func main() {
spec.RegisterDatabaseFlags()
cpuCount := runtime.NumCPU()
runtime.GOMAXPROCS(cpuCount)
flag.Usage = func() {
fmt.Fprintln(os.Stderr, "Usage: csv-export [options] dataset > filename")
flag.PrintDefaults()
}
flag.Parse()
if flag.NArg() != 1 {
util.CheckError(errors.New("expected dataset arg"))
}
ds, err := spec.GetDataset(flag.Arg(0))
util.CheckError(err)
defer ds.Database().Close()
comma, err := csv.StringToRune(*delimiter)
util.CheckError(err)
err = d.Try(func() {
defer profile.MaybeStartProfile().Stop()
nomsList, structDesc := csv.ValueToListAndElemDesc(ds.HeadValue(), ds.Database())
csv.Write(nomsList, structDesc, comma, os.Stdout)
})
if err != nil {
fmt.Println("Failed to export dataset as CSV:")
fmt.Println(err)
}
}
func main() {
flag.Usage = func() {
fmt.Fprintf(os.Stderr, "usage: %s [options] <dataset>\n", os.Args[0])
flag.PrintDefaults()
}
spec.RegisterDatabaseFlags(flag.CommandLine)
flag.Parse(true)
if flag.NArg() != 1 {
fmt.Fprintln(os.Stderr, "Missing required dataset argument")
return
}
ds, err := spec.GetDataset(flag.Arg(0))
if err != nil {
fmt.Fprintf(os.Stderr, "Could not create dataset: %s\n", err)
return
}
defer ds.Database().Close()
newVal := uint64(1)
if lastVal, ok := ds.MaybeHeadValue(); ok {
newVal = uint64(lastVal.(types.Number)) + 1
}
_, err = ds.CommitValue(types.Number(newVal))
if err != nil {
fmt.Fprintf(os.Stderr, "Error committing: %s\n", err)
return
}
fmt.Println(newVal)
}
func start(dataset string, mount mount) {
ds, err := spec.GetDataset(dataset)
if err != nil {
fmt.Fprintf(os.Stderr, "Could not create dataset: %s\n", err)
return
}
hv, ok := ds.MaybeHeadValue()
if ok {
if !types.IsSubtype(fsType, hv.Type()) {
fmt.Fprintf(os.Stderr, "Invalid dataset head: expected type '%s' but found type '%s'\n", fsType.Desc.(types.StructDesc).Name, hv.Type().Desc.(types.StructDesc).Name)
return
}
} else {
rootAttr := makeAttr(0777) // create the root directory with maximally permissive permissions
rootDir := types.NewStructWithType(directoryType, types.ValueSlice{types.NewMap()})
rootInode := types.NewStructWithType(inodeType, types.ValueSlice{rootAttr, rootDir})
hv = types.NewStructWithType(fsType, types.ValueSlice{rootInode})
}
mount(&nomsFS{
FileSystem: pathfs.NewDefaultFileSystem(),
ds: ds,
head: hv.(types.Struct),
mdLock: &sync.Mutex{},
nodes: make(map[hash.Hash]*nNode),
})
}
func (s *nomsDiffTestSuite) TestNomsDiffSummarize() {
datasetName := "diffSummarizeTest"
str := spec.CreateValueSpecString("ldb", s.LdbDir, datasetName)
ds, err := spec.GetDataset(str)
s.NoError(err)
defer ds.Database().Close()
ds, err = addCommit(ds, "first commit")
s.NoError(err)
r1 := spec.CreateHashSpecString("ldb", s.LdbDir, ds.HeadRef().TargetHash())
ds, err = addCommit(ds, "second commit")
s.NoError(err)
r2 := spec.CreateHashSpecString("ldb", s.LdbDir, ds.HeadRef().TargetHash())
out, _ := s.Run(main, []string{"diff", "--summarize", r1, r2})
s.Contains(out, "Comparing commit values")
