Skip to content

CSV import options for DELIMITER, NULL, and QUOTE #256

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

Merged
Greenscreen23 merged 11 commits into from
Sep 17, 2025
Merged

CSV import options for DELIMITER, NULL, and QUOTE #256

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
11 commits
Select commit Hold shift + click to select a range
38e3258
This branch implements more csv parsing options. The goal is that the…
Greenscreen23 Jul 28, 2025
062a6ec
move csv options to separate struct and check whether the format is c…
Greenscreen23 Aug 2, 2025
f7d7b9f
Use single CSV option, simplify parsing and add more test cases
Greenscreen23 Aug 5, 2025
0110e59
Add type specifier to std::pair
Greenscreen23 Aug 5, 2025
14069d8
Implement destructor, switch, remove namespace prefix and add more ba…
Greenscreen23 Aug 25, 2025
9b4f431
Add addtitional anti testcase
Greenscreen23 Aug 26, 2025
95f98b8
Add more good query examples
Greenscreen23 Aug 29, 2025
9c638a7
Shorten csv option handling
Greenscreen23 Aug 30, 2025
7d8171f
Merge branch 'main' of https://github.com/hyrise/sql-parser into luka…
Greenscreen23 Sep 3, 2025
31b8916
Move accept_csv_option to struct CsvOptions
Greenscreen23 Sep 3, 2025
5166a80
Last changes
Greenscreen23 Sep 16, 2025
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
3,469 changes: 1,793 additions & 1,676 deletions src/parser/bison_parser.cpp
View file
Open in desktop

Large diffs are not rendered by default.

20 changes: 11 additions & 9 deletions src/parser/bison_parser.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -258,14 +258,16 @@ extern int hsql_debug;
SQL_FOREIGN = 426, /* FOREIGN */
SQL_KEY = 427, /* KEY */
SQL_REFERENCES = 428, /* REFERENCES */
SQL_EQUALS = 429, /* EQUALS */
SQL_NOTEQUALS = 430, /* NOTEQUALS */
SQL_LESS = 431, /* LESS */
SQL_GREATER = 432, /* GREATER */
SQL_LESSEQ = 433, /* LESSEQ */
SQL_GREATEREQ = 434, /* GREATEREQ */
SQL_NOTNULL = 435, /* NOTNULL */
SQL_UMINUS = 436 /* UMINUS */
SQL_DELIMITER = 429, /* DELIMITER */
SQL_QUOTE = 430, /* QUOTE */
SQL_EQUALS = 431, /* EQUALS */
SQL_NOTEQUALS = 432, /* NOTEQUALS */
SQL_LESS = 433, /* LESS */
SQL_GREATER = 434, /* GREATER */
SQL_LESSEQ = 435, /* LESSEQ */
SQL_GREATEREQ = 436, /* GREATEREQ */
SQL_NOTNULL = 437, /* NOTNULL */
SQL_UMINUS = 438 /* UMINUS */
};
typedef enum hsql_tokentype hsql_token_kind_t;
#endif
Expand Down Expand Up @@ -347,7 +349,7 @@ union HSQL_STYPE

// clang-format off

#line 351 "bison_parser.h"
#line 353 "bison_parser.h"

};
typedef union HSQL_STYPE HSQL_STYPE;
Expand Down
79 changes: 79 additions & 0 deletions src/parser/bison_parser.y
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -230,6 +230,7 @@
%token NOWAIT SKIP LOCKED SHARE
%token RANGE ROWS GROUPS UNBOUNDED FOLLOWING PRECEDING CURRENT_ROW
%token UNIQUE PRIMARY FOREIGN KEY REFERENCES
%token DELIMITER QUOTE

/*********************************
** Non-Terminal types (http://www.gnu.org/software/bison/manual/html_node/Type-Decl.html)
Expand Down Expand Up @@ -467,6 +468,18 @@ import_statement : IMPORT FROM file_type FILE file_path INTO table_name {
$$->encoding = $5->encoding;
$5->encoding = nullptr;
}
if ($5->delimiter) {
$$->delimiter = $5->delimiter;
$5->delimiter = nullptr;
}
if ($5->null) {
$$->null = $5->null;
$5->null = nullptr;
}
if ($5->quote) {
$$->quote = $5->quote;
$5->quote = nullptr;
}
delete $5;
};

Expand Down Expand Up @@ -517,6 +530,48 @@ import_export_options : import_export_options ',' FORMAT file_type {
| ENCODING STRING {
$$ = new ImportExportOptions{};
$$->encoding = $2;
}
| import_export_options ',' DELIMITER STRING {
if ($1->delimiter) {
delete $1;
free($4);
yyerror(&yyloc, result, scanner, "Delimiter must only be provided once.");
YYERROR;
}
$1->delimiter = $4;
$$ = $1;
}
| DELIMITER STRING {
$$ = new ImportExportOptions{};
$$->delimiter = $2;
}
| import_export_options ',' NULL STRING {
if ($1->null) {
delete $1;
free($4);
yyerror(&yyloc, result, scanner, "Null string must only be provided once.");
YYERROR;
}
$1->null = $4;
$$ = $1;
}
| NULL STRING {
$$ = new ImportExportOptions{};
$$->null = $2;
}
| import_export_options ',' QUOTE STRING {
if ($1->quote) {
delete $1;
free($4);
yyerror(&yyloc, result, scanner, "Quote string must only be provided once.");
YYERROR;
}
$1->quote = $4;
$$ = $1;
}
| QUOTE STRING {
$$ = new ImportExportOptions{};
$$->quote = $2;
};

/******************************
Expand All @@ -533,6 +588,18 @@ export_statement : COPY table_name TO file_path opt_import_export_options {
$$->encoding = $5->encoding;
$5->encoding = nullptr;
}
if ($5->delimiter) {
$$->delimiter = $5->delimiter;
$5->delimiter = nullptr;
}
if ($5->null) {
$$->null = $5->null;
$5->null = nullptr;
}
if ($5->quote) {
$$->quote = $5->quote;
$5->quote = nullptr;
}
delete $5;
}
| COPY select_with_paren TO file_path opt_import_export_options {
Expand All @@ -543,6 +610,18 @@ export_statement : COPY table_name TO file_path opt_import_export_options {
$$->encoding = $5->encoding;
$5->encoding = nullptr;
}
if ($5->delimiter) {
$$->delimiter = $5->delimiter;
$5->delimiter = nullptr;
}
if ($5->null) {
$$->null = $5->null;
$5->null = nullptr;
}
if ($5->quote) {
$$->quote = $5->quote;
$5->quote = nullptr;
}
delete $5;
};

Expand Down
Loading
Loading