jsonapi.c File Reference

#include "postgres.h"
#include "common/jsonapi.h"
#include "mb/pg_wchar.h"
#include "port/pg_lfind.h"
#include "miscadmin.h"

Include dependency graph for jsonapi.c:

Go to the source code of this file.

Macros
#define	JSON_ALPHANUMERIC_CHAR(c)
#define	FAIL_AT_CHAR_START(code)
#define	FAIL_AT_CHAR_END(code)

Enumerations
enum	JsonParseContext {   JSON_PARSE_VALUE , JSON_PARSE_STRING , JSON_PARSE_ARRAY_START , JSON_PARSE_ARRAY_NEXT ,   JSON_PARSE_OBJECT_START , JSON_PARSE_OBJECT_LABEL , JSON_PARSE_OBJECT_NEXT , JSON_PARSE_OBJECT_COMMA ,   JSON_PARSE_END }

Functions
static JsonParseErrorType	json_lex_string (JsonLexContext *lex)
static JsonParseErrorType	json_lex_number (JsonLexContext *lex, char *s, bool *num_err, int *total_len)
static JsonParseErrorType	parse_scalar (JsonLexContext *lex, JsonSemAction *sem)
static JsonParseErrorType	parse_object_field (JsonLexContext *lex, JsonSemAction *sem)
static JsonParseErrorType	parse_object (JsonLexContext *lex, JsonSemAction *sem)
static JsonParseErrorType	parse_array_element (JsonLexContext *lex, JsonSemAction *sem)
static JsonParseErrorType	parse_array (JsonLexContext *lex, JsonSemAction *sem)
static JsonParseErrorType	report_parse_error (JsonParseContext ctx, JsonLexContext *lex)
static JsonTokenType	lex_peek (JsonLexContext *lex)
static JsonParseErrorType	lex_expect (JsonParseContext ctx, JsonLexContext *lex, JsonTokenType token)
bool	IsValidJsonNumber (const char *str, int len)
JsonLexContext *	makeJsonLexContextCstringLen (JsonLexContext *lex, char *json, int len, int encoding, bool need_escapes)
void	freeJsonLexContext (JsonLexContext *lex)
JsonParseErrorType	pg_parse_json (JsonLexContext *lex, JsonSemAction *sem)
JsonParseErrorType	json_count_array_elements (JsonLexContext *lex, int *elements)
JsonParseErrorType	json_lex (JsonLexContext *lex)
static char *	extract_token (JsonLexContext *lex)
char *	json_errdetail (JsonParseErrorType error, JsonLexContext *lex)

Variables
JsonSemAction	nullSemAction

Macro Definition Documentation

FAIL_AT_CHAR_END

#define FAIL_AT_CHAR_END

(

code

)

Value:

    do { \
        lex->token_terminator = \
            s + pg_encoding_mblen_bounded(lex->input_encoding, s); \
        return code; \
    } while (0)

FAIL_AT_CHAR_START

#define FAIL_AT_CHAR_START

(

code

)

Value:

    do { \
        lex->token_terminator = s; \
        return code; \
    } while (0)

JSON_ALPHANUMERIC_CHAR

#define JSON_ALPHANUMERIC_CHAR

(

c

)

Value:

    (((c) >= 'a' && (c) <= 'z') || \
     ((c) >= 'A' && (c) <= 'Z') || \
     ((c) >= '0' && (c) <= '9') || \
     (c) == '_' || \
     IS_HIGHBIT_SET(c))

Definition at line 92 of file jsonapi.c.

Enumeration Type Documentation

JsonParseContext

enum JsonParseContext

Enumerator
JSON_PARSE_VALUE
JSON_PARSE_STRING
JSON_PARSE_ARRAY_START
JSON_PARSE_ARRAY_NEXT
JSON_PARSE_OBJECT_START
JSON_PARSE_OBJECT_LABEL
JSON_PARSE_OBJECT_NEXT
JSON_PARSE_OBJECT_COMMA
JSON_PARSE_END

Definition at line 33 of file jsonapi.c.

{
    JSON_PARSE_VALUE,           /* expecting a value */
    JSON_PARSE_STRING,          /* expecting a string (for a field name) */
    JSON_PARSE_ARRAY_START,     /* saw '[', expecting value or ']' */
    JSON_PARSE_ARRAY_NEXT,      /* saw array element, expecting ',' or ']' */
    JSON_PARSE_OBJECT_START,    /* saw '{', expecting label or '}' */
    JSON_PARSE_OBJECT_LABEL,    /* saw object label, expecting ':' */
    JSON_PARSE_OBJECT_NEXT,     /* saw object value, expecting ',' or '}' */
    JSON_PARSE_OBJECT_COMMA,    /* saw object ',', expecting next label */
    JSON_PARSE_END,             /* saw the end of a document, expect nothing */
} JsonParseContext;

Function Documentation

extract_token()

static char* extract_token ( JsonLexContext *  lex )

static

Definition at line 1154 of file jsonapi.c.

{
    int         toklen = lex->token_terminator - lex->token_start;
    char       *token = palloc(toklen + 1);
 
    memcpy(token, lex->token_start, toklen);
    token[toklen] = '\0';
    return token;
}

References palloc(), token, JsonLexContext::token_start, and JsonLexContext::token_terminator.

Referenced by json_errdetail().

freeJsonLexContext()

void freeJsonLexContext

(

JsonLexContext *

lex

)

Definition at line 183 of file jsonapi.c.

{
    if (lex->flags & JSONLEX_FREE_STRVAL)
    {
        pfree(lex->strval->data);
        pfree(lex->strval);
    }
    if (lex->flags & JSONLEX_FREE_STRUCT)
        pfree(lex);
}

References StringInfoData::data, JsonLexContext::flags, JSONLEX_FREE_STRUCT, JSONLEX_FREE_STRVAL, pfree(), and JsonLexContext::strval.

Referenced by datum_to_jsonb_internal(), each_worker(), elements_worker(), get_json_object_as_hash(), get_worker(), iterate_json_values(), json_object_keys(), json_parse_manifest(), json_validate(), populate_array_json(), populate_recordset_worker(), and transform_json_string_values().

