diff options
| -rw-r--r-- | src/backend/utils/adt/Makefile | 1 | ||||
| -rw-r--r-- | src/backend/utils/adt/json.c | 1206 | ||||
| -rw-r--r-- | src/backend/utils/adt/jsonapi.c | 1216 | ||||
| -rw-r--r-- | src/include/utils/jsonapi.h | 6 |
4 files changed, 1224 insertions, 1205 deletions
diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 13efa9338c1..790d7a24fb8 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -44,6 +44,7 @@ OBJS = \ int.o \ int8.o \ json.o \ + jsonapi.o \ jsonb.o \ jsonb_gin.o \ jsonb_op.o \ diff --git a/src/backend/utils/adt/json.c b/src/backend/utils/adt/json.c index 458505abfd8..4be16b5c201 100644 --- a/src/backend/utils/adt/json.c +++ b/src/backend/utils/adt/json.c @@ -13,14 +13,9 @@ */ #include "postgres.h" -#include "access/htup_details.h" -#include "access/transam.h" #include "catalog/pg_type.h" -#include "executor/spi.h" #include "funcapi.h" -#include "lib/stringinfo.h" #include "libpq/pqformat.h" -#include "mb/pg_wchar.h" #include "miscadmin.h" #include "parser/parse_coerce.h" #include "utils/array.h" @@ -30,27 +25,8 @@ #include "utils/json.h" #include "utils/jsonapi.h" #include "utils/lsyscache.h" -#include "utils/syscache.h" #include "utils/typcache.h" -/* - * The context of the parser is maintained by the recursive descent - * mechanism, but is passed explicitly to the error reporting routine - * for better diagnostics. - */ -typedef enum /* contexts of JSON parser */ -{ - 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; - typedef enum /* type categories for datum_to_json */ { JSONTYPE_NULL, /* null, so we didn't bother to identify */ @@ -75,19 +51,6 @@ typedef struct JsonAggState Oid val_output_func; } JsonAggState; -static inline void json_lex(JsonLexContext *lex); -static inline void json_lex_string(JsonLexContext *lex); -static inline void json_lex_number(JsonLexContext *lex, char *s, - bool *num_err, int *total_len); -static inline void parse_scalar(JsonLexContext *lex, JsonSemAction *sem); -static void parse_object_field(JsonLexContext *lex, JsonSemAction *sem); -static void parse_object(JsonLexContext *lex, JsonSemAction *sem); -static void parse_array_element(JsonLexContext *lex, JsonSemAction *sem); -static void parse_array(JsonLexContext *lex, JsonSemAction *sem); -static void report_parse_error(JsonParseContext ctx, JsonLexContext *lex) pg_attribute_noreturn(); -static void report_invalid_token(JsonLexContext *lex) pg_attribute_noreturn(); -static int report_json_context(JsonLexContext *lex); -static char *extract_mb_char(char *s); static void composite_to_json(Datum composite, StringInfo result, bool use_line_feeds); static void array_dim_to_json(StringInfo result, int dim, int ndims, int *dims, @@ -106,121 +69,6 @@ static void add_json(Datum val, bool is_null, StringInfo result, Oid val_type, bool key_scalar); static text *catenate_stringinfo_string(StringInfo buffer, const char *addon); -/* the null action object used for pure validation */ -static JsonSemAction nullSemAction = -{ - NULL, NULL, NULL, NULL, NULL, - NULL, NULL, NULL, NULL, NULL -}; - -/* Recursive Descent parser support routines */ - -/* - * lex_peek - * - * what is the current look_ahead token? -*/ -static inline JsonTokenType -lex_peek(JsonLexContext *lex) -{ - return lex->token_type; -} - -/* - * lex_accept - * - * accept the look_ahead token and move the lexer to the next token if the - * look_ahead token matches the token parameter. In that case, and if required, - * also hand back the de-escaped lexeme. - * - * returns true if the token matched, false otherwise. - */ -static inline bool -lex_accept(JsonLexContext *lex, JsonTokenType token, char **lexeme) -{ - if (lex->token_type == token) - { - if (lexeme != NULL) - { - if (lex->token_type == JSON_TOKEN_STRING) - { - if (lex->strval != NULL) - *lexeme = pstrdup(lex->strval->data); - } - else - { - int len = (lex->token_terminator - lex->token_start); - char *tokstr = palloc(len + 1); - - memcpy(tokstr, lex->token_start, len); - tokstr[len] = '\0'; - *lexeme = tokstr; - } - } - json_lex(lex); - return true; - } - return false; -} - -/* - * lex_accept - * - * move the lexer to the next token if the current look_ahead token matches - * the parameter token. Otherwise, report an error. - */ -static inline void -lex_expect(JsonParseContext ctx, JsonLexContext *lex, JsonTokenType token) -{ - if (!lex_accept(lex, token, NULL)) - report_parse_error(ctx, lex); -} - -/* chars to consider as part of an alphanumeric token */ -#define JSON_ALPHANUMERIC_CHAR(c) \ - (((c) >= 'a' && (c) <= 'z') || \ - ((c) >= 'A' && (c) <= 'Z') || \ - ((c) >= '0' && (c) <= '9') || \ - (c) == '_' || \ - IS_HIGHBIT_SET(c)) - -/* - * Utility function to check if a string is a valid JSON number. - * - * str is of length len, and need not be null-terminated. - */ -bool -IsValidJsonNumber(const char *str, int len) -{ - 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); -} - /* * Input. */ @@ -286,1058 +134,6 @@ json_recv(PG_FUNCTION_ARGS) } /* - * makeJsonLexContext - * - * lex constructor, with or without StringInfo object - * for de-escaped lexemes. - * - * Without is better as it makes the processing faster, so only make one - * if really required. - * - * If you already have the json as a text* value, use the first of these - * functions, otherwise use makeJsonLexContextCstringLen(). - */ -JsonLexContext * -makeJsonLexContext(text *json, bool need_escapes) -{ - return makeJsonLexContextCstringLen(VARDATA_ANY(json), - VARSIZE_ANY_EXHDR(json), - need_escapes); -} - -JsonLexContext * -makeJsonLexContextCstringLen(char *json, int len, bool need_escapes) -{ - JsonLexContext *lex = palloc0(sizeof(JsonLexContext)); - - lex->input = lex->token_terminator = lex->line_start = json; - lex->line_number = 1; - lex->input_length = len; - if (need_escapes) - lex->strval = makeStringInfo(); - return lex; -} - -/* - * pg_parse_json - * - * Publicly visible entry point for the JSON parser. - * - * lex is a lexing context, set up for the json to be processed by calling - * makeJsonLexContext(). sem is a structure of function pointers to semantic - * action routines to be called at appropriate spots during parsing, and a - * pointer to a state object to be passed to those routines. - */ -void -pg_parse_json(JsonLexContext *lex, JsonSemAction *sem) -{ - JsonTokenType tok; - - /* get the initial token */ - json_lex(lex); - - tok = lex_peek(lex); - - /* parse by recursive descent */ - switch (tok) - { - case JSON_TOKEN_OBJECT_START: - parse_object(lex, sem); - break; - case