Skip to content

Support parsing doubly quoted strings as identifiers #296

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
garnacho wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Support parsing doubly quoted strings as identifiers #296

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
72 changes: 57 additions & 15 deletions sqlite-vec.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2072,6 +2072,7 @@ static void _static_text_func(sqlite3_context *context, int argc,

enum Vec0TokenType {
TOKEN_TYPE_IDENTIFIER,
TOKEN_TYPE_DOUBLY_QUOTED_IDENTIFIER,
TOKEN_TYPE_DIGIT,
TOKEN_TYPE_LBRACKET,
TOKEN_TYPE_RBRACKET,
Expand Down Expand Up @@ -2157,6 +2158,17 @@ int vec0_token_next(char *start, char *end, struct Vec0Token *out) {
out->end = ptr;
out->token_type = TOKEN_TYPE_IDENTIFIER;
return VEC0_TOKEN_RESULT_SOME;
} else if (curr == '"') {
char *start = ptr;
int match = 0;
do {
match = ptr > start && (*ptr == '"');
ptr++;
} while (ptr < end && !match);
out->start = start;
out->end = ptr;
out->token_type = TOKEN_TYPE_DOUBLY_QUOTED_IDENTIFIER;
return VEC0_TOKEN_RESULT_SOME;
} else if (is_digit(curr)) {
char *start = ptr;
while (ptr < end && (is_digit(*ptr))) {
Expand Down Expand Up @@ -2263,12 +2275,18 @@ int vec0_parse_partition_key_definition(const char *source, int source_length,
// Check first token is identifier, will be the column name
int rc = vec0_scanner_next(&scanner, &token);
if (rc != VEC0_TOKEN_RESULT_SOME &&
token.token_type != TOKEN_TYPE_IDENTIFIER) {
!((token.token_type == TOKEN_TYPE_IDENTIFIER) ||
(token.token_type == TOKEN_TYPE_DOUBLY_QUOTED_IDENTIFIER))) {
return SQLITE_EMPTY;
}

column_name = token.start;
column_name_length = token.end - token.start;
if (token.token_type == TOKEN_TYPE_DOUBLY_QUOTED_IDENTIFIER) {
column_name = token.start + 1;
column_name_length = token.end - token.start - 2;
} else {
column_name = token.start;
column_name_length = token.end - token.start;
}

// Check the next token matches "text" or "integer", as column type
rc = vec0_scanner_next(&scanner, &token);
Expand Down Expand Up @@ -2346,12 +2364,18 @@ int vec0_parse_auxiliary_column_definition(const char *source, int source_length

rc = vec0_scanner_next(&scanner, &token);
if (rc != VEC0_TOKEN_RESULT_SOME &&
token.token_type != TOKEN_TYPE_IDENTIFIER) {
!((token.token_type == TOKEN_TYPE_IDENTIFIER) ||
(token.token_type == TOKEN_TYPE_DOUBLY_QUOTED_IDENTIFIER))) {
return SQLITE_EMPTY;
}

column_name = token.start;
column_name_length = token.end - token.start;
if (token.token_type == TOKEN_TYPE_DOUBLY_QUOTED_IDENTIFIER) {
column_name = token.start + 1;
column_name_length = token.end - token.start - 2;
} else {
column_name = token.start;
column_name_length = token.end - token.start;
}

// Check the next token matches "text" or "integer", as column type
rc = vec0_scanner_next(&scanner, &token);
Expand Down Expand Up @@ -2418,12 +2442,18 @@ int vec0_parse_metadata_column_definition(const char *source, int source_length,

rc = vec0_scanner_next(&scanner, &token);
if (rc != VEC0_TOKEN_RESULT_SOME ||
token.token_type != TOKEN_TYPE_IDENTIFIER) {
!((token.token_type == TOKEN_TYPE_IDENTIFIER) ||
(token.token_type == TOKEN_TYPE_DOUBLY_QUOTED_IDENTIFIER))) {
return SQLITE_EMPTY;
}

column_name = token.start;
column_name_length = token.end - token.start;
if (token.token_type == TOKEN_TYPE_DOUBLY_QUOTED_IDENTIFIER) {
column_name = token.start + 1;
column_name_length = token.end - token.start - 2;
} else {
column_name = token.start;
column_name_length = token.end - token.start;
}

// Check the next token matches a valid metadata type
rc = vec0_scanner_next(&scanner, &token);
Expand Down Expand Up @@ -2478,12 +2508,18 @@ int vec0_parse_primary_key_definition(const char *source, int source_length,
// Check first token is identifier, will be the column name
int rc = vec0_scanner_next(&scanner, &token);
if (rc != VEC0_TOKEN_RESULT_SOME &&
token.token_type != TOKEN_TYPE_IDENTIFIER) {
!((token.token_type == TOKEN_TYPE_IDENTIFIER) ||
(token.token_type == TOKEN_TYPE_DOUBLY_QUOTED_IDENTIFIER))) {
return SQLITE_EMPTY;
}

column_name = token.start;
column_name_length = token.end - token.start;
if (token.token_type == TOKEN_TYPE_DOUBLY_QUOTED_IDENTIFIER) {
column_name = token.start + 1;
column_name_length = token.end - token.start - 2;
} else {
column_name = token.start;
column_name_length = token.end - token.start;
}

// Check the next token matches "text" or "integer", as column type
rc = vec0_scanner_next(&scanner, &token);
Expand Down Expand Up @@ -2998,12 +3034,18 @@ int vec0_parse_vector_column(const char *source, int source_length,
rc = vec0_scanner_next(&scanner, &token);

if (rc != VEC0_TOKEN_RESULT_SOME &&
token.token_type != TOKEN_TYPE_IDENTIFIER) {
!((token.token_type == TOKEN_TYPE_IDENTIFIER) ||
(token.token_type == TOKEN_TYPE_DOUBLY_QUOTED_IDENTIFIER))) {
return SQLITE_EMPTY;
}

name = token.start;
nameLength = token.end - token.start;
if (token.token_type == TOKEN_TYPE_DOUBLY_QUOTED_IDENTIFIER) {
name = token.start + 1;
nameLength = token.end - token.start - 2;
} else {
name = token.start;
nameLength = token.end - token.start;
}

// vector column type comes next: float, int, or bit
rc = vec0_scanner_next(&scanner, &token);
Expand Down