IsValidJsonNumber()

bool IsValidJsonNumber	(	const char *	str,
		int	len
	)

Definition at line 105 of file jsonapi.c.

{
    bool        numeric_error;
    int         total_len;
    JsonLexContext dummy_lex;
 
    if (len <= 0)
        return false;
 
    /*
     * json_lex_number expects a leading  '-' to have been eaten already.
     *
     * having to cast away the constness of str is ugly, but there's not much
     * easy alternative.
     */
    if (*str == '-')
    {
        dummy_lex.input = unconstify(char *, str) + 1;
        dummy_lex.input_length = len - 1;
    }
    else
    {
        dummy_lex.input = unconstify(char *, str);
        dummy_lex.input_length = len;
    }
 
    json_lex_number(&dummy_lex, dummy_lex.input, &numeric_error, &total_len);
 
    return (!numeric_error) && (total_len == dummy_lex.input_length);
}

References JsonLexContext::input, JsonLexContext::input_length, json_lex_number(), len, generate_unaccent_rules::str, and unconstify.

Referenced by hstore_to_json_loose(), and hstore_to_jsonb_loose().

json_count_array_elements()

JsonParseErrorType json_count_array_elements	(	JsonLexContext *	lex,
		int *	elements
	)

Definition at line 245 of file jsonapi.c.

{
    JsonLexContext copylex;
    int         count;
    JsonParseErrorType result;
 
    /*
     * It's safe to do this with a shallow copy because the lexical routines
     * don't scribble on the input. They do scribble on the other pointers
     * etc, so doing this with a copy makes that safe.
     */
    memcpy(&copylex, lex, sizeof(JsonLexContext));
    copylex.strval = NULL;      /* not interested in values here */
    copylex.lex_level++;
 
    count = 0;
    result = lex_expect(JSON_PARSE_ARRAY_START, &copylex,
                        JSON_TOKEN_ARRAY_START);
    if (result != JSON_SUCCESS)
        return result;
    if (lex_peek(&copylex) != JSON_TOKEN_ARRAY_END)
    {
        while (1)
        {
            count++;
            result = parse_array_element(&copylex, &nullSemAction);
            if (result != JSON_SUCCESS)
                return result;
            if (copylex.token_type != JSON_TOKEN_COMMA)
                break;
            result = json_lex(&copylex);
            if (result != JSON_SUCCESS)
                return result;
        }
    }
    result = lex_expect(JSON_PARSE_ARRAY_NEXT, &copylex,
                        JSON_TOKEN_ARRAY_END);
    if (result != JSON_SUCCESS)
        return result;
 
    *elements = count;
    return JSON_SUCCESS;
}

References json_lex(), JSON_PARSE_ARRAY_NEXT, JSON_PARSE_ARRAY_START, JSON_SUCCESS, JSON_TOKEN_ARRAY_END, JSON_TOKEN_ARRAY_START, JSON_TOKEN_COMMA, lex_expect(), JsonLexContext::lex_level, lex_peek(), nullSemAction, parse_array_element(), JsonLexContext::strval, and JsonLexContext::token_type.

Referenced by get_array_start().

json_errdetail()

char* json_errdetail	(	JsonParseErrorType	error,
		JsonLexContext *	lex
	)

Definition at line 1172 of file jsonapi.c.

{
    switch (error)
    {
        case JSON_SUCCESS:
            /* fall through to the error code after switch */
            break;
        case JSON_ESCAPING_INVALID:
            return psprintf(_("Escape sequence \"\\%s\" is invalid."),
                            extract_token(lex));
        case JSON_ESCAPING_REQUIRED:
            return psprintf(_("Character with value 0x%02x must be escaped."),
                            (unsigned char) *(lex->token_terminator));
        case JSON_EXPECTED_END:
            return psprintf(_("Expected end of input, but found \"%s\"."),
                            extract_token(lex));
        case JSON_EXPECTED_ARRAY_FIRST:
            return psprintf(_("Expected array element or \"]\", but found \"%s\"."),
                            extract_token(lex));
        case JSON_EXPECTED_ARRAY_NEXT:
            return psprintf(_("Expected \",\" or \"]\", but found \"%s\"."),
                            extract_token(lex));
        case JSON_EXPECTED_COLON:
            return psprintf(_("Expected \":\", but found \"%s\"."),
                            extract_token(lex));
        case JSON_EXPECTED_JSON:
            return psprintf(_("Expected JSON value, but found \"%s\"."),
                            extract_token(lex));
        case JSON_EXPECTED_MORE:
            return _("The input string ended unexpectedly.");
        case JSON_EXPECTED_OBJECT_FIRST:
            return psprintf(_("Expected string or \"}\", but found \"%s\"."),
                            extract_token(lex));
        case JSON_EXPECTED_OBJECT_NEXT:
            return psprintf(_("Expected \",\" or \"}\", but found \"%s\"."),
                            extract_token(lex));
        case JSON_EXPECTED_STRING:
            return psprintf(_("Expected string, but found \"%s\"."),
                            extract_token(lex));
        case JSON_INVALID_TOKEN:
            return psprintf(_("Token \"%s\" is invalid."),
                            extract_token(lex));
        case JSON_UNICODE_CODE_POINT_ZERO:
            return _("\\u0000 cannot be converted to text.");
        case JSON_UNICODE_ESCAPE_FORMAT:
            return _("\"\\u\" must be followed by four hexadecimal digits.");
        case JSON_UNICODE_HIGH_ESCAPE:
            /* note: this case is only reachable in frontend not backend */
            return _("Unicode escape values cannot be used for code point values above 007F when the encoding is not UTF8.");
        case JSON_UNICODE_UNTRANSLATABLE:
            /* note: this case is only reachable in backend not frontend */
            return psprintf(_("Unicode escape value could not be translated to the server's encoding %s."),
                            GetDatabaseEncodingName());
        case JSON_UNICODE_HIGH_SURROGATE:
            return _("Unicode high surrogate must not follow a high surrogate.");
        case JSON_UNICODE_LOW_SURROGATE:
            return _("Unicode low surrogate must follow a high surrogate.");
        case JSON_SEM_ACTION_FAILED:
            /* fall through to the error code after switch */
            break;
    }
 
