Files
s3/weed/util/sqlutil/splitter_test.go
zooqueen dd74d3e6d6 Replace AGPL MinIO fork with Apache-2.0 SeaweedFS fork; rebrand CLI weed->s3
hanzoai/s3 was an AGPL-3.0 MinIO fork whose network-copyleft blocks embedding
and reselling as a managed service. Replace it wholesale with a fork of
SeaweedFS (github.com/seaweedfs/seaweedfs, Apache-2.0, Go) which ships a
built-in S3 gateway + Filer.

- License: AGPL-3.0 -> Apache-2.0 (upstream LICENSE kept verbatim, incl.
  "Copyright 2025 Chris Lu"); NOTICE added crediting SeaweedFS. No AGPL/BUSL/
  SSPL/GPL or enterprise ("ee") files remain.
- Module: go.mod path set to github.com/hanzoai/s3 with a self-replace
  (replace github.com/seaweedfs/seaweedfs => ./) so the ~1800 internal Go files
  keep their upstream import paths with zero churn. Internal identifiers and
  import paths are intentionally NOT renamed.
- CLI rebrand: the binary is built as `s3` (was `weed`); root usage, per-command
  help/usage/flag strings, shell autocomplete program name, and the product name
  in CLI output now read "Hanzo S3" / `s3`. Users never see `weed`.
  (e.g. `s3 server`, `s3 filer`, `s3 master`, `s3 volume`, `s3 s3`, `s3 mount`.)
- Build: `make` (or `go build -o s3 ./weed`) builds the `s3` binary green;
  `cmd/weed-db` and `cmd/weed-sql` also build; `go vet ./weed/command/` clean.
- README/LLM.md rewritten for Hanzo S3; AGENTS.md/CLAUDE.md symlinks preserved.
- Dropped a 33MB prebuilt Mach-O `stress` binary upstream had committed; `.gitignore`
  updated to ignore the `s3` build output.
2026-06-18 23:41:25 -07:00

158 lines
4.7 KiB
Go

package sqlutil
import (
"reflect"
"testing"
)
func TestSplitStatements(t *testing.T) {
tests := []struct {
name string
input string
expected []string
}{
{
name: "Simple single statement",
input: "SELECT * FROM users",
expected: []string{"SELECT * FROM users"},
},
{
name: "Multiple statements",
input: "SELECT * FROM users; SELECT * FROM orders;",
expected: []string{"SELECT * FROM users", "SELECT * FROM orders"},
},
{
name: "Semicolon in single quotes",
input: "SELECT 'hello;world' FROM users; SELECT * FROM orders;",
expected: []string{"SELECT 'hello;world' FROM users", "SELECT * FROM orders"},
},
{
name: "Semicolon in double quotes",
input: `SELECT "column;name" FROM users; SELECT * FROM orders;`,
expected: []string{`SELECT "column;name" FROM users`, "SELECT * FROM orders"},
},
{
name: "Escaped quotes in strings",
input: `SELECT 'don''t split; here' FROM users; SELECT * FROM orders;`,
expected: []string{`SELECT 'don''t split; here' FROM users`, "SELECT * FROM orders"},
},
{
name: "Escaped quotes in identifiers",
input: `SELECT "column""name" FROM users; SELECT * FROM orders;`,
expected: []string{`SELECT "column""name" FROM users`, "SELECT * FROM orders"},
},
{
name: "Single line comment",
input: "SELECT * FROM users; -- This is a comment\nSELECT * FROM orders;",
expected: []string{"SELECT * FROM users", "SELECT * FROM orders"},
},
{
name: "Single line comment with semicolon",
input: "SELECT * FROM users; -- Comment with; semicolon\nSELECT * FROM orders;",
expected: []string{"SELECT * FROM users", "SELECT * FROM orders"},
},
{
name: "Multi-line comment",
input: "SELECT * FROM users; /* Multi-line\ncomment */ SELECT * FROM orders;",
expected: []string{"SELECT * FROM users", "SELECT * FROM orders"},
},
{
name: "Multi-line comment with semicolon",
input: "SELECT * FROM users; /* Comment with; semicolon */ SELECT * FROM orders;",
expected: []string{"SELECT * FROM users", "SELECT * FROM orders"},
},
{
name: "Complex mixed case",
input: `SELECT 'test;string', "quoted;id" FROM users; -- Comment; here
/* Another; comment */
INSERT INTO users VALUES ('name''s value', "id""field");`,
expected: []string{
`SELECT 'test;string', "quoted;id" FROM users`,
`INSERT INTO users VALUES ('name''s value', "id""field")`,
},
},
{
name: "Empty statements filtered",
input: "SELECT * FROM users;;; SELECT * FROM orders;",
expected: []string{"SELECT * FROM users", "SELECT * FROM orders"},
},
{
name: "Whitespace handling",
input: " SELECT * FROM users ; SELECT * FROM orders ; ",
expected: []string{"SELECT * FROM users", "SELECT * FROM orders"},
},
{
name: "Single statement without semicolon",
input: "SELECT * FROM users",
expected: []string{"SELECT * FROM users"},
},
{
name: "Empty query",
input: "",
expected: []string{},
},
{
name: "Only whitespace",
input: " \n\t ",
expected: []string{},
},
{
name: "Only single line comment",
input: "-- just a comment",
expected: []string{},
},
{
name: "Only multi-line comment",
input: "/* just a comment; with separator */",
expected: []string{},
},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
result := SplitStatements(tt.input)
if !reflect.DeepEqual(result, tt.expected) {
t.Errorf("SplitStatements() = %v, expected %v", result, tt.expected)
}
})
}
}
func TestSplitStatements_EdgeCases(t *testing.T) {
tests := []struct {
name string
input string
expected []string
}{
{
name: "Nested comments are not supported but handled gracefully",
input: "SELECT * FROM users; /* Outer /* inner */ comment */ SELECT * FROM orders;",
expected: []string{"SELECT * FROM users", "comment */ SELECT * FROM orders"},
},
{
name: "Unterminated string (malformed SQL)",
input: "SELECT 'unterminated string; SELECT * FROM orders;",
expected: []string{"SELECT 'unterminated string; SELECT * FROM orders;"},
},
{
name: "Unterminated comment (malformed SQL)",
input: "SELECT * FROM users; /* unterminated comment",
expected: []string{"SELECT * FROM users"},
},
{
name: "Multiple semicolons in quotes",
input: "SELECT ';;;' FROM users; SELECT ';;;' FROM orders;",
expected: []string{"SELECT ';;;' FROM users", "SELECT ';;;' FROM orders"},
},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
result := SplitStatements(tt.input)
if !reflect.DeepEqual(result, tt.expected) {
t.Errorf("SplitStatements() = %v, expected %v", result, tt.expected)
}
})
}
}