JSON_TOKEN_ARRAY_START: - parse_array(lex, sem); - break; - default: - parse_scalar(lex, sem); /* json can be a bare scalar */ - } - - lex_expect(JSON_PARSE_END, lex, JSON_TOKEN_END); - -} - -/* - * json_count_array_elements - * - * Returns number of array elements in lex context at start of array token - * until end of array token at same nesting level. - * - * Designed to be called from array_start routines. - */ -int -json_count_array_elements(JsonLexContext *lex) -{ - JsonLexContext copylex; - int count; - - /* - * 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(©lex, lex, sizeof(JsonLexContext)); - copylex.strval = NULL; /* not interested in values here */ - copylex.lex_level++; - - count = 0; - lex_expect(JSON_PARSE_ARRAY_START, ©lex, JSON_TOKEN_ARRAY_START); - if (lex_peek(©lex) != JSON_TOKEN_ARRAY_END) - { - do - { - count++; - parse_array_element(©lex, &nullSemAction); - } - while (lex_accept(©lex, JSON_TOKEN_COMMA, NULL)); - } - lex_expect(JSON_PARSE_ARRAY_NEXT, ©lex, JSON_TOKEN_ARRAY_END); - - return count; -} - -/* - * Recursive Descent parse routines. There is one for each structural - * element in a json document: - * - scalar (string, number, true, false, null) - * - array ( [ ] ) - * - array element - * - object ( { } ) - * - object field - */ -static inline void -parse_scalar(JsonLexContext *lex, JsonSemAction *sem) -{ - char *val = NULL; - json_scalar_action sfunc = sem->scalar; - char **valaddr; - JsonTokenType tok = lex_peek(lex); - - valaddr = sfunc == NULL ? NULL : &val; - - /* a scalar must be a string, a number, true, false, or null */ - switch (tok) - { - case JSON_TOKEN_TRUE: - lex_accept(lex, JSON_TOKEN_TRUE, valaddr); - break; - case JSON_TOKEN_FALSE: - lex_accept(lex, JSON_TOKEN_FALSE, valaddr); - break; - case JSON_TOKEN_NULL: - lex_accept(lex, JSON_TOKEN_NULL, valaddr); - break; - case JSON_TOKEN_NUMBER: - lex_accept(lex, JSON_TOKEN_NUMBER, valaddr); - break; - case JSON_TOKEN_STRING: - lex_accept(lex, JSON_TOKEN_STRING, valaddr); - break; - default: - report_parse_error(JSON_PARSE_VALUE, lex); - } - - if (sfunc != NULL) - (*sfunc) (sem->semstate, val, tok); -} - -static void -parse_object_field(JsonLexContext *lex, JsonSemAction *sem) -{ - /* - * 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; - char **fnameaddr = NULL; - JsonTokenType tok; - - if (ostart != NULL || oend != NULL) - fnameaddr = &fname; - - if (!lex_accept(lex, JSON_TOKEN_STRING, fnameaddr)) - report_parse_error(JSON_PARSE_STRING, lex); - - lex_expect(JSON_PARSE_OBJECT_LABEL, lex, JSON_TOKEN_COLON); - - tok = lex_peek(lex); - isnull = tok == JSON_TOKEN_NULL; - - if (ostart != NULL) - (*ostart) (sem->semstate, fname, isnull); - - switch (tok) - { - case JSON_TOKEN_OBJECT_START: - parse_object(lex, sem); - break; - case JSON_TOKEN_ARRAY_START: - parse_array(lex, sem); - break; - default: - parse_scalar(lex, sem); - } - - if (oend != NULL) - (*oend) (sem->semstate, fname, isnull); -} - -static void -parse_object(JsonLexContext *lex, JsonSemAction *sem) -{ - /* - * 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; - - check_stack_depth(); - - if (ostart != NULL) - (*ostart) (sem->semstate); - - /* - * 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++; - - /* we know this will succeed, just clearing the token */ - lex_expect(JSON_PARSE_OBJECT_START, lex, JSON_TOKEN_OBJECT_START); - - tok = lex_peek(lex); - switch (tok) - { - case JSON_TOKEN_STRING: - parse_object_field(lex, sem); - while (lex_accept(lex, JSON_TOKEN_COMMA, NULL)) - parse_object_field(lex, sem); - break; - case JSON_TOKEN_OBJECT_END: - break; - default: - /* case of an invalid initial token inside the object */ - report_parse_error(JSON_PARSE_OBJECT_START, lex); - } - - lex_expect(JSON_PARSE_OBJECT_NEXT, lex, JSON_TOKEN_OBJECT_END); - - lex->lex_level--; - - if (oend != NULL) - (*oend) (sem->semstate); -} - -static void -parse_array_element(JsonLexContext *lex, JsonSemAction *sem) -{ - json_aelem_action astart = sem->array_element_start; - json_aelem_action aend = sem->array_element_end; - JsonTokenType tok = lex_peek(lex); - - bool isnull; - - isnull = tok == JSON_TOKEN_NULL; - - if (astart != NULL) - (*astart) (sem->semstate, isnull); - - /* an array element is any object, array or scalar */ - switch (tok) - { - case JSON_TOKEN_OBJECT_START: - parse_object(lex, sem); - break; - case JSON_TOKEN_ARRAY_START: - parse_array(lex, sem); - break; - default: - parse_scalar(lex, sem); - } - - if (aend != NULL) - (*aend) (sem->semstate, isnull); -} - -static void -parse_array(JsonLexContext *lex, JsonSemAction *sem) -{ - /* - * 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; - - check_stack_depth(); - - if (astart != NULL) - (*astart) (sem->semstate); - - /* - * 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++; - - lex_expect(JSON_PARSE_ARRAY_START, lex, JSON_TOKEN_ARRAY_START); - if (lex_peek(lex) != JSON_TOKEN_ARRAY_END) - { - - parse_array_element(lex, sem); - - while (lex_accept(lex, JSON_TOKEN_COMMA, NULL)) - parse_array_element(lex, sem); - } - - lex_expect(JSON_PARSE_ARRAY_NEXT, lex, JSON_TOKEN_ARRAY_END); - - lex->lex_level--; - - if (aend != NULL) - (*aend) (sem->semstate); -} - -/* - * Lex one token from the input stream. - */ -static inline void -json_lex(JsonLexContext *lex) -{ - char *s; - int len; - - /* Skip leading whitespace. */ - s = lex->token_terminator; - len = s - lex->input; - while (len < lex->input_length && - (*s == ' ' || *s == '\t' || *s == '\n' || *s == '\r')) - { - if (*s == '\n') - ++lex->line_number; - ++s; - ++len; - } - lex->token_start = s; - - /* Determine token type. */ - if (len >= lex->input_length) - { - 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 */ - json_lex_string(lex); - lex->token_type = JSON_TOKEN_STRING; - break; - case '-': - /* Negative number. */ - json_lex_number(lex, s + 1, NULL, NULL); - 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. */ - json_lex_number(lex, s, NULL, NULL); - 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 - s < lex->input_length - len && 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; - report_invalid_token(lex); - } - - /* - * 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 - report_invalid_token(lex); - } - else if (p - s == 5 && memcmp(s, "false", 5) == 0) - lex->token_type = JSON_TOKEN_FALSE; - else - report_invalid_token(lex); - - } - } /* end of switch */ -} - -/* - * The next token in the input stream is known to be a string; lex it. - */ -static inline void -json_lex_string(JsonLexContext *lex) -{ - char *s; - int len; - int hi_surrogate = -1; - - if (lex->strval != NULL) - resetStringInfo(lex->strval); - - Assert(lex->input_length > 0); - s = lex->token_start; - len = lex->token_start - lex->input; - for (;;) - { - s++; - len++; - /* Premature end of the string. */ - if (len >= lex->input_length) - { - lex->token_terminator = s; - report_invalid_token(lex); - } - else if (*s == '"') - break; - else if ((unsigned char) *s < 32) - { - /* Per RFC4627, these characters MUST be escaped. */ - /* Since *s isn't printable, exclude it from the context string */ - lex->token_terminator = s; - ereport(ERROR, - (errcode(ERRCODE_INVALID_TEXT_REPRESENTATION), - errmsg("invalid input syntax for type %s", "json"), - errdetail("Character with value 0x%02x must be escaped.", - (unsigned char) *s), - report_json_context(lex))); - } - else if (*s == '\\') - { - /* OK, we have an escape character. */ - s++; - len++; - if (len >= lex->input_length) - { - lex->token_terminator = s; - report_invalid_token(lex); - } - else if (*s == 'u') - { - int i; - int ch = 0; - - for (i = 1; i <= 4; i++) - { - s++; - len++; - if (len >= lex->input_length) - { - lex->token_terminator = s; - report_invalid_token(lex); - } - 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 - { - lex->token_terminator = s + pg_mblen(s); - ereport(ERROR, - (errcode(ERRCODE_INVALID_TEXT_REPRESENTATION), - errmsg("invalid input syntax for type %s", - "json"), - errdetail("\"\\u\" must be followed by four hexadecimal digits."), - report_json_context(lex))); - } - } - if (lex->strval != NULL) - { - char utf8str[5]; - int utf8len; - - if (ch >= 0xd800 && ch <= 0xdbff) - { - if (hi_surrogate != -1) - ereport(ERROR, - (errcode(ERRCODE_INVALID_TEXT_REPRESENTATION), - errmsg("invalid input syntax for type %s", - "json"), - errdetail("Unicode high surrogate must not follow a high surrogate."), - report_json_context(lex))); - hi_surrogate = (ch & 0x3ff) << 10; - continue; - } - else if (ch >= 0xdc00 && ch <= 0xdfff) - { - if (hi_surrogate == -1) - ereport(ERROR, - (errcode(ERRCODE_INVALID_TEXT_REPRESENTATION), - errmsg("invalid input syntax for type %s", "json"), - errdetail("Unicode low surrogate must follow a high surrogate."), - report_json_context(lex))); - ch = 0x10000 + hi_surrogate + (ch & 0x3ff); - hi_surrogate = -1; - } - - if (hi_surrogate != -1) - ereport(ERROR, - (errcode(ERRCODE_INVALID_TEXT_REPRESENTATION), - errmsg("invalid input syntax for type %s", "json"), - errdetail("Unicode low surrogate must follow a high surrogate."), - report_json_context(lex))); - - /* - * For UTF8, replace the escape sequence by the actual - * utf8 character in lex->strval. Do this also for other - * encodings if the escape designates an ASCII character, - * otherwise raise an error. - */ - - if (ch == 0) - { - /* We can't allow this, since our TEXT type doesn't */ - ereport(ERROR, - (errcode(ERRCODE_UNTRANSLATABLE_CHARACTER), - errmsg("unsupported Unicode escape sequence"), - errdetail("\\u0000 cannot be converted to text."), - report_json_context(lex))); - } - else if (GetDatabaseEncoding() == PG_UTF8) - { - unicode_to_utf8(ch, (unsigned char *) utf8str); - utf8len = pg_utf_mblen((unsigned char *) utf8str); - appendBinaryStringInfo(lex->strval, utf8str, utf8len); - } - else if (ch <= 0x007f) - { - /* - * This is the only way to designate things like a - * form feed character in JSON, so it's useful in all - * encodings. - */ - appendStringInfoChar(lex->strval, (char) ch); - } - else - { - ereport(ERROR, - (errcode(ERRCODE_UNTRANSLATABLE_CHARACTER), - errmsg("unsupported Unicode escape sequence"), - errdetail("Unicode escape values cannot be used for code point values above 007F when the server encoding is not UTF8."), - report_json_context(lex))); - } - - } - } - else if (lex->strval != NULL) - { - if (hi_surrogate != -1) - ereport(ERROR, - (errcode(ERRCODE_INVALID_TEXT_REPRESENTATION), - errmsg("invalid input syntax for type %s", - "json"), - errdetail("Unicode low surrogate must follow a high surrogate."), - report_json_context(lex))); - - 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 error out. */ - lex->token_terminator = s + pg_mblen(s); - ereport(ERROR, - (errcode(ERRCODE_INVALID_TEXT_REPRESENTATION), - errmsg("invalid input syntax for type %s", - "json"), - errdetail("Escape sequence \"\\%s\" is invalid.", - extract_mb_char(s)), - report_json_context(lex))); - } - } - 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_terminator = s + pg_mblen(s); - ereport(ERROR, - (errcode(ERRCODE_INVALID_TEXT_REPRESENTATION), - errmsg("invalid input syntax for type %s", "json"), - errdetail("Escape sequence \"\\%s\" is invalid.", - extract_mb_char(s)), - report_json_context(lex))); - } - - } - else if (lex->strval != NULL) - { - if (hi_surrogate != -1) - ereport(ERROR, - (errcode(ERRCODE_INVALID_TEXT_REPRESENTATION), - errmsg("invalid input syntax for type %s", "json"), - errdetail("Unicode low surrogate must follow a high surrogate."), - report_json_context(lex))); - - appendStringInfoChar(lex->strval, *s); - } - - } - - if (hi_surrogate != -1) - ereport(ERROR, - (errcode(ERRCODE_INVALID_TEXT_REPRESENTATION), - errmsg("invalid input syntax for type %s", "json"), - errdetail("Unicode low surrogate must follow a high surrogate."), - report_json_context(lex))); - - /* Hooray, we found the end of the string! */ - lex->prev_token_terminator = lex->token_terminator; - lex->token_terminator = s + 1; -} - -/* - * The next token in the input stream is known to be a number; lex it. - * - * In JSON, a number consists of four parts: - * - * (1) An optional minus sign ('-'). - * - * (2) Either a single '0', or a string of one or more digits that does not - * begin with a '0'. - * - * (3) An optional decimal part, consisting of a period ('.') followed by - * one or more digits. (Note: While this part can be omitted - * completely, it's not OK to have only the decimal point without - * any digits afterwards.) - * - * (4) An optional exponent part, consisting of 'e' or 'E', optionally - * followed by '+' or '-', followed by one or more digits. (Note: - * As with the decimal part, if 'e' or 'E' is present, it must be - * followed by at least one digit.) - * - * The 's' argument to this function points to the ostensible beginning - * of part 2 - i.e. the character after any optional minus sign, or the - * first character of the string if there is none. - * - * If num_err is not NULL, we return an error flag to *num_err rather than - * raising an error for a badly-formed number. Also, if total_len is not NULL - * the distance from lex->input to the token end+1 is returned to *total_len. - */ -static inline void -json_lex_number(JsonLexContext *lex, char *s, - bool *num_err, int *total_len) -{ - 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) - report_invalid_token(lex); - } -} - -/* - * Report a parse error. - * - * lex->token_start and lex->token_terminator must identify the current token. - */ -static void -report_parse_error(JsonParseContext ctx, JsonLexContext *lex) -{ - char *token; - int toklen; - - /* Handle case where the input ended prematurely. */ - if (lex->token_start == NULL || lex->token_type == JSON_TOKEN_END) - ereport(ERROR, - (errcode(ERRCODE_INVALID_TEXT_REPRESENTATION), - errmsg("invalid input syntax for type %s", "json"), - errdetail("The input string ended unexpectedly."), - report_json_context(lex))); - - /* Separate out the current token. */ - toklen = lex->token_terminator - lex->token_start; - token = palloc(toklen + 1); - memcpy(token, lex->token_start, toklen); - token[toklen] = '\0'; - - /* Complain, with the appropriate detail message. */ - if (ctx == JSON_PARSE_END) - ereport(ERROR, - (errcode(ERRCODE_INVALID_TEXT_REPRESENTATION), - errmsg("invalid input syntax for type %s", "json"), - errdetail("Expected end of input, but found \"%s\".", - token), - report_json_context(lex))); - else - { - switch (ctx) - { - case JSON_PARSE_VALUE: - ereport(ERROR, - (errcode(ERRCODE_INVALID_TEXT_REPRESENTATION), - errmsg("invalid input syntax for type %s", "json"), - errdetail("Expected JSON value, but found \"%s\".", - token), - report_json_context(lex))); - break; - case JSON_PARSE_STRING: - ereport(ERROR, - (errcode(ERRCODE_INVALID_TEXT_REPRESENTATION), - errmsg("invalid input syntax for type %s", "json"), - errdetail("Expected string, but found \"%s\".", - token), - report_json_context(lex))); - break; - case JSON_PARSE_ARRAY_START: - ereport(ERROR, - (errcode(ERRCODE_INVALID_TEXT_REPRESENTATION), - errmsg("invalid input syntax for type %s", "json"), - errdetail("Expected array element or \"]\", but found \"%s\".", - token), - report_json_context(lex))); - break; - case JSON_PARSE_ARRAY_NEXT: - ereport(ERROR, - (errcode(ERRCODE_INVALID_TEXT_REPRESENTATION), - errmsg("invalid input syntax for type %s", "json"), - errdetail("Expected \",\" or \"]\", but found \"%s\".", - token), - report_json_context(lex))); - break; - case JSON_PARSE_OBJECT_START: - ereport(ERROR, - (errcode(ERRCODE_INVALID_TEXT_REPRESENTATION), - errmsg("invalid input syntax for type %s", "json"), - errdetail("Expected string or \"}\", but found \"%s\".", - token), - report_json_context(lex))); - break; - case JSON_PARSE_OBJECT_LABEL: - ereport(ERROR, - (errcode(ERRCODE_INVALID_TEXT_REPRESENTATION), - errmsg("invalid input syntax for type %s", "json"), - errdetail("Expected \":\", but found \"%s\".", - token), - report_json_context(lex))); - break; - case JSON_PARSE_OBJECT_NEXT: - ereport(ERROR, - (errcode(ERRCODE_INVALID_TEXT_REPRESENTATION), - errmsg("invalid input syntax for type %s", "json"), - errdetail("Expected \",\" or \"}\", but found \"%s\".", - token), - report_json_context(lex))); - break; - case JSON_PARSE_OBJECT_COMMA: - ereport(ERROR, - (errcode(ERRCODE_INVALID_TEXT_REPRESENTATION), - errmsg("invalid input syntax for type %s", "json"), - errdetail("Expected string, but found \"%s\".", - token), - report_json_context(lex))); - break; - default: - elog(ERROR, "unexpected json parse state: %d", ctx); - } - } -} - -/* - * Report an invalid input token. - * - * lex->token_start and lex->token_terminator must identify the token. - */ -static void -report_invalid_token(JsonLexContext *lex) -{ - char *token; - int toklen; - - /* Separate out the offending token. */ - toklen = lex->token_terminator - lex->token_start; - token = palloc(toklen + 1); - memcpy(token, lex->token_start, toklen); - token[toklen] = '\0'; - - ereport(ERROR, - (errcode(ERRCODE_INVALID_TEXT_REPRESENTATION), - errmsg("invalid input syntax for type %s", "json"), - errdetail("Token \"%s\" is invalid.", token), - report_json_context(lex))); -} - -/* - * Report a CONTEXT line for bogus JSON input. - * - * lex->token_terminator must be set to identify the spot where we detected - * the error. Note that lex->token_start might be NULL, in case we recognized - * error at EOF. - * - * The return value isn't meaningful, but we make it non-void so that this - * can be invoked inside ereport(). - */ -static int -report_json_context(JsonLexContext *lex) -{ - const char *context_start; - const char *context_end; - const char *line_start; - int line_number; - char *ctxt; - int ctxtlen; - const char *prefix; - const char *suffix; - - /* Choose boundaries for the part of the input we will display */ - context_start = lex->input; - context_end = lex->token_terminator; - line_start = context_start; - line_number = 1; - for (;;) - { - /* Always advance over newlines */ - if (context_start < context_end && *context_start == '\n') - { - context_start++; - line_start = context_start; - line_number++; - continue; - } - /* Otherwise, done as soon as we are close enough to context_end */ - if (context_end - context_start < 50) - break; - /* Advance to next multibyte character */ - if (IS_HIGHBIT_SET(*context_start)) - context_start += pg_mblen(context_start); - else - context_start++; - } - - /* - * We add "..." to indicate that the excerpt doesn't start at the - * beginning of the line ... but if we're within 3 characters of the - * beginning of the line, we might as well just show the whole line. - */ - if (context_start - line_start <= 3) - context_start = line_start; - - /* Get a null-terminated copy of the data to present */ - ctxtlen = context_end - context_start; - ctxt = palloc(ctxtlen + 1); - memcpy(ctxt, context_start, ctxtlen); - ctxt[ctxtlen] = '\0'; - - /* - * Show the context, prefixing "..." if not starting at start of line, and - * suffixing "..." if not ending at end of line. - */ - prefix = (context_start > line_start) ? "..." : ""; - suffix = (lex->token_type != JSON_TOKEN_END && context_end - lex->input < lex->input_length && *context_end != '\n' && *context_end != '\r') ? "..." : ""; - - return errcontext("JSON data, line %d: %s%s%s", - line_number, prefix, ctxt, suffix); -} - -/* - * Extract a single, possibly multi-byte char from the input string. - */ -static char * -extract_mb_char(char *s) -{ - char *res; - int len; - - len = pg_mblen(s); - res = palloc(len + 1); - memcpy(res, s, len); - res[len] = '\0'; - - return res; -} - -/* * Determine how we want to print values of a given type in datum_to_json. * * Given the datatype OID, return its JsonTypeCategory, as well as the type's @@ -2547,7 +1343,7 @@ json_typeof(PG_FUNCTION_ARGS) /* Lex exactly one token from the input and check its type. */ json_lex(lex); - tok = lex_peek(lex); + tok = lex->token_type; switch (tok) { case JSON_TOKEN_OBJECT_START: diff --git a/src/backend/utils/adt/jsonapi.c b/src/backend/utils/adt/jsonapi.c new file mode 100644 index 00000000000..fc8af9f861e --- /dev/null +++ b/src/backend/utils/adt/jsonapi.c @@ -0,0 +1,1216 @@ +/*------------------------------------------------------------------------- + * + * jsonapi.c + * JSON parser and lexer interfaces + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * IDENTIFICATION + * src/backend/utils/adt/jsonapi.