func DynamoFlags(prefix string) DynamoStoreFlags {
return DynamoStoreFlags{
flag.Bool(prefix+"dynamo-stats", false, "On each DynamoStore close, print read and write stats. Can be quite verbose"),
flag.String(prefix+"dynamo-table", dynamoTableName, "dynamodb table to store the values of the chunkstore in. You probably don't want to change this."),
flag.String(prefix+"aws-region", "us-west-2", "aws region to put the aws-based chunkstore in"),
flag.Bool(prefix+"aws-auth-from-env", false, "creates the aws-based chunkstore from authorization found in the environment. This is typically used in production to get keys from IAM profile. If not specified, then -aws-key and aws-secret must be specified instead"),
flag.String(prefix+"aws-key", "", "aws key to use to create the aws-based chunkstore"),
flag.String(prefix+"aws-secret", "", "aws secret to use to create the aws-based chunkstore"),
}
}
func main() {
useSHA := flag.String("use-sha", "", "<default>=no hashing, 1=sha1, 256=sha256, 512=sha512, blake=blake2b")
useBH := flag.Bool("use-bh", false, "whether we buzhash the bytes")
flag.Parse(true)
flag.Usage = func() {
fmt.Printf("%s <big-file>\n", os.Args[0])
flag.PrintDefaults()
return
}
if len(flag.Args()) < 1 {
flag.Usage()
return
}
p := flag.Args()[0]
bh := buzhash.NewBuzHash(64 * 8)
f, _ := os.Open(p)
defer f.Close()
t0 := time.Now()
buf := make([]byte, 4*1024)
l := uint64(0)
var h hash.Hash
if *useSHA == "1" {
h = sha1.New()
} else if *useSHA == "256" {
h = sha256.New()
} else if *useSHA == "512" {
h = sha512.New()
} else if *useSHA == "blake" {
h = blake2.NewBlake2B()
}
for {
n, err := f.Read(buf)
l += uint64(n)
if err == io.EOF {
break
}
s := buf[:n]
if h != nil {
h.Write(s)
}
if *useBH {
bh.Write(s)
}
}
t1 := time.Now()
d := t1.Sub(t0)
fmt.Printf("Read %s in %s (%s/s)\n", humanize.Bytes(l), d, humanize.Bytes(uint64(float64(l)/d.Seconds())))
digest := []byte{}
if h != nil {
fmt.Printf("%x\n", h.Sum(digest))
}
}
"path/filepath"
"runtime"
"sort"
"sync"
"github.com/attic-labs/noms/go/d"
"github.com/attic-labs/noms/go/spec"
"github.com/attic-labs/noms/go/types"
"github.com/attic-labs/noms/go/util/jsontonoms"
"github.com/attic-labs/noms/go/util/profile"
"github.com/clbanning/mxj"
flag "github.com/tsuru/gnuflag"
)
var (
noIO = flag.Bool("benchmark", false, "Run in 'benchmark' mode, without file-IO")
customUsage = func() {
fmtString := `%s walks the given directory, looking for .xml files. When it finds one, the entity inside is parsed into nested Noms maps/lists and committed to the dataset indicated on the command line.`
fmt.Fprintf(os.Stderr, fmtString, os.Args[0])
fmt.Fprintf(os.Stderr, "\n\nUsage: %s [options] <path/to/root/directory> <dataset>\n", os.Args[0])
flag.PrintDefaults()
}
)
type fileIndex struct {
path string
index int
}
type refIndex struct {
ref types.Ref
func main() {
// Actually the delimiter uses runes, which can be multiple characters long.
// https://blog.golang.org/strings
delimiter := flag.String("delimiter", ",", "field delimiter for csv file, must be exactly one character long.")
comment := flag.String("comment", "", "comment to add to commit's meta data")
header := flag.String("header", "", "header row. If empty, we'll use the first row of the file")
name := flag.String("name", "Row", "struct name. The user-visible name to give to the struct type that will hold each row of data.")
columnTypes := flag.String("column-types", "", "a comma-separated list of types representing the desired type of each column. if absent all types default to be String")
pathDescription := "noms path to blob to import"
path := flag.String("path", "", pathDescription)
flag.StringVar(path, "p", "", pathDescription)
dateFlag := flag.String("date", "", fmt.Sprintf(`date of commit in ISO 8601 format ("%s"). By default, the current date is used.`, dateFormat))
noProgress := flag.Bool("no-progress", false, "prevents progress from being output if true")
destType := flag.String("dest-type", "list", "the destination type to import to. can be 'list' or 'map:<pk>', where <pk> is the index position (0-based) of the column that is a the unique identifier for the column")
skipRecords := flag.Uint("skip-records", 0, "number of records to skip at beginning of file")
destTypePattern := regexp.MustCompile("^(list|map):(\\d+)$")
spec.RegisterDatabaseFlags(flag.CommandLine)
profile.RegisterProfileFlags(flag.CommandLine)
flag.Usage = func() {
fmt.Fprintf(os.Stderr, "Usage: csv-import [options] <csvfile> <dataset>\n\n")
flag.PrintDefaults()
}
flag.Parse(true)
var err error
switch {
case flag.NArg() == 0:
err = errors.New("Maybe you put options after the dataset?")