    /*
     * We don't use a default: case, so that the compiler will warn about
     * unhandled enum values.  But this needs to be here anyway to cover the
     * possibility of an incorrect input.
     */
    elog(ERROR, "unexpected json parse error type: %d", (int) error);
    return NULL;
}

References _, elog(), ERROR, error(), extract_token(), GetDatabaseEncodingName(), JSON_ESCAPING_INVALID, JSON_ESCAPING_REQUIRED, JSON_EXPECTED_ARRAY_FIRST, JSON_EXPECTED_ARRAY_NEXT, JSON_EXPECTED_COLON, JSON_EXPECTED_END, JSON_EXPECTED_JSON, JSON_EXPECTED_MORE, JSON_EXPECTED_OBJECT_FIRST, JSON_EXPECTED_OBJECT_NEXT, JSON_EXPECTED_STRING, JSON_INVALID_TOKEN, JSON_SEM_ACTION_FAILED, JSON_SUCCESS, JSON_UNICODE_CODE_POINT_ZERO, JSON_UNICODE_ESCAPE_FORMAT, JSON_UNICODE_HIGH_ESCAPE, JSON_UNICODE_HIGH_SURROGATE, JSON_UNICODE_LOW_SURROGATE, JSON_UNICODE_UNTRANSLATABLE, psprintf(), and JsonLexContext::token_terminator.

Referenced by json_errsave_error().

json_lex()

JsonParseErrorType json_lex

(

JsonLexContext *

lex

)

Definition at line 588 of file jsonapi.c.

{
    char       *s;
    char       *const end = lex->input + lex->input_length;
    JsonParseErrorType result;
 
    /* Skip leading whitespace. */
    s = lex->token_terminator;
    while (s < end && (*s == ' ' || *s == '\t' || *s == '\n' || *s == '\r'))
    {
        if (*s++ == '\n')
        {
            ++lex->line_number;
            lex->line_start = s;
        }
    }
    lex->token_start = s;
 
    /* Determine token type. */
    if (s >= end)
    {
        lex->token_start = NULL;
        lex->prev_token_terminator = lex->token_terminator;
        lex->token_terminator = s;
        lex->token_type = JSON_TOKEN_END;
    }
    else
    {
        switch (*s)
        {
                /* Single-character token, some kind of punctuation mark. */
            case '{':
                lex->prev_token_terminator = lex->token_terminator;
                lex->token_terminator = s + 1;
                lex->token_type = JSON_TOKEN_OBJECT_START;
                break;
            case '}':
                lex->prev_token_terminator = lex->token_terminator;
                lex->token_terminator = s + 1;
                lex->token_type = JSON_TOKEN_OBJECT_END;
                break;
            case '[':
                lex->prev_token_terminator = lex->token_terminator;
                lex->token_terminator = s + 1;
                lex->token_type = JSON_TOKEN_ARRAY_START;
                break;
            case ']':
                lex->prev_token_terminator = lex->token_terminator;
                lex->token_terminator = s + 1;
                lex->token_type = JSON_TOKEN_ARRAY_END;
                break;
            case ',':
                lex->prev_token_terminator = lex->token_terminator;
                lex->token_terminator = s + 1;
                lex->token_type = JSON_TOKEN_COMMA;
                break;
            case ':':
                lex->prev_token_terminator = lex->token_terminator;
                lex->token_terminator = s + 1;
                lex->token_type = JSON_TOKEN_COLON;
                break;
            case '"':
                /* string */
                result = json_lex_string(lex);
                if (result != JSON_SUCCESS)
                    return result;
                lex->token_type = JSON_TOKEN_STRING;
                break;
            case '-':
                /* Negative number. */
                result = json_lex_number(lex, s + 1, NULL, NULL);
                if (result != JSON_SUCCESS)
                    return result;
                lex->token_type = JSON_TOKEN_NUMBER;
                break;
            case '0':
            case '1':
            case '2':
            case '3':
            case '4':
            case '5':
            case '6':
            case '7':
            case '8':
            case '9':
                /* Positive number. */
                result = json_lex_number(lex, s, NULL, NULL);
                if (result != JSON_SUCCESS)
                    return result;
                lex->token_type = JSON_TOKEN_NUMBER;
                break;
            default:
                {
                    char       *p;
 
                    /*
                     * We're not dealing with a string, number, legal
                     * punctuation mark, or end of string.  The only legal
                     * tokens we might find here are true, false, and null,
                     * but for error reporting purposes we scan until we see a
                     * non-alphanumeric character.  That way, we can report
                     * the whole word as an unexpected token, rather than just
                     * some unintuitive prefix thereof.
                     */
                    for (p = s; p < end && JSON_ALPHANUMERIC_CHAR(*p); p++)
                         /* skip */ ;
 
                    /*
                     * We got some sort of unexpected punctuation or an
                     * otherwise unexpected character, so just complain about
                     * that one character.
                     */
                    if (p == s)
                    {
                        lex->prev_token_terminator = lex->token_terminator;
                        lex->token_terminator = s + 1;
                        return JSON_INVALID_TOKEN;
                    }
 
                    /*
                     * We've got a real alphanumeric token here.  If it
                     * happens to be true, false, or null, all is well.  If
                     * not, error out.
                     */
                    lex->prev_token_terminator = lex->token_terminator;
                    lex->token_terminator = p;
                    if (p - s == 4)
                    {
                        if (memcmp(s, "true", 4) == 0)
                            lex->token_type = JSON_TOKEN_TRUE;
                        else if (memcmp(s, "null", 4) == 0)
                            lex->token_type = JSON_TOKEN_NULL;
                        else
                            return JSON_INVALID_TOKEN;
                    }
                    else if (p - s == 5 && memcmp(s, "false", 5) == 0)
                        lex->token_type = JSON_TOKEN_FALSE;
                    else
                        return JSON_INVALID_TOKEN;
                }
        }                       /* end of switch */
    }
 
    return JSON_SUCCESS;
}

References if(), JsonLexContext::input, JsonLexContext::input_length, JSON_ALPHANUMERIC_CHAR, JSON_INVALID_TOKEN, json_lex_number(), json_lex_string(), JSON_SUCCESS, JSON_TOKEN_ARRAY_END, JSON_TOKEN_ARRAY_START, JSON_TOKEN_COLON, JSON_TOKEN_COMMA, JSON_TOKEN_END, JSON_TOKEN_FALSE, JSON_TOKEN_NULL, JSON_TOKEN_NUMBER, JSON_TOKEN_OBJECT_END, JSON_TOKEN_OBJECT_START, JSON_TOKEN_STRING, JSON_TOKEN_TRUE, JsonLexContext::line_number, JsonLexContext::line_start, JsonLexContext::prev_token_terminator, JsonLexContext::token_start, JsonLexContext::token_terminator, and JsonLexContext::token_type.

