mirror of
https://github.com/therootcompany/golib.git
synced 2025-10-12 20:18:16 +00:00
184 lines
4.7 KiB
Go
184 lines
4.7 KiB
Go
package main
|
|
|
|
import (
|
|
"errors"
|
|
"flag"
|
|
"fmt"
|
|
"io"
|
|
"os"
|
|
"strings"
|
|
"unicode/utf8"
|
|
|
|
"github.com/therootcompany/golib/io/transform/gsheet2csv"
|
|
)
|
|
|
|
const (
|
|
fileSeparator = "\x1c"
|
|
groupSeparator = "\x1d"
|
|
recordSeparator = "\x1e"
|
|
unitSeparator = "\x1f"
|
|
)
|
|
|
|
func main() {
|
|
var commentArg string
|
|
format := "CSV"
|
|
delim := ','
|
|
if strings.Contains(os.Args[0], "tsv") {
|
|
delim = '\t'
|
|
format = "TSV"
|
|
}
|
|
|
|
// Parse command-line flags
|
|
flag.StringVar(&commentArg, "comment", "#", "treat lines beginning with this rune as comments")
|
|
outputFile := flag.String("o", "", "Output "+format+" file (default: stdout)")
|
|
delimString := flag.String("d", string(delim), "field delimiter to use for output file ('\\t' for tab, '^_' for Unit Separator, etc)")
|
|
useCRLF := flag.Bool("crlf", false, "use CRLF (\\r\\n) as record separator")
|
|
urlOnly := flag.Bool("print-url", false, "don't download, just print the Google Sheet URL")
|
|
parseOnly := flag.Bool("print-ids", false, "don't download, just print the Doc ID and Sheet ID (gid)")
|
|
rawOnly := flag.Bool("raw", false, "don't parse, just download")
|
|
flag.Usage = func() {
|
|
fmt.Fprintf(os.Stderr, "Usage: %s [flags] <google-sheet-url-or-file-path>\n", os.Args[0])
|
|
fmt.Fprintf(os.Stderr, "Converts a Google Sheet to %s format.\n\n", format)
|
|
fmt.Fprintf(os.Stderr, "Flags:\n")
|
|
flag.PrintDefaults()
|
|
fmt.Fprintf(os.Stderr, "\nExample:\n")
|
|
fmt.Fprintf(os.Stderr, " %s -o output.tsv 'https://docs.google.com/spreadsheets/d/1KdNsc63pk0QRerWDPcIL9cMnGQlG-9Ue9Jlf0PAAA34/edit?gid=559037238#gid=559037238'\n", os.Args[0])
|
|
fmt.Fprintf(os.Stderr, " %s -o output.tsv 'file://gsheet.csv'\n", os.Args[0])
|
|
fmt.Fprintf(os.Stderr, " %s -o output.tsv './gsheet.csv'\n", os.Args[0])
|
|
}
|
|
flag.Parse()
|
|
|
|
// Check for URL argument
|
|
if len(flag.Args()) != 1 {
|
|
fmt.Fprintf(os.Stderr, "Error: exactly one Google Sheet URL is required\n")
|
|
flag.Usage()
|
|
os.Exit(1)
|
|
}
|
|
url := flag.Args()[0]
|
|
|
|
// Prepare output writer
|
|
var out *os.File
|
|
if *outputFile != "" {
|
|
var err error
|
|
out, err = os.Create(*outputFile)
|
|
if err != nil {
|
|
fmt.Fprintf(os.Stderr, "Error creating output file: %v\n", err)
|
|
os.Exit(1)
|
|
}
|
|
defer func() { _ = out.Close() }()
|
|
} else {
|
|
out = os.Stdout
|
|
}
|
|
|
|
switch *delimString {
|
|
case "^_", "\\x1f":
|
|
*delimString = unitSeparator
|
|
case "^^", "\\x1e":
|
|
*delimString = recordSeparator
