From 57c782546739fde08138b00e2d0b3ba5f18fb676 Mon Sep 17 00:00:00 2001
From: "Gabriel A. Giovanini" <mail@gabrielgio.me>
Date: Fri, 19 Apr 2024 18:22:50 +0200
Subject: ref: Better organize the files

---
 cmd/importer/importer.go | 131 +++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 131 insertions(+)
 create mode 100644 cmd/importer/importer.go

(limited to 'cmd/importer')

diff --git a/cmd/importer/importer.go b/cmd/importer/importer.go
new file mode 100644
index 0000000..18a7a7b
--- /dev/null
+++ b/cmd/importer/importer.go
@@ -0,0 +1,131 @@
+package importer
+
+import (
+	"bufio"
+	"bytes"
+	"context"
+	"fmt"
+	"io"
+	"math"
+	"os"
+	"strings"
+
+	"github.com/urfave/cli/v2"
+
+	"git.gabrielgio.me/dict/db"
+)
+
+var ImportCommand = &cli.Command{
+	Name:  "import",
+	Usage: "convert dict.cc dictionary into a queryable sqlite format.",
+	Flags: []cli.Flag{
+		&cli.StringFlag{
+			Name:  "output",
+			Value: "main.dict",
+			Usage: "Dictionary database location",
+		},
+		&cli.StringFlag{
+			Name:  "input",
+			Value: "dict.txt",
+			Usage: "Dict.cc txt dictionary file",
+		},
+	},
+	Action: func(cCtx *cli.Context) error {
+		input := cCtx.String("input")
+		output := cCtx.String("output")
+		return Import(context.Background(), input, output)
+	},
+}
+
+func Import(ctx context.Context, txtInput, sqliteOutput string) error {
+	db, err := db.Open(":memory:")
+	if err != nil {
+		return err
+	}
+	err = db.Migrate(ctx)
+	if err != nil {
+		return err
+	}
+
+	file, err := os.Open(txtInput)
+	if err != nil {
+		return err
+	}
+	defer file.Close()
+
+	count := 0
+	total, err := lineCounter(file)
+	if err != nil {
+		return err
+	}
+
+	_, err = file.Seek(0, 0)
+	if err != nil {
+		return err
+	}
+
+	scanner := bufio.NewScanner(file)
+	for scanner.Scan() {
+		if strings.HasPrefix(scanner.Text(), "#") || scanner.Text() == "" {
+			continue
+		}
+
+		var (
+			p    = strings.SplitN(scanner.Text(), "\t", 2)
+			word = p[0]
+			line = strings.ReplaceAll(p[1], "\t", " ")
+		)
+
+		if err := db.InsertLine(ctx, word, line); err != nil {
+			return err
+		}
+		count++
+
+		if (count % 1234) == 0 {
+			fmt.Print("\033[G\033[K") // move the cursor left and clear the line
+			per := math.Ceil((float64(count) / float64(total)) * 100.0)
+			fmt.Printf("%d/%d (%.0f%%)", count, total, per)
+		}
+	}
+
+	fmt.Printf("Consolidating")
+	err = db.Consolidade(ctx)
+	if err != nil {
+		return err
+	}
+
+	err = db.Backup(ctx, sqliteOutput)
+	if err != nil {
+		return err
+	}
+	return nil
+}
+
+func lineCounter(r io.Reader) (int, error) {
+	var count int
+	const lineBreak = '\n'
+
+	buf := make([]byte, bufio.MaxScanTokenSize)
+
+	for {
+		bufferSize, err := r.Read(buf)
+		if err != nil && err != io.EOF {
+			return 0, err
+		}
+
+		var buffPosition int
+		for {
+			i := bytes.IndexByte(buf[buffPosition:], lineBreak)
+			if i == -1 || bufferSize == buffPosition {
+				break
+			}
+			buffPosition += i + 1
+			count++
+		}
+		if err == io.EOF {
+			break
+		}
+	}
+
+	return count, nil
+}
-- 
cgit v1.2.3