Referenced by json_count_array_elements(), json_get_first_token(), json_typeof(), lex_expect(), parse_array(), parse_object(), parse_object_field(), parse_scalar(), and pg_parse_json().

json_lex_number()

static JsonParseErrorType json_lex_number ( JsonLexContext *  lex, char *  s, bool *  num_err, int *  total_len  )

inlinestatic

Definition at line 1011 of file jsonapi.c.

{
    bool        error = false;
    int         len = s - lex->input;
 
    /* Part (1): leading sign indicator. */
    /* Caller already did this for us; so do nothing. */
 
    /* Part (2): parse main digit string. */
    if (len < lex->input_length && *s == '0')
    {
        s++;
        len++;
    }
    else if (len < lex->input_length && *s >= '1' && *s <= '9')
    {
        do
        {
            s++;
            len++;
        } while (len < lex->input_length && *s >= '0' && *s <= '9');
    }
    else
        error = true;
 
    /* Part (3): parse optional decimal portion. */
    if (len < lex->input_length && *s == '.')
    {
        s++;
        len++;
        if (len == lex->input_length || *s < '0' || *s > '9')
            error = true;
        else
        {
            do
            {
                s++;
                len++;
            } while (len < lex->input_length && *s >= '0' && *s <= '9');
        }
    }
 
    /* Part (4): parse optional exponent. */
    if (len < lex->input_length && (*s == 'e' || *s == 'E'))
    {
        s++;
        len++;
        if (len < lex->input_length && (*s == '+' || *s == '-'))
        {
            s++;
            len++;
        }
        if (len == lex->input_length || *s < '0' || *s > '9')
            error = true;
        else
        {
            do
            {
                s++;
                len++;
            } while (len < lex->input_length && *s >= '0' && *s <= '9');
        }
    }
 
    /*
     * Check for trailing garbage.  As in json_lex(), any alphanumeric stuff
     * here should be considered part of the token for error-reporting
     * purposes.
     */
    for (; len < lex->input_length && JSON_ALPHANUMERIC_CHAR(*s); s++, len++)
        error = true;
 
    if (total_len != NULL)
        *total_len = len;
 
    if (num_err != NULL)
    {
        /* let the caller handle any error */
        *num_err = error;
    }
    else
    {
        /* return token endpoint */
        lex->prev_token_terminator = lex->token_terminator;
        lex->token_terminator = s;
        /* handle error if any */
        if (error)
            return JSON_INVALID_TOKEN;
    }
 
    return JSON_SUCCESS;
}

References error(), JsonLexContext::input, JsonLexContext::input_length, JSON_ALPHANUMERIC_CHAR, JSON_INVALID_TOKEN, JSON_SUCCESS, len, JsonLexContext::prev_token_terminator, and JsonLexContext::token_terminator.

Referenced by IsValidJsonNumber(), and json_lex().

json_lex_string()

static JsonParseErrorType json_lex_string ( JsonLexContext *  lex )

inlinestatic

Definition at line 746 of file jsonapi.c.

{
    char       *s;
    char       *const end = lex->input + lex->input_length;
    int         hi_surrogate = -1;
 
    /* Convenience macros for error exits */
#define FAIL_AT_CHAR_START(code) \
    do { \
        lex->token_terminator = s; \
        return code; \
    } while (0)
#define FAIL_AT_CHAR_END(code) \
    do { \
        lex->token_terminator = \
            s + pg_encoding_mblen_bounded(lex->input_encoding, s); \
        return code; \
    } while (0)
 
    if (lex->strval != NULL)
        resetStringInfo(lex->strval);
 
    Assert(lex->input_length > 0);
    s = lex->token_start;
    for (;;)
    {
        s++;
        /* Premature end of the string. */
        if (s >= end)
            FAIL_AT_CHAR_START(JSON_INVALID_TOKEN);
        else if (*s == '"')
            break;
        else if (*s == '\\')
        {
            /* OK, we have an escape character. */
            s++;
            if (s >= end)
                FAIL_AT_CHAR_START(JSON_INVALID_TOKEN);
            else if (*s == 'u')
            {
                int         i;
                int         ch = 0;
 
                for (i = 1; i <= 4; i++)
                {
                    s++;
                    if (s >= end)
                        FAIL_AT_CHAR_START(JSON_INVALID_TOKEN);
                    else if (*s >= '0' && *s <= '9')
                        ch = (ch * 16) + (*s - '0');
                    else if (*s >= 'a' && *s <= 'f')
                        ch = (ch * 16) + (*s - 'a') + 10;
                    else if (*s >= 'A' && *s <= 'F')
                        ch = (ch * 16) + (*s - 'A') + 10;
                    else
                        FAIL_AT_CHAR_END(JSON_UNICODE_ESCAPE_FORMAT);
                }
                if (lex->strval != NULL)
                {
                    /*
                     * Combine surrogate pairs.
                     */
                    if (is_utf16_surrogate_first(ch))
                    {
                        if (hi_surrogate != -1)
                            FAIL_AT_CHAR_END(JSON_UNICODE_HIGH_SURROGATE);
                        hi_surrogate = ch;
                        continue;
                    }
                    else if (is_utf16_surrogate_second(ch))
                    {
                        if (hi_surrogate == -1)
                            FAIL_AT_CHAR_END(JSON_UNICODE_LOW_SURROGATE);
                        ch = surrogate_pair_to_codepoint(hi_surrogate, ch);
                        hi_surrogate = -1;
                    }
 
                    if (hi_surrogate != -1)
                        FAIL_AT_CHAR_END(JSON_UNICODE_LOW_SURROGATE);
 