case flag.NArg() == 1 && *path == "":
err = errors.New("If <csvfile> isn't specified, you must specify a noms path with -p")
case flag.NArg() == 2 && *path != "":
err = errors.New("Cannot specify both <csvfile> and a noms path with -p")
case flag.NArg() > 2:
err = errors.New("Too many arguments")
}
d.CheckError(err)
var date = *dateFlag
if date == "" {
date = time.Now().UTC().Format(dateFormat)
} else {
_, err := time.Parse(dateFormat, date)
d.CheckErrorNoUsage(err)
}
defer profile.MaybeStartProfile().Stop()
var r io.Reader
var size uint64
var filePath string
var dataSetArgN int
if *path != "" {
db, val, err := spec.GetPath(*path)
d.CheckError(err)
if val == nil {
d.CheckError(fmt.Errorf("Path %s not found\n", *path))
}
blob, ok := val.(types.Blob)
if !ok {
d.CheckError(fmt.Errorf("Path %s not a Blob: %s\n", *path, types.EncodedValue(val.Type())))
}
defer db.Close()
r = blob.Reader()
size = blob.Len()
dataSetArgN = 0
} else {
filePath = flag.Arg(0)
res, err := os.Open(filePath)
d.CheckError(err)
defer res.Close()
fi, err := res.Stat()
d.CheckError(err)
r = res
size = uint64(fi.Size())
dataSetArgN = 1
}
if !*noProgress {
r = progressreader.New(r, getStatusPrinter(size))
}
comma, err := csv.StringToRune(*delimiter)
d.CheckErrorNoUsage(err)
var dest int
var pk int
if *destType == "list" {
dest = destList
} else if match := destTypePattern.FindStringSubmatch(*destType); match != nil {
dest = destMap
pk, err = strconv.Atoi(match[2])
d.CheckErrorNoUsage(err)
} else {
fmt.Println("Invalid dest-type: ", *destType)
return
}
cr := csv.NewCSVReader(r, comma)
for i := uint(0); i < *skipRecords; i++ {
cr.Read()
}
var headers []string
if *header == "" {
headers, err = cr.Read()
d.PanicIfError(err)
} else {
headers = strings.Split(*header, string(comma))
}
ds, err := spec.GetDataset(flag.Arg(dataSetArgN))
d.CheckError(err)
defer ds.Database().Close()
kinds := []types.NomsKind{}
if *columnTypes != "" {
kinds = csv.StringsToKinds(strings.Split(*columnTypes, ","))
}
var value types.Value
if dest == destList {
value, _ = csv.ReadToList(cr, *name, headers, kinds, ds.Database())
} else {
value = csv.ReadToMap(cr, headers, pk, kinds, ds.Database())
}
mi := metaInfoForCommit(date, filePath, *path, *comment)
_, err = ds.Commit(value, dataset.CommitOptions{Meta: mi})
if !*noProgress {
status.Clear()
}
d.PanicIfError(err)
}
func main() {
comment := flag.String("comment", "", "comment to add to commit's meta data")
stdin := flag.Bool("stdin", false, "read blob from stdin")
spec.RegisterDatabaseFlags(flag.CommandLine)
flag.Usage = func() {
fmt.Fprintf(os.Stderr, "Fetches a URL, file, or stdin into a noms blob\n\nUsage: %s [--stdin?] [url-or-local-path?] [dataset]\n", os.Args[0])
flag.PrintDefaults()
}
flag.Parse(true)
if !(*stdin && flag.NArg() == 1) && flag.NArg() != 2 {
flag.Usage()
os.Exit(-1)
}
start = time.Now()
ds, err := spec.GetDataset(flag.Arg(flag.NArg() - 1))
d.CheckErrorNoUsage(err)
defer ds.Database().Close()
var r io.Reader
var contentLength int64
var sourceType, sourceVal string
if *stdin {
r = os.Stdin
contentLength = -1
} else if url := flag.Arg(0); strings.HasPrefix(url, "http") {
resp, err := http.Get(url)
if err != nil {
fmt.Fprintf(os.Stderr, "Could not fetch url %s, error: %s\n", url, err)
return
}
switch resp.StatusCode / 100 {
case 4, 5:
fmt.Fprintf(os.Stderr, "Could not fetch url %s, error: %d (%s)\n", url, resp.StatusCode, resp.Status)
return
}
r = resp.Body
contentLength = resp.ContentLength
sourceType, sourceVal = "url", url
} else {
// assume it's a file
f, err := os.Open(url)
if err != nil {
fmt.Fprintf(os.Stderr, "Invalid URL %s - does not start with 'http' and isn't local file either. fopen error: %s", url, err)
return
}
s, err := f.Stat()
if err != nil {
fmt.Fprintf(os.Stderr, "Could not stat file %s: %s", url, err)
return
}
r = f
contentLength = s.Size()
sourceType, sourceVal = "file", url
}
pr := progressreader.New(r, getStatusPrinter(contentLength))
b := types.NewStreamingBlob(pr, ds.Database())
mi := metaInfoForCommit(sourceType, sourceVal, *comment)
ds, err = ds.Commit(b, dataset.CommitOptions{Meta: mi})
if err != nil {
d.Chk.Equal(datas.ErrMergeNeeded, err)
fmt.Fprintf(os.Stderr, "Could not commit, optimistic concurrency failed.")
return
}
status.Done()
fmt.Println("Done")
}