s.Contains(out, "1 insertion (100.00%), 1 deletion (100.00%), 0 changes (0.00%), (1 value vs 1 value)")
out, _ = s.Run(main, []string{"diff", "--summarize", r1 + ".value", r2 + ".value"})
s.NotContains(out, "Comparing commit values")
ds, err = ds.CommitValue(types.NewList(types.Number(1), types.Number(2), types.Number(3), types.Number(4)))
s.NoError(err)
r3 := spec.CreateHashSpecString("ldb", s.LdbDir, ds.HeadRef().TargetHash()) + ".value"
ds, err = ds.CommitValue(types.NewList(types.Number(1), types.Number(222), types.Number(4)))
s.NoError(err)
r4 := spec.CreateHashSpecString("ldb", s.LdbDir, ds.HeadRef().TargetHash()) + ".value"
out, _ = s.Run(main, []string{"diff", "--summarize", r3, r4})
s.Contains(out, "1 insertion (25.00%), 2 deletions (50.00%), 0 changes (0.00%), (4 values vs 3 values)")
}
func runDs(args []string) int {
if toDelete != "" {
set, err := spec.GetDataset(toDelete)
d.CheckError(err)
oldCommitRef, errBool := set.MaybeHeadRef()
if !errBool {
d.CheckError(fmt.Errorf("Dataset %v not found", set.ID()))
}
store, err := set.Database().Delete(set.ID())
d.CheckError(err)
defer store.Close()
fmt.Printf("Deleted dataset %v (was %v)\n\n", set.ID(), oldCommitRef.TargetHash().String())
} else {
if len(args) != 1 {
d.CheckError(fmt.Errorf("Database arg missing"))
}
store, err := spec.GetDatabase(args[0])
d.CheckError(err)
defer store.Close()
store.Datasets().IterAll(func(k, v types.Value) {
fmt.Println(k)
})
}
return 0
}
func main() {
flag.Usage = func() {
fmt.Fprintf(os.Stderr, "usage: %s [options] <dataset>\n", os.Args[0])
flag.PrintDefaults()
}
spec.RegisterDatabaseFlags()
flag.Parse()
if flag.NArg() != 1 {
util.CheckError(errors.New("expected dataset arg"))
}
ds, err := spec.GetDataset(flag.Arg(0))
util.CheckError(err)
defer ds.Database().Close()
newVal := uint64(1)
if lastVal, ok := ds.MaybeHeadValue(); ok {
newVal = uint64(lastVal.(types.Number)) + 1
}
_, err = ds.Commit(types.Number(newVal))
d.Exp.NoError(err)
fmt.Println(newVal)
}
func testCommitInResults(s *nomsLogTestSuite, str string, i int) {
ds, err := spec.GetDataset(str)
s.NoError(err)
ds, err = ds.CommitValue(types.Number(i))
s.NoError(err)
commit := ds.Head()
ds.Database().Close()
res, _ := s.Run(main, []string{"log", str})
s.Contains(res, commit.Hash().String())
}
func (s *nomsLogTestSuite) TestNomsLog() {
datasetName := "dsTest"
str := spec.CreateValueSpecString("ldb", s.LdbDir, datasetName)
ds, err := spec.GetDataset(str)
s.NoError(err)
ds.Database().Close()
s.Panics(func() { s.Run(main, []string{"log", str}) })
testCommitInResults(s, str, 1)
testCommitInResults(s, str, 2)
}
func writeTestData(str string, value types.Value) types.Ref {
ds, err := spec.GetDataset(str)
d.Chk.NoError(err)
r1 := ds.Database().WriteValue(value)
ds, err = ds.CommitValue(r1)
d.Chk.NoError(err)
err = ds.Database().Close()
d.Chk.NoError(err)
return r1
}
func (s *nomsDiffTestSuite) TestNomsDiffOutputNotTruncated() {
datasetName := "diffTest"
str := spec.CreateValueSpecString("ldb", s.LdbDir, datasetName)
ds, err := spec.GetDataset(str)