                    /*
                     * Reject invalid cases.  We can't have a value above
                     * 0xFFFF here (since we only accepted 4 hex digits
                     * above), so no need to test for out-of-range chars.
                     */
                    if (ch == 0)
                    {
                        /* We can't allow this, since our TEXT type doesn't */
                        FAIL_AT_CHAR_END(JSON_UNICODE_CODE_POINT_ZERO);
                    }
 
                    /*
                     * Add the represented character to lex->strval.  In the
                     * backend, we can let pg_unicode_to_server_noerror()
                     * handle any required character set conversion; in
                     * frontend, we can only deal with trivial conversions.
                     */
#ifndef FRONTEND
                    {
                        char        cbuf[MAX_UNICODE_EQUIVALENT_STRING + 1];
 
                        if (!pg_unicode_to_server_noerror(ch, (unsigned char *) cbuf))
                            FAIL_AT_CHAR_END(JSON_UNICODE_UNTRANSLATABLE);
                        appendStringInfoString(lex->strval, cbuf);
                    }
#else
                    if (lex->input_encoding == PG_UTF8)
                    {
                        /* OK, we can map the code point to UTF8 easily */
                        char        utf8str[5];
                        int         utf8len;
 
                        unicode_to_utf8(ch, (unsigned char *) utf8str);
                        utf8len = pg_utf_mblen((unsigned char *) utf8str);
                        appendBinaryStringInfo(lex->strval, utf8str, utf8len);
                    }
                    else if (ch <= 0x007f)
                    {
                        /* The ASCII range is the same in all encodings */
                        appendStringInfoChar(lex->strval, (char) ch);
                    }
                    else
                        FAIL_AT_CHAR_END(JSON_UNICODE_HIGH_ESCAPE);
#endif                          /* FRONTEND */
                }
            }
            else if (lex->strval != NULL)
            {
                if (hi_surrogate != -1)
                    FAIL_AT_CHAR_END(JSON_UNICODE_LOW_SURROGATE);
 
                switch (*s)
                {
                    case '"':
                    case '\\':
                    case '/':
                        appendStringInfoChar(lex->strval, *s);
                        break;
                    case 'b':
                        appendStringInfoChar(lex->strval, '\b');
                        break;
                    case 'f':
                        appendStringInfoChar(lex->strval, '\f');
                        break;
                    case 'n':
                        appendStringInfoChar(lex->strval, '\n');
                        break;
                    case 'r':
                        appendStringInfoChar(lex->strval, '\r');
                        break;
                    case 't':
                        appendStringInfoChar(lex->strval, '\t');
                        break;
                    default:
 
                        /*
                         * Not a valid string escape, so signal error.  We
                         * adjust token_start so that just the escape sequence
                         * is reported, not the whole string.
                         */
                        lex->token_start = s;
                        FAIL_AT_CHAR_END(JSON_ESCAPING_INVALID);
                }
            }
            else if (strchr("\"\\/bfnrt", *s) == NULL)
            {
                /*
                 * Simpler processing if we're not bothered about de-escaping
                 *
                 * It's very tempting to remove the strchr() call here and
                 * replace it with a switch statement, but testing so far has
                 * shown it's not a performance win.
                 */
                lex->token_start = s;
                FAIL_AT_CHAR_END(JSON_ESCAPING_INVALID);
            }
        }
        else
        {
            char       *p = s;
 
            if (hi_surrogate != -1)
                FAIL_AT_CHAR_END(JSON_UNICODE_LOW_SURROGATE);
 
            /*
             * Skip to the first byte that requires special handling, so we
             * can batch calls to appendBinaryStringInfo.
             */
            while (p < end - sizeof(Vector8) &&
                   !pg_lfind8('\\', (uint8 *) p, sizeof(Vector8)) &&
                   !pg_lfind8('"', (uint8 *) p, sizeof(Vector8)) &&
                   !pg_lfind8_le(31, (uint8 *) p, sizeof(Vector8)))
                p += sizeof(Vector8);
 
            for (; p < end; p++)
            {
                if (*p == '\\' || *p == '"')
                    break;
                else if ((unsigned char) *p <= 31)
                {
                    /* Per RFC4627, these characters MUST be escaped. */
                    /*
                     * Since *p isn't printable, exclude it from the context
                     * string
                     */
                    lex->token_terminator = p;
                    return JSON_ESCAPING_REQUIRED;
                }
            }
 
            if (lex->strval != NULL)
                appendBinaryStringInfo(lex->strval, s, p - s);
 
            /*
             * s will be incremented at the top of the loop, so set it to just
             * behind our lookahead position
             */
            s = p - 1;
        }
    }
 
    if (hi_surrogate != -1)
    {
        lex->token_terminator = s + 1;
        return JSON_UNICODE_LOW_SURROGATE;
    }
 
    /* Hooray, we found the end of the string! */
    lex->prev_token_terminator = lex->token_terminator;
    lex->token_terminator = s + 1;
    return JSON_SUCCESS;
 
#undef FAIL_AT_CHAR_START
#undef FAIL_AT_CHAR_END
}

References appendBinaryStringInfo(), appendStringInfoChar(), appendStringInfoString(), Assert(), FAIL_AT_CHAR_END, FAIL_AT_CHAR_START, i, JsonLexContext::input, JsonLexContext::input_encoding, JsonLexContext::input_length, is_utf16_surrogate_first(), is_utf16_surrogate_second(), JSON_ESCAPING_INVALID, JSON_ESCAPING_REQUIRED, JSON_INVALID_TOKEN, JSON_SUCCESS, JSON_UNICODE_CODE_POINT_ZERO, JSON_UNICODE_ESCAPE_FORMAT, JSON_UNICODE_HIGH_ESCAPE, JSON_UNICODE_HIGH_SURROGATE, JSON_UNICODE_LOW_SURROGATE, JSON_UNICODE_UNTRANSLATABLE, MAX_UNICODE_EQUIVALENT_STRING, pg_lfind8(), pg_lfind8_le(), pg_unicode_to_server_noerror(), PG_UTF8, pg_utf_mblen, JsonLexContext::prev_token_terminator, resetStringInfo(), JsonLexContext::strval, surrogate_pair_to_codepoint(), JsonLexContext::token_start, JsonLexContext::token_terminator, and unicode_to_utf8().

