Postgresql源码（51）变长类型实现(valena.c)

(gdb) p *t
$6 = {vl_len_ = "<\000\000", vl_dat = 0x1bd49a4 "hello world~\020"}

struct varlena
{
	char		vl_len_[4];		/* Do not touch this field directly! */
	char		vl_dat[FLEXIBLE_ARRAY_MEMBER];	/* Data content is here */
};

#define VARHDRSZ		((int32) sizeof(int32))
typedef struct varlena text;

typedef union
{
	struct						/* Normal varlena (4-byte length) */
	{
		uint32		va_header;
		char		va_data[FLEXIBLE_ARRAY_MEMBER];
	}			va_4byte;
	struct						/* Compressed-in-line format */
	{
		uint32		va_header;
		uint32		va_tcinfo;	/* Original data size (excludes header) and
								 * compression method; see va_extinfo */
		char		va_data[FLEXIBLE_ARRAY_MEMBER]; /* Compressed data */
	}			va_compressed;
} varattrib_4b;

typedef struct
{
	uint8		va_header;
	char		va_data[FLEXIBLE_ARRAY_MEMBER]; /* Data begins here */
} varattrib_1b;

/* TOAST pointers are a subset of varattrib_1b with an identifying tag byte */
typedef struct
{
	uint8		va_header;		/* Always 0x80 or 0x01 */
	uint8		va_tag;			/* Type of datum */
	char		va_data[FLEXIBLE_ARRAY_MEMBER]; /* Type-specific data */
} varattrib_1b_e;

varattrib_4b  ---使用--->  varlena、bytea(varlena)、text(varlena)、BpChar(varlena)、VarChar(varlena)
varattrib_1b  ---使用--->  Pointer(char*)、Datum(uintptr_t)、char*
varattrib_1b_e

typedef struct ArrayType
{
	int32		vl_len_;		/* varlena header (do not touch directly!) */
	int			ndim;			/* # of dimensions */
	int32		dataoffset;		/* offset to data, or 0 if no bitmap */
	Oid			elemtype;		/* element type OID */
} ArrayType;

// 使用
ArrayType  *aresult = (ArrayType *) result;
...
SET_VARSIZE(aresult, allocated_size);

typedef union
{
	struct						/* Normal varlena (4-byte length) */
	{
		uint32		va_header;
		char		va_data[FLEXIBLE_ARRAY_MEMBER];
	}			va_4byte;
	struct						/* Compressed-in-line format */
	{
		uint32		va_header;
		uint32		va_tcinfo;	/* Original data size (excludes header) and
								 * compression method; see va_extinfo */
		char		va_data[FLEXIBLE_ARRAY_MEMBER]; /* Compressed data */
	}			va_compressed;
} varattrib_4b;

/*
xxxxxx00 4-byte length word, aligned, uncompressed data (up to 1G)
xxxxxx10 4-byte length word, aligned, *compressed* data (up to 1G)

The "xxx" bits are the length field (which includes itself in all cases). In the big-endian case we mask to extract the length, in the little-endian case we shift.  Note that in both cases the flag bits are in the physically first byte.  Also, it is not possible for a 1-byte length word to be zero; this lets us disambiguate alignment padding bytes from the start of an unaligned datum.  (We now *require* pad bytes to be filled with zero!)

“xxx”位是长度字段（在所有情况下都包括它自己）。在 big-endian 的情况下，我们使用 mask 来提取长度，在 little-endian 的情况下，我们进行移位。请注意，在这两种情况下，标志位都在物理上的第一个字节中。此外，一个 1 字节长度的字不可能为零。这让我们可以从未对齐数据的开头消除对齐填充字节的歧义。 （我们现在*要求*填充字节用零填充！）

*/

// 判断类型
#define VARATT_IS_4B(PTR) \
	((((varattrib_1b *) (PTR))->va_header & 0x01) == 0x00)
#define VARATT_IS_4B_U(PTR) \
	((((varattrib_1b *) (PTR))->va_header & 0x03) == 0x00)
#define VARATT_IS_4B_C(PTR) \
	((((varattrib_1b *) (PTR))->va_header & 0x03) == 0x02)
#define VARATT_IS_1B(PTR) \
	((((varattrib_1b *) (PTR))->va_header & 0x01) == 0x01)
#define VARATT_IS_1B_E(PTR) \
	((((varattrib_1b *) (PTR))->va_header) == 0x01)