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "mb/pg_wchar.h" +#include "miscadmin.h" +#include "utils/jsonapi.h" + +/* + * The context of the parser is maintained by the recursive descent + * mechanism, but is passed explicitly to the error reporting routine + * for better diagnostics. + */ +typedef enum /* contexts of JSON parser */ +{ + 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; + +static inline void json_lex_string(JsonLexContext *lex); +static inline void json_lex_number(JsonLexContext *lex, char *s, + bool *num_err, int *total_len); +static inline void parse_scalar(JsonLexContext *lex, JsonSemAction *sem); +static void parse_object_field(JsonLexContext *lex, JsonSemAction *sem); +static void parse_object(JsonLexContext *lex, JsonSemAction *sem); +static void parse_array_element(JsonLexContext *lex, JsonSemAction *sem); +static void parse_array(JsonLexContext *lex, JsonSemAction *sem); +static void report_parse_error(JsonParseContext ctx, JsonLexContext *lex) pg_attribute_noreturn(); +static void report_invalid_token(JsonLexContext *lex) pg_attribute_noreturn(); +static int report_json_context(JsonLexContext *lex); +static char *extract_mb_char(char *s); + +/* the null action object used for pure validation */ +JsonSemAction nullSemAction = +{ + NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL +}; + +/* Recursive Descent parser support routines */ + +/* + * lex_peek + * + * what is the current look_ahead token? +*/ +static inline JsonTokenType +lex_peek(JsonLexContext *lex) +{ + return lex->token_type; +} + +/* + * lex_accept + * + * accept the look_ahead token and move the lexer to the next token if the + * look_ahead token matches the token parameter. In that case, and if required, + * also hand back the de-escaped lexeme. + * + * returns true if the token matched, false otherwise. + */ +static inline bool +lex_accept(JsonLexContext *lex, JsonTokenType token, char **lexeme) +{ + if (lex->token_type == token) + { + if (lexeme != NULL) + { + if (lex->token_type == JSON_TOKEN_STRING) + { + if (lex->strval != NULL) + *lexeme = pstrdup(lex->strval->data); + } + else + { + int len = (lex->token_terminator - lex->token_start); + char *tokstr = palloc(len + 1); + + memcpy(tokstr, lex->token_start, len); + tokstr[len] = '\0'; + *lexeme = tokstr; + } + } + json_lex(lex); + return true; + } + return false; +} + +/* + * lex_accept + * + * move the lexer to the next token if the current look_ahead token matches + * the parameter token. Otherwise, report an error. + */ +static inline void +lex_expect(JsonParseContext ctx, JsonLexContext *lex, JsonTokenType token) +{ + if (!lex_accept(lex, token, NULL)) + report_parse_error(ctx, lex); +} + +/* chars to consider as part of an alphanumeric token */ +#define JSON_ALPHANUMERIC_CHAR(c) \ + (((c) >= 'a' && (c) <= 'z') || \ + ((c) >= 'A' && (c) <= 'Z') || \ + ((c) >= '0' && (c) <= '9') || \ + (c) == '_' || \ + IS_HIGHBIT_SET(c)) + +/* + * Utility function to check if a string is a valid JSON number. + * + * str is of length len, and need not be null-terminated. + */ +bool +IsValidJsonNumber(const char *str, int len) +{ + 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); +} + +/* + * makeJsonLexContext + * + * lex constructor, with or without StringInfo object + * for de-escaped lexemes. + * + * Without is better as it makes the processing faster, so only make one + * if really required. + * + * If you already have the json as a text* value, use the first of these + * functions, otherwise use makeJsonLexContextCstringLen(). + */ +JsonLexContext * +makeJsonLexContext(text *json, bool need_escapes) +{ + return makeJsonLexContextCstringLen(VARDATA_ANY(json), + VARSIZE_ANY_EXHDR(json), + need_escapes); +} + +JsonLexContext * +makeJsonLexContextCstringLen(char *json, int len, bool need_escapes) +{ + JsonLexContext *lex = palloc0(sizeof(JsonLexContext)); + + lex->input = lex->token_terminator = lex->line_start = json; + lex->line_number = 1; + lex->input_length = len; + if (need_escapes) + lex->strval = makeStringInfo(); + return lex; +} + +/* + * pg_parse_json + * + * Publicly visible entry point for the JSON parser. + * + * lex is a lexing context, set up for the json to be processed by calling + * makeJsonLexContext(). sem is a structure of function pointers to semantic + * action routines to be called at appropriate spots during parsing, and a + * pointer to a state object to be passed to those routines. + */ +void +pg_parse_json(JsonLexContext *lex, JsonSemAction *sem) +{ + JsonTokenType tok; + + /* get the initial token */ + json_lex(lex); + + tok = lex_peek(lex); + + /* parse by recursive descent */ + switch (tok) + { + case JSON_TOKEN_OBJECT_START: + parse_object(lex, sem); + break; + case JSON_TOKEN_ARRAY_START: + parse_array(lex, sem); + break; + default: + parse_scalar(lex, sem); /* json can be a bare scalar */ + } + + lex_expect(JSON_PARSE_END, lex, JSON_TOKEN_END); + +} + +/* + * json_count_array_elements + * + * Returns number of array elements in lex context at start of array token + * until end of array token at same nesting level. + * + * Designed to be called from array_start routines. + */ +int +json_count_array_elements(JsonLexContext *lex) +{ + JsonLexContext copylex; + int count; + + /* + * 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(©lex, lex, sizeof(JsonLexContext)); + copylex.strval = NULL; /* not interested in values here */ + copylex.lex_level++; + + count = 0; + lex_expect(JSON_PARSE_ARRAY_START, ©lex, JSON_TOKEN_ARRAY_START); + if (lex_peek(©lex) != JSON_TOKEN_ARRAY_END) + { + do + { + count++; + parse_array_element(©lex, &nullSemAction); + } + while (lex_accept(©lex, JSON_TOKEN_COMMA, NULL)); + } + lex_expect(JSON_PARSE_ARRAY_NEXT, ©lex, JSON_TOKEN_ARRAY_END); + + return count; +} + +/* + * Recursive Descent parse routines. There is one for each structural + * element in a json document: + * - scalar (string, number, true, false, null) + * - array ( [ ] ) + * - array element + * - object ( { } ) + * - object field + */ +static inline void +parse_scalar(JsonLexContext *lex, JsonSemAction *sem) +{ + char *val = NULL; + json_scalar_action sfunc = sem->scalar; + char **valaddr; + JsonTokenType tok = lex_peek(lex); + + valaddr = sfunc == NULL ? NULL : &val; + + /* a scalar must be a string, a number, true, false, or null */ + switch (tok) + { + case JSON_TOKEN_TRUE: + lex_accept(lex, JSON_TOKEN_TRUE, valaddr); + break; + case JSON_TOKEN_FALSE: + lex_accept(lex, JSON_TOKEN_FALSE, valaddr); + break; + case JSON_TOKEN_NULL: + lex_accept(lex, JSON_TOKEN_NULL, valaddr); + break; + case JSON_TOKEN_NUMBER: + lex_accept(lex, JSON_TOKEN_NUMBER, valaddr); + break; + case JSON_TOKEN_STRING: + lex_accept(lex, JSON_TOKEN_STRING, valaddr); + break; + default: + report_parse_error(JSON_PARSE_VALUE, lex); + } + + if (sfunc != NULL) + (*sfunc) (sem->semstate, val, tok); +} + +static void +parse_object_field(JsonLexContext *lex, JsonSemAction *sem) +{ + /* + * 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; + char **fnameaddr = NULL; + JsonTokenType tok; + + if (ostart != NULL || oend != NULL) + fnameaddr = &fname; + + if (!lex_accept(lex, JSON_TOKEN_STRING, fnameaddr)) + report_parse_error(JSON_PARSE_STRING, lex); + + lex_expect(JSON_PARSE_OBJECT_LABEL, lex, JSON_TOKEN_COLON); + + tok = lex_peek(lex); + isnull = tok == JSON_TOKEN_NULL; + + if (ostart != NULL) + (*ostart) (sem->semstate, fname, isnull); + + switch (tok) + { + case JSON_TOKEN_OBJECT_START: + parse_object(lex, sem); + break; + case JSON_TOKEN_ARRAY_START: + parse_array(lex, sem); + break; + default: + parse_scalar(lex, sem); + } + + if (oend != NULL) + (*oend) (sem->semstate, fname, isnull); +} + +static void +parse_object(JsonLexContext *lex, JsonSemAction *sem) +{ + /* + * 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; + + check_stack_depth(); + + if (ostart != NULL) + (*ostart) (sem->semstate); + + /* + * 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++; + + /* we know this will succeed, just clearing the token */ + lex_expect(JSON_PARSE_OBJECT_START, lex, JSON_TOKEN_OBJECT_START); + + tok = lex_peek(lex); + switch (tok) + { + case JSON_TOKEN_STRING: + parse_object_field(lex, sem); + while (lex_accept(lex, JSON_TOKEN_COMMA, NULL)) + parse_object_field(lex, sem); + break; + case JSON_TOKEN_OBJECT_END: + break; + default: + /* case of an invalid initial token inside the object */ + report_parse_error(JSON_PARSE_OBJECT_START, lex); + } + + lex_expect(JSON_PARSE_OBJECT_NEXT, lex, JSON_TOKEN_OBJECT_END); + + lex->lex_level--; + + if (oend != NULL) + (*oend) (sem->semstate); +} + +static void +parse_array_element(JsonLexContext *lex, JsonSemAction *sem) +{ + json_aelem_action astart = sem->array_element_start; + json_aelem_action aend = sem->array_element_end; + JsonTokenType tok = lex_peek(lex); + + bool isnull; + + isnull = tok == JSON_TOKEN_NULL; + + if (astart != NULL) + (*astart) (sem->semstate, isnull); + + /* an array element is any object, array or scalar */ + switch (tok) + { + case JSON_TOKEN_OBJECT_START: + parse_object(lex, sem); + break; + case JSON_TOKEN_ARRAY_START: + parse_array(lex, sem); + break; + default: + parse_scalar(lex, sem); + } + + if (aend != NULL) + (*aend) (sem->semstate, isnull); +} + +static void +parse_array(JsonLexContext *lex, JsonSemAction *sem) +{ + /* + * 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; + + check_stack_depth(); + + if (astart != NULL) + (*astart) (sem->semstate); + + /* + * 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++; + + lex_expect(JSON_PARSE_ARRAY_START, lex, JSON_TOKEN_ARRAY_START); + if (lex_peek(lex) != JSON_TOKEN_ARRAY_END) + { + + parse_array_element(lex, sem); + + while (lex_accept(lex, JSON_TOKEN_COMMA, NULL)) + parse_array_element(lex, sem); + } + + lex_expect(JSON_PARSE_ARRAY_NEXT, lex, JSON_TOKEN_ARRAY_END); + + lex->lex_level--; + + if (aend != NULL) + (*aend) (sem->semstate); +} + +/* + * Lex one token from the input stream. + */ +void +json_lex(JsonLexContext *lex) +{ + char *s; + int len; + + /* Skip leading whitespace. */ + s = lex->token_terminator; + len = s - lex->input; + while (len < lex->input_length && + (*s == ' ' || *s == '\t' || *s == '\n' || *s == '\r')) + { + if (*s == '\n') + ++lex->line_number; + ++s; + ++len; + } + lex->token_start = s; + + /* Determine token type. */ + if (len >= lex->input_length) + { + 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 */ + json_lex_string(lex); + lex->token_type = JSON_TOKEN_STRING; + break; + case '-': + /* Negative number. */ + json_lex_number(lex, s + 1, NULL, NULL); + 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. */ + json_lex_number(lex, s, NULL, NULL); + 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 - s < lex->input_length - len && 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; + report_invalid_token(lex); + } + + /* + * 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 + report_invalid_token(lex); + } + else if (p - s == 5 && memcmp(s, "false", 5) == 0) + lex->token_type = JSON_TOKEN_FALSE; + else + report_invalid_token(lex); + + } + } /* end of switch */ +} + +/* + * The next token in the input stream is known to be a string; lex it. + */ +static inline void +json_lex_string(JsonLexContext *lex) +{ + char *s; + int len; + int hi_surrogate = -1; + + if (lex->strval != NULL) + resetStringInfo(lex->strval); + + Assert(lex->input_length > 0); + s = lex->token_start; + len = lex->token_start - lex->input; + for (;;) + { + s++; + len++; + /* Premature end of the string. */ + if (len >= lex->input_length) + { + lex->token_terminator = s; + report_invalid_token(lex); + } + else if (*s == '"') + break; + else if ((unsigned char) *s < 32) + { + /* Per RFC4627, these characters MUST be escaped. */ + /* Since *s isn't printable, exclude it from the context string */ + lex->token_terminator = s; + ereport(ERROR, + (errcode(ERRCODE_INVALID_TEXT_REPRESENTATION), + errmsg("invalid input syntax for type %s", "json"), + errdetail("Character with value 0x%02x must be escaped.", + (unsigned char) *s), + report_json_context(lex))); + } + else if (*s == '\\') + { + /* OK, we have an escape character. */ + s++; + len++; + if (len >= lex->input_length) + { + lex->token_terminator = s; + report_invalid_token(lex); + } + else if (*s == 'u') + { + int i; + int ch = 0; + + for (i = 1; i <= 4; i++) + { + s++; + len++; + if (len >= lex->input_length) + { + lex->token_terminator = s; + report_invalid_token(lex); + } + 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 + { + lex->token_terminator = s + pg_mblen(s); + ereport(ERROR, + (errcode(ERRCODE_INVALID_TEXT_REPRESENTATION), + errmsg("invalid input syntax for type %s", + "json"), + errdetail("\"\\u\" must be followed by four hexadecimal digits."), + report_json_context(lex))); + } + } + if (lex->strval != NULL) + { + char utf8str[5]; + int utf8len; + + if (ch >= 0xd800 && ch <= 0xdbff) + { + if (hi_surrogate != -1) + ereport(ERROR, + (errcode(ERRCODE_INVALID_TEXT_REPRESENTATION), + errmsg("invalid input syntax for type %s", + "json"), + errdetail("Unicode high surrogate must not follow a high surrogate."), + report_json_context(lex))); + hi_surrogate = (ch & 0x3ff) << 10; + continue; + } + else if (ch >= 0xdc00 && ch <= 0xdfff) + { + if (hi_surrogate == -1) + ereport(ERROR, + (errcode(ERRCODE_INVALID_TEXT_REPRESENTATION), + errmsg("invalid input syntax for type %s", "json"), + errdetail("Unicode low surrogate must follow a high surrogate."), + report_json_context(lex))); + ch = 0x10000 + hi_surrogate + (ch & 0x3ff); + hi_surrogate = -1; + } + + if (hi_surrogate != -1) + ereport(ERROR, + (errcode(ERRCODE_INVALID_TEXT_REPRESENTATION), + errmsg("invalid input syntax for type %s", "json"), + errdetail("Unicode low surrogate must follow a high surrogate."), + report_json_context(lex))); + + /* + * For UTF8, replace the escape sequence by the actual + * utf8 character in lex->strval. Do this also for other + * encodings if the escape designates an ASCII character, + * otherwise raise an error. + */ + + if (ch == 0) + { + /* We can't allow this, since our TEXT type doesn't */ + ereport(ERROR, + (errcode(ERRCODE_UNTRANSLATABLE_CHARACTER), + errmsg("unsupported Unicode escape sequence"), + errdetail("\\u0000 cannot be converted to text."), + report_json_context(lex))); + } + else if (GetDatabaseEncoding() == PG_UTF8) + { + unicode_to_utf8(ch, (unsigned char *) utf8str); + utf8len = pg_utf_mblen((unsigned char *) utf8str); + appendBinaryStringInfo(lex->strval, utf8str, utf8len); + } + else if (ch <= 0x007f) + { + /* + * This is the only way to designate things like a + * form feed character in JSON, so it's useful in all + * encodings. + */ + appendStringInfoChar(lex->strval, (char) ch); + } + else + { + ereport(ERROR, + (errcode(ERRCODE_UNTRANSLATABLE_CHARACTER), + errmsg("unsupported Unicode escape sequence"), + errdetail("Unicode escape values cannot be used for code point values above 007F when the server encoding is not UTF8."), + report_json_context(lex))); + } + + } + } + else if (lex->strval != NULL) + { + if (hi_surrogate != -1) + ereport(ERROR, + (errcode(ERRCODE_INVALID_TEXT_REPRESENTATION), + errmsg("invalid input syntax for type %s", + "json"), + errdetail("Unicode low surrogate must follow a high surrogate."), + report_json_context(lex))); + + 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 error out. */ + lex->token_terminator = s + pg_mblen(s); + ereport(ERROR, + (errcode(ERRCODE_INVALID_TEXT_REPRESENTATION), + errmsg("invalid input syntax for type %s", + "json"), + errdetail("Escape sequence \"\\%s\" is invalid.", + extract_mb_char(s)), + report_json_context(lex))); + } + } + 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_terminator = s + pg_mblen(s); + ereport(ERROR, + (errcode(ERRCODE_INVALID_TEXT_REPRESENTATION), + errmsg("invalid input syntax for type %s", "json"), + errdetail("Escape sequence \"\\%s\" is invalid.", + extract_mb_char(s)), + report_json_context(lex))); + } + + } + else if (lex->strval != NULL) + { + if (hi_surrogate != -1) + ereport(ERROR, + (errcode(ERRCODE_INVALID_TEXT_REPRESENTATION), + errmsg("invalid input syntax for type %s", "json"), + errdetail("Unicode low surrogate must follow a high surrogate."), + report_json_context(lex))); + + appendStringInfoChar(lex->strval, *s); + } + + } + + if (hi_surrogate != -1) + ereport(ERROR, + (errcode(ERRCODE_INVALID_TEXT_REPRESENTATION), + errmsg("invalid input syntax for type %s", "json"), + errdetail("Unicode low surrogate must follow a high surrogate."), + report_json_context(lex))); + + /* Hooray, we found the end of the string! */ + lex->prev_token_terminator = lex->token_terminator; + lex->token_terminator = s + 1; +} + +/* + * The next token in the input stream is known to be a number; lex it. + * + * In JSON, a number consists of four parts: + * + * (1) An optional minus sign ('-'). + * + * (2) Either a single '0', or a string of one or more digits that does not + * begin with a '0'. + * + * (3) An optional decimal part, consisting of a period ('.') followed by + * one or more digits. (Note: While this part can be omitted + * completely, it's not OK to have only the decimal point without + * any digits afterwards.) + * + * (4) An optional exponent part, consisting of 'e' or 'E', optionally + * followed by '+' or '-', followed by one or more digits. (Note: + * As with the decimal part, if 'e' or 'E' is present, it must be + * followed by at least one digit.) + * + * The 's' argument to this function points to the ostensible beginning + * of part 2 - i.e. the character after any optional minus sign, or the + * first character of the string if there is none. + * + * If num_err is not NULL, we return an error flag to *num_err rather than + * raising an error for a badly-formed number. Also, if total_len is not NULL + * the distance from lex->input to the token end+1 is returned to *total_len. + */ +static inline void +json_lex_number(JsonLexContext *lex, char *s, + bool *num_err, int *total_len) +{ + 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) + report_invalid_token(lex); + } +} + +/* + * Report a parse error. + * + * lex->token_start and lex->token_terminator must identify the current token. + */ +static void +report_parse_error(JsonParseContext ctx, JsonLexContext *lex) +{ + char *token; + int toklen; + + /* Handle case where the input ended prematurely. */ + if (lex->token_start == NULL || lex->token_type == JSON_TOKEN_END) + ereport(ERROR, + (errcode(ERRCODE_INVALID_TEXT_REPRESENTATION), + errmsg("invalid input syntax for type %s", "json"), + errdetail("The input string ended