Referenced by json_lex().

lex_expect()

static JsonParseErrorType lex_expect ( JsonParseContext  ctx, JsonLexContext *  lex, JsonTokenType  token  )

inlinestatic

Definition at line 83 of file jsonapi.c.

{
    if (lex_peek(lex) == token)
        return json_lex(lex);
    else
        return report_parse_error(ctx, lex);
}

References json_lex(), lex_peek(), report_parse_error(), and token.

Referenced by json_count_array_elements(), parse_array(), parse_object(), parse_object_field(), and pg_parse_json().

lex_peek()

static JsonTokenType lex_peek ( JsonLexContext *  lex )

inlinestatic

Definition at line 71 of file jsonapi.c.

{
    return lex->token_type;
}

References JsonLexContext::token_type.

Referenced by json_count_array_elements(), lex_expect(), parse_array(), parse_array_element(), parse_object(), parse_object_field(), parse_scalar(), and pg_parse_json().

makeJsonLexContextCstringLen()

JsonLexContext* makeJsonLexContextCstringLen	(	JsonLexContext *	lex,
		char *	json,
		int	len,
		int	encoding,
		bool	need_escapes
	)

Definition at line 153 of file jsonapi.c.

{
    if (lex == NULL)
    {
        lex = palloc0(sizeof(JsonLexContext));
        lex->flags |= JSONLEX_FREE_STRUCT;
    }
    else
        memset(lex, 0, sizeof(JsonLexContext));
 
    lex->input = lex->token_terminator = lex->line_start = json;
    lex->line_number = 1;
    lex->input_length = len;
    lex->input_encoding = encoding;
    if (need_escapes)
    {
        lex->strval = makeStringInfo();
        lex->flags |= JSONLEX_FREE_STRVAL;
    }
 
    return lex;
}

References encoding, JsonLexContext::flags, JsonLexContext::input, JsonLexContext::input_encoding, JsonLexContext::input_length, JSONLEX_FREE_STRUCT, JSONLEX_FREE_STRVAL, len, JsonLexContext::line_number, JsonLexContext::line_start, makeStringInfo(), palloc0(), JsonLexContext::strval, and JsonLexContext::token_terminator.

Referenced by get_json_object_as_hash(), json_parse_manifest(), json_recv(), jsonb_from_cstring(), makeJsonLexContext(), and populate_array_json().

parse_array()

static JsonParseErrorType parse_array ( JsonLexContext *  lex, JsonSemAction *  sem  )

static

Definition at line 523 of file jsonapi.c.

{
    /*
     * an array is a possibly empty sequence of array elements, separated by
     * commas and surrounded by square brackets.
     */
    json_struct_action astart = sem->array_start;
    json_struct_action aend = sem->array_end;
    JsonParseErrorType result;
 
#ifndef FRONTEND
    check_stack_depth();
#endif
 
    if (astart != NULL)
    {
        result = (*astart) (sem->semstate);
        if (result != JSON_SUCCESS)
            return result;
    }
 
    /*
     * Data inside an array is at a higher nesting level than the array
     * itself. Note that we increment this after we call the semantic routine
     * for the array start and restore it before we call the routine for the
     * array end.
     */
    lex->lex_level++;
 
    result = lex_expect(JSON_PARSE_ARRAY_START, lex, JSON_TOKEN_ARRAY_START);
    if (result == JSON_SUCCESS && lex_peek(lex) != JSON_TOKEN_ARRAY_END)
    {
        result = parse_array_element(lex, sem);
 
        while (result == JSON_SUCCESS && lex_peek(lex) == JSON_TOKEN_COMMA)
        {
            result = json_lex(lex);
            if (result != JSON_SUCCESS)
                break;
            result = parse_array_element(lex, sem);
        }
    }
    if (result != JSON_SUCCESS)
        return result;
 
    result = lex_expect(JSON_PARSE_ARRAY_NEXT, lex, JSON_TOKEN_ARRAY_END);
    if (result != JSON_SUCCESS)
        return result;
 
    lex->lex_level--;
 
    if (aend != NULL)
    {
        result = (*aend) (sem->semstate);
        if (result != JSON_SUCCESS)
            return result;
    }
 
    return JSON_SUCCESS;
}

References JsonSemAction::array_end, JsonSemAction::array_start, check_stack_depth(), json_lex(), JSON_PARSE_ARRAY_NEXT, JSON_PARSE_ARRAY_START, JSON_SUCCESS, JSON_TOKEN_ARRAY_END, JSON_TOKEN_ARRAY_START, JSON_TOKEN_COMMA, lex_expect(), JsonLexContext::lex_level, lex_peek(), parse_array_element(), and JsonSemAction::semstate.

Referenced by parse_array_element(), parse_object_field(), and pg_parse_json().

parse_array_element()

static JsonParseErrorType parse_array_element ( JsonLexContext *  lex, JsonSemAction *  sem  )

static

Definition at line 479 of file jsonapi.c.

{
    json_aelem_action astart = sem->array_element_start;
    json_aelem_action aend = sem->array_element_end;
    JsonTokenType tok = lex_peek(lex);
    JsonParseErrorType result;
    bool        isnull;
 
    isnull = tok == JSON_TOKEN_NULL;
 
    if (astart != NULL)
    {
        result = (*astart) (sem->semstate, isnull);
        if (result != JSON_SUCCESS)
            return result;
    }
 
    /* an array element is any object, array or scalar */
    switch (tok)
    {
        case JSON_TOKEN_OBJECT_START:
            result = parse_object(lex, sem);
            break;
        case JSON_TOKEN_ARRAY_START:
            result = parse_array(lex, sem);
            break;
        default:
            result = parse_scalar(lex, sem);
    }
 
    if (result != JSON_SUCCESS)
        return result;
 
    if (aend != NULL)
    {
        result = (*aend) (sem->semstate, isnull);
        if (result != JSON_SUCCESS)
            return result;
    }
 
    return JSON_SUCCESS;
}

References JsonSemAction::array_element_end, JsonSemAction::array_element_start, JSON_SUCCESS, JSON_TOKEN_ARRAY_START, JSON_TOKEN_NULL, JSON_TOKEN_OBJECT_START, lex_peek(), parse_array(), parse_object(), parse_scalar(), and JsonSemAction::semstate.