// 长度操作
#define VARSIZE_4B(PTR) \
	((((varattrib_4b *) (PTR))->va_4byte.va_header >> 2) & 0x3FFFFFFF)

#define SET_VARSIZE_4B(PTR,len) \
	(((varattrib_4b *) (PTR))->va_4byte.va_header = (((uint32) (len)) << 2))
#define SET_VARSIZE_4B_C(PTR,len) \
	(((varattrib_4b *) (PTR))->va_4byte.va_header = (((uint32) (len)) << 2) | 0x02)

// 获取数据
#define VARDATA_4B(PTR)		(((varattrib_4b *) (PTR))->va_4byte.va_data)
#define VARDATA_4B_C(PTR)	(((varattrib_4b *) (PTR))->va_compressed.va_data)

// 压缩用
#define VARHDRSZ_COMPRESSED		offsetof(varattrib_4b, va_compressed.va_data)
#define VARDATA_COMPRESSED_GET_EXTSIZE(PTR) \
	(((varattrib_4b *) (PTR))->va_compressed.va_tcinfo & VARLENA_EXTSIZE_MASK)
#define VARDATA_COMPRESSED_GET_COMPRESS_METHOD(PTR) \
	(((varattrib_4b *) (PTR))->va_compressed.va_tcinfo >> VARLENA_EXTSIZE_BITS)

text *
cstring_to_text(const char *s)
{
	return cstring_to_text_with_len(s, strlen(s));
}

text *
cstring_to_text_with_len(const char *s, int len)
{
	text	   *result = (text *) palloc(len + VARHDRSZ);

	SET_VARSIZE(result, len + VARHDRSZ);
	memcpy(VARDATA(result), s, len);

	return result;
}

char *
text_to_cstring(const text *t)
{
	/* must cast away the const, unfortunately */
	text	   *tunpacked = pg_detoast_datum_packed(unconstify(text *, t));
	int			len = VARSIZE_ANY_EXHDR(tunpacked);
	char	   *result;

	result = (char *) palloc(len + 1);
	memcpy(result, VARDATA_ANY(tunpacked), len);
	result[len] = '\0';

	if (tunpacked != t)
		pfree(tunpacked);

	return result;
}

/*
 *		textin			- converts "..." to internal representation
 */
Datum
textin(PG_FUNCTION_ARGS)
{
	char	   *inputText = PG_GETARG_CSTRING(0);

	PG_RETURN_TEXT_P(cstring_to_text(inputText));
}

/*
 *		textout			- converts internal representation to "..."
 */
Datum
textout(PG_FUNCTION_ARGS)
{
	Datum		txt = PG_GETARG_DATUM(0);

	PG_RETURN_CSTRING(TextDatumGetCString(txt));
}

Datum
textcat(PG_FUNCTION_ARGS)
{
	text	   *t1 = PG_GETARG_TEXT_PP(0);
	text	   *t2 = PG_GETARG_TEXT_PP(1);

	PG_RETURN_TEXT_P(text_catenate(t1, t2));
}
/*
 * text_catenate
 *	Guts of textcat(), broken out so it can be used by other functions
 *
 * Arguments can be in short-header form, but not compressed or out-of-line
 */
static text *
text_catenate(text *t1, text *t2)
{
	text	   *result;
	int			len1,
				len2,
				len;
	char	   *ptr;

	len1 = VARSIZE_ANY_EXHDR(t1);
	len2 = VARSIZE_ANY_EXHDR(t2);

	/* paranoia ... probably should throw error instead? */
	if (len1 < 0)
		len1 = 0;
	if (len2 < 0)
		len2 = 0;

	len = len1 + len2 + VARHDRSZ;
	result = (text *) palloc(len);

	/* Set size of result string... */
	SET_VARSIZE(result, len);

	/* Fill data field of result string... */
	ptr = VARDATA(result);
	if (len1 > 0)
		memcpy(ptr, VARDATA_ANY(t1), len1);
	if (len2 > 0)
		memcpy(ptr + len1, VARDATA_ANY(t2), len2);

	return result;
}

static text *
text_substring(Datum str, int32 start, int32 length, bool length_not_specified)

static text *
text_overlay(text *t1, text *t2, int sp, int sl)

static int
text_position(text *t1, text *t2, Oid collid)

int
varstr_cmp(const char *arg1, int len1, const char *arg2, int len2, Oid collid)
  
// texteq text_lt text_le text_gt text_ge
// 

Datum
text_starts_with(PG_FUNCTION_ARGS)