYTE_SQL_NULL_MASK;
					offs |= REC_OFFS_SQL_NULL;
				}
				rec_offs_base(offsets)[1 + i] = offs;
			} while (++i < rec_offs_n_fields(offsets));
		} else {
			offs += 2 * rec_offs_n_fields(offsets);
			*rec_offs_base(offsets) = offs;
			/* Determine offsets to fields */
			do {
				offs = rec_2_get_field_end_info(rec, i);
				if (offs & REC_2BYTE_SQL_NULL_MASK) {
					offs &= ~REC_2BYTE_SQL_NULL_MASK;
					offs |= REC_OFFS_SQL_NULL;
				}
				if (offs & REC_2BYTE_EXTERN_MASK) {
					offs &= ~REC_2BYTE_EXTERN_MASK;
					offs |= REC_OFFS_EXTERNAL;
				}
				rec_offs_base(offsets)[1 + i] = offs;
			} while (++i < rec_offs_n_fields(offsets));
		}
	}
}

/**********************************************************
The following function determines the offsets to each field
in the record.  It can reuse a previously returned array. */

ulint*
rec_get_offsets_func(
/*=================*/
				/* out: the new offsets */
	rec_t*		rec,	/* in: physical record */
	dict_index_t*	index,	/* in: record descriptor */
	ulint*		offsets,/* in: array consisting of offsets[0]
				allocated elements, or an array from
				rec_get_offsets(), or NULL */
	ulint		n_fields,/* in: maximum number of initialized fields
				(ULINT_UNDEFINED if all fields) */
	mem_heap_t**	heap,	/* in/out: memory heap */
	const char*	file,	/* in: file name where called */
	ulint		line)	/* in: line number where called */
{
	ulint	n;
	ulint	size;

	ut_ad(rec);
	ut_ad(index);
	ut_ad(heap);

	if (UNIV_LIKELY(index->table->comp)) {
		switch (UNIV_EXPECT(rec_get_status(rec),
				REC_STATUS_ORDINARY)) {
		case REC_STATUS_ORDINARY:
			n = dict_index_get_n_fields(index);
			break;
		case REC_STATUS_NODE_PTR:
			n = dict_index_get_n_unique_in_tree(index) + 1;
			break;
		case REC_STATUS_INFIMUM:
		case REC_STATUS_SUPREMUM:
			/* infimum or supremum record */
			n = 1;
			break;
		default:
			ut_error;
			return(NULL);
		}
	} else {
		n = rec_get_n_fields_old(rec);
	}

	if (UNIV_UNLIKELY(n_fields < n)) {
		n = n_fields;
	}

	size = n + (1 + REC_OFFS_HEADER_SIZE);

	if (UNIV_UNLIKELY(!offsets) ||
			UNIV_UNLIKELY(rec_offs_get_n_alloc(offsets) < size)) {
		if (!*heap) {
			*heap = mem_heap_create_func(size * sizeof(ulint),
				NULL, MEM_HEAP_DYNAMIC, file, line);
		}
		offsets = mem_heap_alloc(*heap, size * sizeof(ulint));
		rec_offs_set_n_alloc(offsets, size);
	}

	rec_offs_set_n_fields(offsets, n);
	rec_init_offsets(rec, index, offsets);
	return(offsets);
}

/****************************************************************
The following function is used to get a pointer to the nth
data field in an old-style record. */

byte*
rec_get_nth_field_old(
/*==================*/
 			/* out: pointer to the field */
 	rec_t*	rec, 	/* in: record */
 	ulint	n,	/* in: index of the field */
	ulint*	len)	/* out: length of the field; UNIV_SQL_NULL if SQL
			null */
{
	ulint	os;
	ulint	next_os;

	ut_ad(rec && len);
	ut_ad(n < rec_get_n_fields_old(rec));

	if (n > REC_MAX_N_FIELDS) {
		fprintf(stderr, "Error: trying to access field %lu in rec\n",
								(ulong) n);
		ut_error;
	}

	if (rec == NULL) {
		fputs("Error: rec is NULL pointer\n", stderr);
		ut_error;
	}
	
	if (rec_get_1byte_offs_flag(rec)) {
		os = rec_1_get_field_start_offs(rec, n);

		next_os = rec_1_get_field_end_info(rec, n);

		if (next_os & REC_1BYTE_SQL_NULL_MASK) {
			*len = UNIV_SQL_NULL;

			return(rec + os);
		}

		next_os = next_os & ~REC_1BYTE_SQL_NULL_MASK;
	} else {
		os = rec_2_get_field_start_offs(rec, n);
	
		next_os = rec_2_get_field_end_info(rec, n);

		if (next_os & REC_2BYTE_SQL_NULL_MASK) {
			*len = UNIV_SQL_NULL;

			return(rec + os);
		}

		next_os = next_os & ~(REC_2BYTE_SQL_NULL_MASK
						| REC_2BYTE_EXTERN_MASK);
	}
	
	*len = next_os - os;

	ut_ad(*len < UNIV_PAGE_SIZE);

	return(rec + os);
}

/**************************************************************
The following function returns the size of a data tuple when converted to
a new-style physical record. */

ulint
rec_get_converted_size_new(
/*=======================*/
				/* out: size */
	dict_index_t*	index,	/* in: record descriptor */
	dtuple_t*	dtuple)	/* in: data tuple */
{
	ulint		size		= REC_N_NEW_EXTRA_BYTES
					+ (index->n_nullable + 7) / 8;
	dict_field_t*	field;
	dtype_t*	type;
	ulint		i;
	ulint		n_fields;
	ut_ad(index && dtuple);
	ut_ad(index->table->comp);

	switch (dtuple_get_info_bits(dtuple) & REC_NEW_STATUS_MASK) {
	case REC_STATUS_ORDINARY:
		n_fields = dict_index_get_n_fields(index);
		ut_ad(n_fields == dtuple_get_n_fields(dtuple));
		break;
	case REC_STATUS_NODE_PTR:
		n_fields = dict_index_get_n_unique_in_tree(index);
		ut_ad(n_fields + 1 == dtuple_get_n_fields(dtuple));
		ut_ad(dtuple_get_nth_field(dtuple, n_fields)->len == 4);
		size += 4; /* child page number */
		break;
	case REC_STATUS_INFIMUM:
	case REC_STATUS_SUPREMUM:
		/* infimum or supremum record, 8 bytes */
		return(size + 8); /* no extra data needed */
	default:
		ut_a(0);
		return(ULINT_UNDEFINED);
	}

	/* read the lengths of fields 0..n */
	for (i = 0; i < n_fields; i++) {
		ulint	len	= dtuple_get_nth_field(dtuple, i)->len;
		field = dict_index_get_nth_field(index, i);
		type = dict_col_get_type(dict_field_get_col(field));
		ut_ad(len != UNIV_SQL_NULL ||
			!(dtype_get_prtype(type) & DATA_NOT_NULL));

		if (len == UNIV_SQL_NULL) {
			/* No length is stored for NULL fields. */
			continue;
		}

		ut_ad(len <= dtype_get_len(type)
			|| dtype_get_mtype(type) == DATA_BLOB);
		ut_ad(!field->fixed_len || len == field->fixed_len);

		if (field->fixed_len) {
		} else if (len < 128 || (dtype_get_len(type) < 256
				&& dtype_get_mtype(type) != DATA_BLOB)) {
			size++;
		} else {
			size += 2;
		}
		size += len;