converter xdfx to csv

main.go

@@ -2,37 +2,47 @@ package main
 
 import (
 	"bufio"
+	"encoding/csv"
 	"fmt"
 	"log"
 	"os"
 	"strings"
-	"sync"
-	"time"
 )
 
+type Words struct {
+	word          string
+	translation   string
+	transcription string
+}
+
 var (
 	full_name string
 	lang_from string
 	lang_to   string
 )
 
-const (
-	FIRST_LINES = 5
-)
-
 func main() {
-	f, err := os.OpenFile("dict.xdxf", os.O_RDONLY, os.ModePerm)
+	fcsv, err := os.Create("./dict.csv")
+	if err != nil {
+		fmt.Println(err)
+	}
+	defer fcsv.Close()
+
+	writer := csv.NewWriter(fcsv)
+	writer.Comma = '|'
+
+	fxdfx, err := os.OpenFile("dict.xdxf", os.O_RDONLY, os.ModePerm)
 	if err != nil {
 		log.Fatalf("open file error: %v", err)
 		return
 	}
-	defer f.Close()
+	defer fxdfx.Close()
 
-	fullFile(f)
+	fullFile(fxdfx, writer)
 }
 
-func fullFile(file *os.File) {
-	sc := bufio.NewScanner(file)
+func fullFile(fxdfx *os.File, fcsv *csv.Writer) {
+	sc := bufio.NewScanner(fxdfx)
 	/*for sc.Scan() {
 		fmt.Println(sc.Text())
 	}*/
@@ -42,14 +52,14 @@ func fullFile(file *os.File) {
 	}
 
 	//skip first lines with some unnessesary data and save full name
-	first:=""
+	first := ""
 	for sc.Scan() {
 		line := sc.Text()
 		if strings.Contains(line, "<full_name>") {
 			line = strings.ReplaceAll(line, "full_name>", "")
 			line = strings.ReplaceAll(line, "</", "")
 			full_name = strings.ReplaceAll(line, "<", "")
-			
+
 		}
 		if strings.Contains(line, "lang_from=") && strings.Contains(line, "lang_to=") {
 			tmp := strings.Split(line, "=")
@@ -57,41 +67,90 @@ func fullFile(file *os.File) {
 			lang_to = strings.Split(tmp[2], " ")[0]
 		}
 		if strings.Contains(line, "<ar><k>") {
-			first= line
+			first = line
 			break
 		}
 	}
 
 	fmt.Printf("Dict name: %s.\n", full_name)
 	fmt.Printf("From %s to %s. \n", lang_from, lang_to)
-	fmt.Println(first)
-	// read file line by line
-	var (
-		word          string
-		translation   string
-		transcription string
-	)
+	//fmt.Println(first)
 
-	for sc.Scan() {
-		line := sc.Text()
-		if strings.Contains(line, "<ar>") {
-			word = ""
-			translation = ""
-			transcription = ""
-			fmt.Println(word, translation, transcription)
+	// read file line by line
+	neww := new(Words)
+	for {
+		first = strings.TrimSpace(first)
+		if first == "" {
+			if sc.Scan() {
+				first += sc.Text()
+			} else {
+				break
+			}
 		}
-		if strings.Contains(line, "<k>") {
-			_, word, _ = strings.Cut(line, "<k>")
+		if strings.Contains(first, "<ar>") {
+			neww.word = ""
+			neww.translation = ""
+			neww.transcription = ""
+			//fmt.Println(neww)
+		}
+		if strings.Contains(first, "<k>") {
+			_, neww.word, _ = strings.Cut(first, "<k>")
+			if strings.Contains(neww.word, "</k>") {
+				neww.word, first, _ = strings.Cut(neww.word, "</k>")
+				first = strings.TrimSpace(first)
+				if first == "" {
+					if sc.Scan() {
+						first += sc.Text()
+					} else {
+						break
+					}
+				}
+			}
+		} else if strings.Contains(first, "<tr>") {
+			_, neww.transcription, _ = strings.Cut(first, "<tr>")
+			if strings.Contains(neww.transcription, "</tr>") {
+				neww.transcription, first, _ = strings.Cut(neww.transcription, "</tr>")
+				first = strings.TrimSpace(first)
+				if first == "" {
+					if sc.Scan() {
+						first += sc.Text()
+					} else {
+						break
+					}
+				}
+			}
+		} else if strings.Contains(first, "</ar>") {
+			neww.translation, first, _ = strings.Cut(first, "</ar>")
+			first = strings.TrimSpace(first)
+			first = strings.TrimSpace(first)
+			if first == "" {
+				if sc.Scan() {
+					//fmt.Printf("Word: %s. Transcription: %s. Translation: %s.\n", neww.word, neww.transcription, neww.translation)
+					err := fcsv.Write([]string{neww.word, neww.transcription, neww.translation})
+					if err != nil {
+						fmt.Println(err)
+					}
+					first += sc.Text()
+				} else {
+					break
+				}
+			}
+		} else {
+			if sc.Scan() {
+				//fmt.Printf("Word: %s. Transcription: %s. Translation: %s.\n", neww.word, neww.transcription, neww.translation)
+				first += sc.Text()
+			} else {
+				break
+			}
 		}
-		fmt.Println(sc.Text())
 	}
 }
 
-func processChunk(chunk []byte, linesPool *sync.Pool, stringPool *sync.Pool, start time.Time, end time.Time) {
+/*func processChunk(chunk []byte, linesPool *sync.Pool, stringPool *sync.Pool, start time.Time, end time.Time) {
 
 }
 
 //readFile opens file in chunks and process to other func. https://medium.com/swlh/processing-16gb-file-in-seconds-go-lang-3982c235dfa2
 func readFile() {
 
-}
+}*/