1
0
mirror of https://github.com/postgres/postgres.git synced 2025-07-17 06:41:09 +03:00
Files
postgres/src/include/utils/jsonpath.h
Tom Lane 1488814542 Fix bogus handling of XQuery regex option flags.
The SQL spec defers to XQuery to define what the option flags are
for LIKE_REGEX patterns.  XQuery says that:
* 's' allows the dot character to match newlines, which by
  default it will not;
* 'm' allows ^ and $ to match at newlines, not only at the
  start/end of the whole string.
Thus, these are *not* inverses as they are for the similarly-named
POSIX options, and neither one corresponds to the POSIX 'n' option.
Fortunately, Spencer's library does expose these two behaviors as
separately twiddlable flags, so we just have to fix the mapping from
JSP flag bits to REG flag bits.  I also chose to rename the symbol
for 's' to DOTALL, to make it clearer that it's not the inverse
of MLINE.

Also, XQuery says that if the 'q' flag "is used together with the m, s,
or x flag, that flag has no effect".  I read this as saying that 'q'
overrides the other flags; whoever wrote our code seems to have read
it backwards.

Lastly, while XQuery's 'x' flag is related to what Spencer's code
does for REG_EXPANDED, it's not the same or a subset.  It seems best
to treat XQuery's 'x' as unimplemented for now.  Maybe later we can
expand our regex code to offer 'x'-style parsing as a separate option.

While at it, refactor the jsonpath code so that (a) there's only
one copy of the flag transformation logic not two, and (b) the
processing of flags is independent of the order in which the flags
are written.

We need some documentation updates to go with this, but I'll
tackle that separately.

Back-patch to v12 where this code originated.

Discussion: https://postgr.es/m/CAPpHfdvDci4iqNF9fhRkTqhe-5_8HmzeLt56drH%2B_Rv2rNRqfg@mail.gmail.com
Reference: https://www.w3.org/TR/2017/REC-xpath-functions-31-20170321/#flags
2019-09-17 15:39:51 -04:00