Referenced by json_count_array_elements(), and parse_array().

parse_object()

static JsonParseErrorType parse_object ( JsonLexContext *  lex, JsonSemAction *  sem  )

static

Definition at line 405 of file jsonapi.c.

{
    /*
     * an object is a possibly empty sequence of object fields, separated by
     * commas and surrounded by curly braces.
     */
    json_struct_action ostart = sem->object_start;
    json_struct_action oend = sem->object_end;
    JsonTokenType tok;
    JsonParseErrorType result;
 
#ifndef FRONTEND
    check_stack_depth();
#endif
 
    if (ostart != NULL)
    {
        result = (*ostart) (sem->semstate);
        if (result != JSON_SUCCESS)
            return result;
    }
 
    /*
     * Data inside an object is at a higher nesting level than the object
     * itself. Note that we increment this after we call the semantic routine
     * for the object start and restore it before we call the routine for the
     * object end.
     */
    lex->lex_level++;
 
    Assert(lex_peek(lex) == JSON_TOKEN_OBJECT_START);
    result = json_lex(lex);
    if (result != JSON_SUCCESS)
        return result;
 
    tok = lex_peek(lex);
    switch (tok)
    {
        case JSON_TOKEN_STRING:
            result = parse_object_field(lex, sem);
            while (result == JSON_SUCCESS && lex_peek(lex) == JSON_TOKEN_COMMA)
            {
                result = json_lex(lex);
                if (result != JSON_SUCCESS)
                    break;
                result = parse_object_field(lex, sem);
            }
            break;
        case JSON_TOKEN_OBJECT_END:
            break;
        default:
            /* case of an invalid initial token inside the object */
            result = report_parse_error(JSON_PARSE_OBJECT_START, lex);
    }
    if (result != JSON_SUCCESS)
        return result;
 
    result = lex_expect(JSON_PARSE_OBJECT_NEXT, lex, JSON_TOKEN_OBJECT_END);
    if (result != JSON_SUCCESS)
        return result;
 
    lex->lex_level--;
 
    if (oend != NULL)
    {
        result = (*oend) (sem->semstate);
        if (result != JSON_SUCCESS)
            return result;
    }
 
    return JSON_SUCCESS;
}

References Assert(), check_stack_depth(), json_lex(), JSON_PARSE_OBJECT_NEXT, JSON_PARSE_OBJECT_START, JSON_SUCCESS, JSON_TOKEN_COMMA, JSON_TOKEN_OBJECT_END, JSON_TOKEN_OBJECT_START, JSON_TOKEN_STRING, lex_expect(), JsonLexContext::lex_level, lex_peek(), JsonSemAction::object_end, JsonSemAction::object_start, parse_object_field(), report_parse_error(), and JsonSemAction::semstate.

Referenced by parse_array_element(), parse_object_field(), and pg_parse_json().

parse_object_field()

static JsonParseErrorType parse_object_field ( JsonLexContext *  lex, JsonSemAction *  sem  )

static

Definition at line 343 of file jsonapi.c.

{
    /*
     * An object field is "fieldname" : value where value can be a scalar,
     * object or array.  Note: in user-facing docs and error messages, we
     * generally call a field name a "key".
     */
 
    char       *fname = NULL;   /* keep compiler quiet */
    json_ofield_action ostart = sem->object_field_start;
    json_ofield_action oend = sem->object_field_end;
    bool        isnull;
    JsonTokenType tok;
    JsonParseErrorType result;
 
    if (lex_peek(lex) != JSON_TOKEN_STRING)
        return report_parse_error(JSON_PARSE_STRING, lex);
    if ((ostart != NULL || oend != NULL) && lex->strval != NULL)
        fname = pstrdup(lex->strval->data);
    result = json_lex(lex);
    if (result != JSON_SUCCESS)
        return result;
 
    result = lex_expect(JSON_PARSE_OBJECT_LABEL, lex, JSON_TOKEN_COLON);
    if (result != JSON_SUCCESS)
        return result;
 
    tok = lex_peek(lex);
    isnull = tok == JSON_TOKEN_NULL;
 
    if (ostart != NULL)
    {
        result = (*ostart) (sem->semstate, fname, isnull);
        if (result != JSON_SUCCESS)
            return result;
    }
 
    switch (tok)
    {
        case JSON_TOKEN_OBJECT_START:
            result = parse_object(lex, sem);
            break;
        case JSON_TOKEN_ARRAY_START:
            result = parse_array(lex, sem);
            break;
        default:
            result = parse_scalar(lex, sem);
    }
    if (result != JSON_SUCCESS)
        return result;
 
    if (oend != NULL)
    {
        result = (*oend) (sem->semstate, fname, isnull);
        if (result != JSON_SUCCESS)
            return result;
    }
 
    return JSON_SUCCESS;
}

References StringInfoData::data, json_lex(), JSON_PARSE_OBJECT_LABEL, JSON_PARSE_STRING, JSON_SUCCESS, JSON_TOKEN_ARRAY_START, JSON_TOKEN_COLON, JSON_TOKEN_NULL, JSON_TOKEN_OBJECT_START, JSON_TOKEN_STRING, lex_expect(), lex_peek(), JsonSemAction::object_field_end, JsonSemAction::object_field_start, parse_array(), parse_object(), parse_scalar(), pstrdup(), report_parse_error(), JsonSemAction::semstate, and JsonLexContext::strval.

Referenced by parse_object().

parse_scalar()

static JsonParseErrorType parse_scalar ( JsonLexContext *  lex, JsonSemAction *  sem  )

inlinestatic

Definition at line 299 of file jsonapi.c.

