mirror of
https://github.com/therootcompany/golib.git
synced 2026-11-04 06:55:00 +00:00
AJ ONeal
1753bd73d0
Human-maintained sources (e.g. Google Sheets exports) routinely carry stray blank rows. A blank row above the header was taken as the header, so every data row decoded to zero values; blank data rows decoded as empty records. ParseCSV now wraps the stream in a streaming csvutil.Reader (skipBlanks) that drops records whose cells are all empty or whitespace-only. Records decode one at a time with a single record buffered; delimiter and ragged-row behavior are unchanged, and all-blank input yields nil, nil.
85 lines
2.1 KiB
Go
85 lines
2.1 KiB
Go
package csvx
|
|
|
|
import (
|
|
"encoding/csv"
|
|
"strings"
|
|
"testing"
|
|
)
|
|
|
|
type blankRec struct {
|
|
A string `json:"a"`
|
|
B string `json:"b"`
|
|
}
|
|
|
|
func parseBlank[T any](in string) ([]T, error) {
|
|
c := csv.NewReader(strings.NewReader(in))
|
|
c.FieldsPerRecord = -1 // ragged-tolerant, as sheet readers configure
|
|
return ParseCSV[T](c)
|
|
}
|
|
|
|
// Leading blank rows must not be taken as the header (Google Sheets
|
|
// exports with an empty row 1).
|
|
func TestParseCSVBlankHeaderRow(t *testing.T) {
|
|
items, err := parseBlank[blankRec](",,,,\r\n\r\na,b\r\n1,x\r\n2,y\r\n")
|
|
if err != nil {
|
|
t.Fatalf("parse: %v", err)
|
|
}
|
|
want := []blankRec{{A: "1", B: "x"}, {A: "2", B: "y"}}
|
|
if len(items) != len(want) {
|
|
t.Fatalf("rows: %d, want %d (%+v)", len(items), len(want), items)
|
|
}
|
|
for i := range want {
|
|
if items[i] != want[i] {
|
|
t.Errorf("row %d: %+v, want %+v", i, items[i], want[i])
|
|
}
|
|
}
|
|
}
|
|
|
|
// Blank and whitespace-only data rows are skipped.
|
|
func TestParseCSVBlankDataRows(t *testing.T) {
|
|
items, err := parseBlank[blankRec]("a,b\r\n1,x\r\n\r\n ,\r\n2,y\r\n")
|
|
if err != nil {
|
|
t.Fatalf("parse: %v", err)
|
|
}
|
|
if len(items) != 2 || items[0] != (blankRec{A: "1", B: "x"}) || items[1] != (blankRec{A: "2", B: "y"}) {
|
|
t.Fatalf("rows: %+v", items)
|
|
}
|
|
}
|
|
|
|
// Normal input is unchanged.
|
|
func TestParseCSVNoBlanks(t *testing.T) {
|
|
items, err := parseBlank[blankRec]("a,b\r\n1,x\r\n2,y\r\n")
|
|
if err != nil {
|
|
t.Fatalf("parse: %v", err)
|
|
}
|
|
if len(items) != 2 || items[1] != (blankRec{A: "2", B: "y"}) {
|
|
t.Fatalf("rows: %+v", items)
|
|
}
|
|
}
|
|
|
|
// TSV: blank header row with tab delimiter.
|
|
func TestParseCSVBlankHeaderTSV(t *testing.T) {
|
|
in := "\t\t\r\na\tb\r\n1\tx\r\n"
|
|
c := csv.NewReader(strings.NewReader(in))
|
|
c.Comma = '\t'
|
|
c.FieldsPerRecord = -1
|
|
items, err := ParseCSV[blankRec](c)
|
|
if err != nil {
|
|
t.Fatalf("parse: %v", err)
|
|
}
|
|
if len(items) != 1 || items[0] != (blankRec{A: "1", B: "x"}) {
|
|
t.Fatalf("rows: %+v", items)
|
|
}
|
|
}
|
|
|
|
// All-blank input: no header, no rows.
|
|
func TestParseCSVAllBlank(t *testing.T) {
|
|
items, err := parseBlank[blankRec]("\r\n,\r\n")
|
|
if err != nil {
|
|
t.Fatalf("parse: %v", err)
|
|
}
|
|
if items != nil {
|
|
t.Fatalf("rows: %+v, want nil", items)
|
|
}
|
|
}
|