251 lines
6.3 KiB
C

/*-------------------------------------------------------------------------
*
* jsonpath.h
* Definitions for jsonpath datatype
*
* Copyright (c) 2019, PostgreSQL Global Development Group
*
* IDENTIFICATION
* src/include/utils/jsonpath.h
*
*-------------------------------------------------------------------------
*/
#ifndef JSONPATH_H
#define JSONPATH_H
#include "fmgr.h"
#include "utils/jsonb.h"
#include "nodes/pg_list.h"
typedef struct
{
int32 vl_len_; /* varlena header (do not touch directly!) */
uint32 header; /* version and flags (see below) */
char data[FLEXIBLE_ARRAY_MEMBER];
} JsonPath;
#define JSONPATH_VERSION (0x01)
#define JSONPATH_LAX (0x80000000)
#define JSONPATH_HDRSZ (offsetof(JsonPath, data))
#define DatumGetJsonPathP(d) ((JsonPath *) DatumGetPointer(PG_DETOAST_DATUM(d)))
#define DatumGetJsonPathPCopy(d) ((JsonPath *) DatumGetPointer(PG_DETOAST_DATUM_COPY(d)))
#define PG_GETARG_JSONPATH_P(x) DatumGetJsonPathP(PG_GETARG_DATUM(x))
#define PG_GETARG_JSONPATH_P_COPY(x) DatumGetJsonPathPCopy(PG_GETARG_DATUM(x))
#define PG_RETURN_JSONPATH_P(p) PG_RETURN_POINTER(p)
#define jspIsScalar(type) ((type) >= jpiNull && (type) <= jpiBool)
/*
* All node's type of jsonpath expression
*/
typedef enum JsonPathItemType
{
jpiNull = jbvNull, /* NULL literal */
jpiString = jbvString, /* string literal */
jpiNumeric = jbvNumeric, /* numeric literal */
jpiBool = jbvBool, /* boolean literal: TRUE or FALSE */
jpiAnd, /* predicate && predicate */
jpiOr, /* predicate || predicate */
jpiNot, /* ! predicate */
jpiIsUnknown, /* (predicate) IS UNKNOWN */
jpiEqual, /* expr == expr */
jpiNotEqual, /* expr != expr */
jpiLess, /* expr < expr */
jpiGreater, /* expr > expr */
jpiLessOrEqual, /* expr <= expr */
jpiGreaterOrEqual, /* expr >= expr */
jpiAdd, /* expr + expr */
jpiSub, /* expr - expr */
jpiMul, /* expr * expr */
jpiDiv, /* expr / expr */
jpiMod, /* expr % expr */
jpiPlus, /* + expr */
jpiMinus, /* - expr */
jpiAnyArray, /* [*] */
jpiAnyKey, /* .* */
jpiIndexArray, /* [subscript, ...] */
jpiAny, /* .** */
jpiKey, /* .key */
jpiCurrent, /* @ */
jpiRoot, /* $ */
jpiVariable, /* $variable */
jpiFilter, /* ? (predicate) */
jpiExists, /* EXISTS (expr) predicate */
jpiType, /* .type() item method */
jpiSize, /* .size() item method */
jpiAbs, /* .abs() item method */
jpiFloor, /* .floor() item method */
jpiCeiling, /* .ceiling() item method */
jpiDouble, /* .double() item method */
jpiKeyValue, /* .keyvalue() item method */
jpiSubscript, /* array subscript: 'expr' or 'expr TO expr' */
jpiLast, /* LAST array subscript */
jpiStartsWith, /* STARTS WITH predicate */
jpiLikeRegex, /* LIKE_REGEX predicate */
} JsonPathItemType;
/* XQuery regex mode flags for LIKE_REGEX predicate */
#define JSP_REGEX_ICASE 0x01 /* i flag, case insensitive */
#define JSP_REGEX_DOTALL 0x02 /* s flag, dot matches newline */
#define JSP_REGEX_MLINE 0x04 /* m flag, ^/$ match at newlines */
#define JSP_REGEX_WSPACE 0x08 /* x flag, ignore whitespace in pattern */
#define JSP_REGEX_QUOTE 0x10 /* q flag, no special characters */
/*
* Support functions to parse/construct binary value.
* Unlike many other representation of expression the first/main
* node is not an operation but left operand of expression. That
* allows to implement cheap follow-path descending in jsonb
* structure and then execute operator with right operand
*/
typedef struct JsonPathItem
{
JsonPathItemType type;
/* position form base to next node */
int32 nextPos;
/*
* pointer into JsonPath value to current node, all positions of current
* are relative to this base
*/
char *base;
union
{
/* classic operator with two operands: and, or etc */
struct
{
int32 left;
int32 right;
} args;
/* any unary operation */
int32 arg;
/* storage for jpiIndexArray: indexes of array */
struct
{
int32 nelems;
struct
{
int32 from;
int32 to;
} *elems;
} array;
/* jpiAny: levels */
struct
{
uint32 first;
uint32 last;
} anybounds;
struct
{
char *data; /* for bool, numeric and string/key */
int32 datalen; /* filled only for string/key */
} value;
struct
{
int32 expr;
char *pattern;
int32 patternlen;
uint32 flags;
} like_regex;
} content;
} JsonPathItem;
#define jspHasNext(jsp) ((jsp)->nextPos > 0)
extern void jspInit(JsonPathItem *v, JsonPath *js);
extern void jspInitByBuffer(JsonPathItem *v, char *base, int32 pos);
extern bool jspGetNext(JsonPathItem *v, JsonPathItem *a);
extern void jspGetArg(JsonPathItem *v, JsonPathItem *a);
extern void jspGetLeftArg(JsonPathItem *v, JsonPathItem *a);
extern void jspGetRightArg(JsonPathItem *v, JsonPathItem *a);
extern Numeric jspGetNumeric(JsonPathItem *v);
extern bool jspGetBool(JsonPathItem *v);
extern char *jspGetString(JsonPathItem *v, int32 *len);
extern bool jspGetArraySubscript(JsonPathItem *v, JsonPathItem *from,
JsonPathItem *to, int i);
extern const char *jspOperationName(JsonPathItemType type);
/*
* Parsing support data structures.
*/
typedef struct JsonPathParseItem JsonPathParseItem;
struct JsonPathParseItem
{
JsonPathItemType type;
JsonPathParseItem *next; /* next in path */
union
{
/* classic operator with two operands: and, or etc */
struct
{
JsonPathParseItem *left;
JsonPathParseItem *right;
} args;
/* any unary operation */
JsonPathParseItem *arg;
/* storage for jpiIndexArray: indexes of array */
struct
{
int nelems;
struct
{
JsonPathParseItem *from;
JsonPathParseItem *to;
} *elems;
} array;
/* jpiAny: levels */
struct
{
uint32 first;
uint32 last;
} anybounds;
struct
{
JsonPathParseItem *expr;
char *pattern; /* could not be not null-terminated */
uint32 patternlen;
uint32 flags;
} like_regex;
/* scalars */
Numeric numeric;
bool boolean;
struct
{
uint32 len;
char *val; /* could not be not null-terminated */
} string;
} value;
};
typedef struct JsonPathParseResult
{
JsonPathParseItem *expr;
bool lax;
} JsonPathParseResult;
extern JsonPathParseResult *parsejsonpath(const char *str, int len);
extern int jspConvertRegexFlags(uint32 xflags);
#endif