|
|
case "^]", "\\x1d":
|
|
*delimString = groupSeparator
|
|
case "^\\", "\\x1c":
|
|
*delimString = fileSeparator
|
|
case "^L", "\\f":
|
|
*delimString = "\f"
|
|
case "^K", "\\v":
|
|
*delimString = "\v"
|
|
case "^I", "\\t":
|
|
*delimString = "\t"
|
|
}
|
|
delim, _ = utf8.DecodeRuneInString(*delimString)
|
|
|
|
var rc io.ReadCloser
|
|
if strings.HasPrefix(url, "https://") || strings.HasPrefix(url, "http://") {
|
|
docid, gid := gsheet2csv.ParseIDs(url)
|
|
if *parseOnly {
|
|
fmt.Printf("docid=%s\ngid=%s\n", docid, gid)
|
|
} else {
|
|
fmt.Fprintf(os.Stderr, "docid=%s\ngid=%s\n", docid, gid)
|
|
}
|
|
|
|
sheetURL := gsheet2csv.ToCSVURL(docid, gid)
|
|
if *urlOnly {
|
|
fmt.Printf("%s\n", sheetURL)
|
|
} else {
|
|
fmt.Fprintf(os.Stderr, "downloading %s\n", sheetURL)
|
|
}
|
|
|
|
if !*urlOnly {
|
|
resp, err := gsheet2csv.GetSheet(docid, gid)
|
|
if err != nil {
|
|
fmt.Fprintf(os.Stderr, "Error getting url: %v\n", err)
|
|
os.Exit(1)
|
|
}
|
|
defer func() { _ = resp.Body.Close() }()
|
|
rc = resp.Body
|
|
}
|
|
} else {
|
|
url = strings.TrimPrefix(url, "file://")
|
|
fmt.Fprintf(os.Stderr, "opening %s\n", url)
|
|
f, err := os.Open(url)
|
|
if err != nil {
|
|
fmt.Fprintf(os.Stderr, "Error opening file: %v\n", err)
|
|
os.Exit(1)
|
|
}
|
|
rc = f
|
|
}
|
|
|
|
if out == os.Stdout {
|
|
fmt.Fprintf(os.Stderr, "\n")
|
|
}
|
|
|
|
if *urlOnly || *parseOnly {
|
|
os.Exit(0)
|
|
return
|
|
}
|
|
|
|
if *rawOnly {
|
|
if _, err := io.Copy(out, rc); err != nil {
|
|
fmt.Fprintf(os.Stderr, "Error getting url body: %v\n", err)
|
|
os.Exit(1)
|
|
}
|
|
return
|
|
}
|
|
|
|
comment, _ := utf8.DecodeRuneInString(commentArg)
|
|
|
|
// Create a reader for the Google Sheet
|
|
gsr := gsheet2csv.NewReader(rc)
|
|
gsr.QuotedComments = false
|
|
gsr.Comment = 0
|
|
gsr.ReuseRecord = true
|
|
|
|
// Create CSV writer
|
|
csvw := gsheet2csv.NewWriter(out)
|
|
csvw.Comma = delim // Set delimiter to tab for TSV
|
|
csvw.Comment = comment
|
|
csvw.UseCRLF = *useCRLF
|
|
for {
|
|
// Convert each record
|
|
record, err := gsr.Read()
|
|
if err != nil {
|
|
if errors.Is(err, io.EOF) {
|
|
break
|
|
}
|
|
fmt.Fprintf(os.Stderr, "Error reading "+format+": %v\n", err)
|
|
os.Exit(1)
|
|
}
|
|
|
|
if err := csvw.Write(record); err != nil {
|
|
fmt.Fprintf(os.Stderr, "Error writing "+format+": %v\n", err)
|
|
os.Exit(1)
|
|
}
|
|
}
|
|
// Flush the writer to ensure all data is written
|
|
csvw.Flush()
|
|
if err := csvw.Error(); err != nil {
|
|
fmt.Fprintf(os.Stderr, "Error flushing "+format+" writer: %v\n", err)
|
|
os.Exit(1)
|
|
}
|
|
|
|
if out != os.Stdout {
|
|
fmt.Fprintf(os.Stderr, "wrote %s\n", *outputFile)
|
|
}
|
|
}
|