First setup: Parse CSV content

4 files changed, 122 insertions, 0 deletions

diff --git a/encoding.go b/encoding.go
new file mode 100644
index 0000000..d77cd65
--- /dev/null
+++ b/encoding.go
@@ -0,0 +1,40 @@
+package main
+
+import (
+	"bytes"
+	"io"
+
+	"github.com/gogs/chardet"
+	"golang.org/x/text/encoding/ianaindex"
+)
+
+// getEncodedReader tries to determine the encoding of the content of `r`.
+// It returns a new reader that returns UTF-8 content.
+func getEncodedReader(r io.Reader) (io.Reader, error) {
+	buf := make([]byte, 128)
+
+	n, err := io.ReadFull(r, buf)
+	switch {
+	case err == io.ErrUnexpectedEOF:
+		buf = buf[:n]
+		// as `buf` holds the whole content, we can use it as the underlying reader
+		r = bytes.NewReader(buf)
+	case err != nil:
+		return nil, err
+	default:
+		// re-append `buf`
+		r = io.MultiReader(bytes.NewReader(buf), r)
+	}
+
+	res, err := chardet.NewTextDetector().DetectBest(buf)
+	if err != nil {
+		return nil, err
+	}
+
+	enc, err := ianaindex.IANA.Encoding(res.Charset)
+	if err != nil {
+		return nil, err
+	}
+
+	return enc.NewDecoder().Reader(r), nil
+}
diff --git a/go.mod b/go.mod
index 522b283..1ba569a 100644
--- a/go.mod
+++ b/go.mod
@@ -1,3 +1,9 @@
 module github.com/Necoro/enguarde-importer
 
 go 1.17
+
+require (
+	github.com/gogs/chardet v0.0.0-20211120154057-b7413eaefb8f
+	github.com/jszwec/csvutil v1.6.0
+	golang.org/x/text v0.3.7
+)
diff --git a/go.sum b/go.sum
new file mode 100644
index 0000000..3e88ccb
--- /dev/null
+++ b/go.sum
@@ -0,0 +1,6 @@
+github.com/gogs/chardet v0.0.0-20211120154057-b7413eaefb8f h1:3BSP1Tbs2djlpprl7wCLuiqMaUh5SJkkzI2gDs+FgLs=
+github.com/gogs/chardet v0.0.0-20211120154057-b7413eaefb8f/go.mod h1:Pcatq5tYkCW2Q6yrR2VRHlbHpZ/R4/7qyL1TCF7vl14=
+github.com/jszwec/csvutil v1.6.0 h1:QORXquCT0t8nUKD7utAD4HDmQMgG0Ir9WieZXzpa7ms=
+github.com/jszwec/csvutil v1.6.0/go.mod h1:Rpu7Uu9giO9subDyMCIQfHVDuLrcaC36UA4YcJjGBkg=
+golang.org/x/text v0.3.7 h1:olpwvP2KacW1ZWvsR7uQhoyTYvKAupfQrRGBFM352Gk=
+golang.org/x/text v0.3.7/go.mod h1:u+2+/6zg+i71rQMx5EYifcz6MCKuco9NR6JIITiCfzQ=
diff --git a/main.go b/main.go
new file mode 100644
index 0000000..29593db
--- /dev/null
+++ b/main.go
@@ -0,0 +1,70 @@
+package main
+
+import (
+	"encoding/csv"
+	"errors"
+	"fmt"
+	"log"
+	"os"
+
+	"github.com/jszwec/csvutil"
+)
+
+type Participant struct {
+	LastName    string `csv:"lastname"`
+	FirstName   string `csv:"firstname"`
+	DateOfBirth string `csv:"dateofbirth"`
+	Gender      string `csv:"gender"`
+	Nation      string `csv:"nation"`
+	Region      string `csv:"region"`
+	Club        string `csv:"club"`
+}
+
+func parseOphardtInput(fileName string) ([]Participant, error) {
+	f, err := os.Open(fileName)
+	if err != nil {
+		return nil, fmt.Errorf("opening input file '%s': %w", fileName, err)
+	}
+
+	encReader, err := getEncodedReader(f)
+	if err != nil {
+		return nil, fmt.Errorf("cannot determine encoding of file '%s': %w", fileName, err)
+	}
+
+	csvReader := csv.NewReader(encReader)
+	csvReader.Comma = ';'
+
+	dec, err := csvutil.NewDecoder(csvReader)
+	if err != nil {
+		return nil, fmt.Errorf("reading from file '%s': %w", fileName, err)
+	}
+	dec.DisallowMissingColumns = true
+
+	var participants []Participant
+	if err = dec.Decode(&participants); err != nil {
+		return nil, fmt.Errorf("decoding file '%s': %w", fileName, err)
+	}
+
+	return participants, nil
+}
+
+func run() error {
+	if len(os.Args) <= 1 {
+		return errors.New("need filename to start with")
+	}
+	fileName := os.Args[1]
+
+	p, err := parseOphardtInput(fileName)
+	if err != nil {
+		return err
+	}
+
+	fmt.Print(p)
+	return nil
+}
+
+func main() {
+	if err := run(); err != nil {
+		log.Fatalf("An error occured: %v", err)
+	}
+}