{
    char       *val = NULL;
    json_scalar_action sfunc = sem->scalar;
    JsonTokenType tok = lex_peek(lex);
    JsonParseErrorType result;
 
    /* a scalar must be a string, a number, true, false, or null */
    if (tok != JSON_TOKEN_STRING && tok != JSON_TOKEN_NUMBER &&
        tok != JSON_TOKEN_TRUE && tok != JSON_TOKEN_FALSE &&
        tok != JSON_TOKEN_NULL)
        return report_parse_error(JSON_PARSE_VALUE, lex);
 
    /* if no semantic function, just consume the token */
    if (sfunc == NULL)
        return json_lex(lex);
 
    /* extract the de-escaped string value, or the raw lexeme */
    if (lex_peek(lex) == JSON_TOKEN_STRING)
    {
        if (lex->strval != NULL)
            val = pstrdup(lex->strval->data);
    }
    else
    {
        int         len = (lex->token_terminator - lex->token_start);
 
        val = palloc(len + 1);
        memcpy(val, lex->token_start, len);
        val[len] = '\0';
    }
 
    /* consume the token */
    result = json_lex(lex);
    if (result != JSON_SUCCESS)
        return result;
 
    /* invoke the callback */
    result = (*sfunc) (sem->semstate, val, tok);
 
    return result;
}

References StringInfoData::data, json_lex(), JSON_PARSE_VALUE, JSON_SUCCESS, JSON_TOKEN_FALSE, JSON_TOKEN_NULL, JSON_TOKEN_NUMBER, JSON_TOKEN_STRING, JSON_TOKEN_TRUE, len, lex_peek(), palloc(), pstrdup(), report_parse_error(), JsonSemAction::scalar, JsonSemAction::semstate, JsonLexContext::strval, JsonLexContext::token_start, JsonLexContext::token_terminator, and val.

Referenced by parse_array_element(), parse_object_field(), and pg_parse_json().

pg_parse_json()

JsonParseErrorType pg_parse_json	(	JsonLexContext *	lex,
		JsonSemAction *	sem
	)

Definition at line 205 of file jsonapi.c.

{
    JsonTokenType tok;
    JsonParseErrorType result;
 
    /* get the initial token */
    result = json_lex(lex);
    if (result != JSON_SUCCESS)
        return result;
 
    tok = lex_peek(lex);
 
    /* parse by recursive descent */
    switch (tok)
    {
        case JSON_TOKEN_OBJECT_START:
            result = parse_object(lex, sem);
            break;
        case JSON_TOKEN_ARRAY_START:
            result = parse_array(lex, sem);
            break;
        default:
            result = parse_scalar(lex, sem);    /* json can be a bare scalar */
    }
 
    if (result == JSON_SUCCESS)
        result = lex_expect(JSON_PARSE_END, lex, JSON_TOKEN_END);
 
    return result;
}

References json_lex(), JSON_PARSE_END, JSON_SUCCESS, JSON_TOKEN_ARRAY_START, JSON_TOKEN_END, JSON_TOKEN_OBJECT_START, lex_expect(), lex_peek(), parse_array(), parse_object(), and parse_scalar().

Referenced by json_parse_manifest(), json_validate(), and pg_parse_json_or_errsave().

report_parse_error()

static JsonParseErrorType report_parse_error ( JsonParseContext  ctx, JsonLexContext *  lex  )

static

Definition at line 1111 of file jsonapi.c.

{
    /* Handle case where the input ended prematurely. */
    if (lex->token_start == NULL || lex->token_type == JSON_TOKEN_END)
        return JSON_EXPECTED_MORE;
 
    /* Otherwise choose the error type based on the parsing context. */
    switch (ctx)
    {
        case JSON_PARSE_END:
            return JSON_EXPECTED_END;
        case JSON_PARSE_VALUE:
            return JSON_EXPECTED_JSON;
        case JSON_PARSE_STRING:
            return JSON_EXPECTED_STRING;
        case JSON_PARSE_ARRAY_START:
            return JSON_EXPECTED_ARRAY_FIRST;
        case JSON_PARSE_ARRAY_NEXT:
            return JSON_EXPECTED_ARRAY_NEXT;
        case JSON_PARSE_OBJECT_START:
            return JSON_EXPECTED_OBJECT_FIRST;
        case JSON_PARSE_OBJECT_LABEL:
            return JSON_EXPECTED_COLON;
        case JSON_PARSE_OBJECT_NEXT:
            return JSON_EXPECTED_OBJECT_NEXT;
        case JSON_PARSE_OBJECT_COMMA:
            return JSON_EXPECTED_STRING;
    }
 
    /*
     * We don't use a default: case, so that the compiler will warn about
     * unhandled enum values.
     */
    Assert(false);
    return JSON_SUCCESS;        /* silence stupider compilers */
}

References Assert(), JSON_EXPECTED_ARRAY_FIRST, JSON_EXPECTED_ARRAY_NEXT, JSON_EXPECTED_COLON, JSON_EXPECTED_END, JSON_EXPECTED_JSON, JSON_EXPECTED_MORE, JSON_EXPECTED_OBJECT_FIRST, JSON_EXPECTED_OBJECT_NEXT, JSON_EXPECTED_STRING, JSON_PARSE_ARRAY_NEXT, JSON_PARSE_ARRAY_START, JSON_PARSE_END, JSON_PARSE_OBJECT_COMMA, JSON_PARSE_OBJECT_LABEL, JSON_PARSE_OBJECT_NEXT, JSON_PARSE_OBJECT_START, JSON_PARSE_STRING, JSON_PARSE_VALUE, JSON_SUCCESS, JSON_TOKEN_END, JsonLexContext::token_start, and JsonLexContext::token_type.

Referenced by lex_expect(), parse_object(), parse_object_field(), and parse_scalar().

Variable Documentation

nullSemAction

JsonSemAction nullSemAction

Initial value:

=
{
    NULL, NULL, NULL, NULL, NULL,
    NULL, NULL, NULL, NULL, NULL
}

Definition at line 57 of file jsonapi.c.

Referenced by json_count_array_elements(), json_in(), json_recv(), and json_validate().