unexpectedly."), + report_json_context(lex))); + + /* Separate out the current token. */ + toklen = lex->token_terminator - lex->token_start; + token = palloc(toklen + 1); + memcpy(token, lex->token_start, toklen); + token[toklen] = '\0'; + + /* Complain, with the appropriate detail message. */ + if (ctx == JSON_PARSE_END) + ereport(ERROR, + (errcode(ERRCODE_INVALID_TEXT_REPRESENTATION), + errmsg("invalid input syntax for type %s", "json"), + errdetail("Expected end of input, but found \"%s\".", + token), + report_json_context(lex))); + else + { + switch (ctx) + { + case JSON_PARSE_VALUE: + ereport(ERROR, + (errcode(ERRCODE_INVALID_TEXT_REPRESENTATION), + errmsg("invalid input syntax for type %s", "json"), + errdetail("Expected JSON value, but found \"%s\".", + token), + report_json_context(lex))); + break; + case JSON_PARSE_STRING: + ereport(ERROR, + (errcode(ERRCODE_INVALID_TEXT_REPRESENTATION), + errmsg("invalid input syntax for type %s", "json"), + errdetail("Expected string, but found \"%s\".", + token), + report_json_context(lex))); + break; + case JSON_PARSE_ARRAY_START: + ereport(ERROR, + (errcode(ERRCODE_INVALID_TEXT_REPRESENTATION), + errmsg("invalid input syntax for type %s", "json"), + errdetail("Expected array element or \"]\", but found \"%s\".", + token), + report_json_context(lex))); + break; + case JSON_PARSE_ARRAY_NEXT: + ereport(ERROR, + (errcode(ERRCODE_INVALID_TEXT_REPRESENTATION), + errmsg("invalid input syntax for type %s", "json"), + errdetail("Expected \",\" or \"]\", but found \"%s\".", + token), + report_json_context(lex))); + break; + case JSON_PARSE_OBJECT_START: + ereport(ERROR, + (errcode(ERRCODE_INVALID_TEXT_REPRESENTATION), + errmsg("invalid input syntax for type %s", "json"), + errdetail("Expected string or \"}\", but found \"%s\".", + token), + report_json_context(lex))); + break; + case JSON_PARSE_OBJECT_LABEL: + ereport(ERROR, + (errcode(ERRCODE_INVALID_TEXT_REPRESENTATION), + errmsg("invalid input syntax for type %s", "json"), + errdetail("Expected \":\", but found \"%s\".", + token), + report_json_context(lex))); + break; + case JSON_PARSE_OBJECT_NEXT: + ereport(ERROR, + (errcode(ERRCODE_INVALID_TEXT_REPRESENTATION), + errmsg("invalid input syntax for type %s", "json"), + errdetail("Expected \",\" or \"}\", but found \"%s\".", + token), + report_json_context(lex))); + break; + case JSON_PARSE_OBJECT_COMMA: + ereport(ERROR, + (errcode(ERRCODE_INVALID_TEXT_REPRESENTATION), + errmsg("invalid input syntax for type %s", "json"), + errdetail("Expected string, but found \"%s\".", + token), + report_json_context(lex))); + break; + default: + elog(ERROR, "unexpected json parse state: %d", ctx); + } + } +} + +/* + * Report an invalid input token. + * + * lex->token_start and lex->token_terminator must identify the token. + */ +static void +report_invalid_token(JsonLexContext *lex) +{ + char *token; + int toklen; + + /* Separate out the offending token. */ + toklen = lex->token_terminator - lex->token_start; + token = palloc(toklen + 1); + memcpy(token, lex->token_start, toklen); + token[toklen] = '\0'; + + ereport(ERROR, + (errcode(ERRCODE_INVALID_TEXT_REPRESENTATION), + errmsg("invalid input syntax for type %s", "json"), + errdetail("Token \"%s\" is invalid.", token), + report_json_context(lex))); +} + +/* + * Report a CONTEXT line for bogus JSON input. + * + * lex->token_terminator must be set to identify the spot where we detected + * the error. Note that lex->token_start might be NULL, in case we recognized + * error at EOF. + * + * The return value isn't meaningful, but we make it non-void so that this + * can be invoked inside ereport(). + */ +static int +report_json_context(JsonLexContext *lex) +{ + const char *context_start; + const char *context_end; + const char *line_start; + int line_number; + char *ctxt; + int ctxtlen; + const char *prefix; + const char *suffix; + + /* Choose boundaries for the part of the input we will display */ + context_start = lex->input; + context_end = lex->token_terminator; + line_start = context_start; + line_number = 1; + for (;;) + { + /* Always advance over newlines */ + if (context_start < context_end && *context_start == '\n') + { + context_start++; + line_start = context_start; + line_number++; + continue; + } + /* Otherwise, done as soon as we are close enough to context_end */ + if (context_end - context_start < 50) + break; + /* Advance to next multibyte character */ + if (IS_HIGHBIT_SET(*context_start)) + context_start += pg_mblen(context_start); + else + context_start++; + } + + /* + * We add "..." to indicate that the excerpt doesn't start at the + * beginning of the line ... but if we're within 3 characters of the + * beginning of the line, we might as well just show the whole line. + */ + if (context_start - line_start <= 3) + context_start = line_start; + + /* Get a null-terminated copy of the data to present */ + ctxtlen = context_end - context_start; + ctxt = palloc(ctxtlen + 1); + memcpy(ctxt, context_start, ctxtlen); + ctxt[ctxtlen] = '\0'; + + /* + * Show the context, prefixing "..." if not starting at start of line, and + * suffixing "..." if not ending at end of line. + */ + prefix = (context_start > line_start) ? "..." : ""; + suffix = (lex->token_type != JSON_TOKEN_END && context_end - lex->input < lex->input_length && *context_end != '\n' && *context_end != '\r') ? "..." : ""; + + return errcontext("JSON data, line %d: %s%s%s", + line_number, prefix, ctxt, suffix); +} + +/* + * Extract a single, possibly multi-byte char from the input string. + */ +static char * +extract_mb_char(char *s) +{ + char *res; + int len; + + len = pg_mblen(s); + res = palloc(len + 1); + memcpy(res, s, len); + res[len] = '\0'; + + return res; +} diff --git a/src/include/utils/jsonapi.h b/src/include/utils/jsonapi.h index 11909474766..bbca121bb72 100644 --- a/src/include/utils/jsonapi.h +++ b/src/include/utils/jsonapi.h @@ -103,6 +103,9 @@ typedef struct JsonSemAction */ extern void pg_parse_json(JsonLexContext *lex, JsonSemAction *sem); +/* the null action object used for pure validation */ +extern JsonSemAction nullSemAction; + /* * json_count_array_elements performs a fast secondary parse to determine the * number of elements in passed array lex context. It should be called from an @@ -124,6 +127,9 @@ extern JsonLexContext *makeJsonLexContextCstringLen(char *json, int len, bool need_escapes); +/* lex one token */ +extern void json_lex(JsonLexContext *lex); + /* * Utility function to check if a string is a valid JSON number. * |