s.NoError(err)
ds, err = addCommit(ds, "first commit")
s.NoError(err)
r1 := spec.CreateValueSpecString("ldb", s.LdbDir, "#"+ds.HeadRef().TargetHash().String())
ds, err = addCommit(ds, "second commit")
s.NoError(err)
r2 := spec.CreateValueSpecString("ldb", s.LdbDir, "#"+ds.HeadRef().TargetHash().String())
ds.Database().Close()
out, _ := s.Run(main, []string{"diff", r1, r2})
s.True(strings.HasSuffix(out, "\"second commit\"\n }\n"), out)
}
func main() {
toDelete := flag.String("d", "", "dataset to delete")
flag.Usage = func() {
fmt.Fprintln(os.Stderr, "Noms dataset management\n")
fmt.Fprintln(os.Stderr, "Usage: noms ds [<database> | -d <dataset>]")
flag.PrintDefaults()
fmt.Fprintf(os.Stderr, "\nFor detailed information on spelling datastores and datasets, see: at https://github.com/attic-labs/noms/blob/master/doc/spelling.md.\n\n")
}
flag.Parse()
if *toDelete != "" {
set, err := spec.GetDataset(*toDelete)
util.CheckError(err)
oldCommitRef, errBool := set.MaybeHeadRef()
if !errBool {
util.CheckError(fmt.Errorf("Dataset %v not found", set.ID()))
}
store, err := set.Database().Delete(set.ID())
util.CheckError(err)
defer store.Close()
fmt.Printf("Deleted dataset %v (was %v)\n\n", set.ID(), oldCommitRef.TargetHash().String())
} else {
if flag.NArg() != 1 {
flag.Usage()
return
}
store, err := spec.GetDatabase(flag.Arg(0))
util.CheckError(err)
defer store.Close()
store.Datasets().IterAll(func(k, v types.Value) {
fmt.Println(k)
})
}
}
func main() {
var dsStr = flag.String("ds", "", "noms dataset to read/write from")
flag.Usage = func() {
fmt.Fprintf(os.Stderr, "Usage: %s [flags] [command] [command-args]\n\n", os.Args[0])
fmt.Fprintln(os.Stderr, "Flags:")
flag.PrintDefaults()
fmt.Fprintln(os.Stderr, "\nCommands:")
fmt.Fprintln(os.Stderr, "\tadd-person <id> <name> <title>")
fmt.Fprintln(os.Stderr, "\tlist-persons")
}
flag.Parse()
if flag.NArg() == 0 {
fmt.Fprintln(os.Stderr, "Not enough arguments")
return
}
if *dsStr == "" {
fmt.Fprintln(os.Stderr, "Required flag '-ds' not set")
return
}
ds, err := spec.GetDataset(*dsStr)
defer ds.Database().Close()
if err != nil {
fmt.Fprintf(os.Stderr, "Could not create dataset: %s\n", err)
return
}
switch flag.Arg(0) {
case "add-person":
addPerson(ds)
case "list-persons":
listPersons(ds)
default:
fmt.Fprintf(os.Stderr, "Unknown command: %s\n", flag.Arg(0))
}
}
func main() {
flag.Usage = func() {
fmt.Fprintf(os.Stderr, "usage: %s <url> <dataset>\n", os.Args[0])
flag.PrintDefaults()
}
spec.RegisterDatabaseFlags(flag.CommandLine)
flag.Parse(true)
if len(flag.Args()) != 2 {
d.CheckError(errors.New("expected url and dataset flags"))
}
ds, err := spec.GetDataset(flag.Arg(1))
d.CheckError(err)
url := flag.Arg(0)
if url == "" {
flag.Usage()
}
res, err := http.Get(url)
if err != nil {
log.Fatalf("Error fetching %s: %+v\n", url, err)
} else if res.StatusCode != 200 {
log.Fatalf("Error fetching %s: %s\n", url, res.Status)
}
defer res.Body.Close()
var jsonObject interface{}
err = json.NewDecoder(res.Body).Decode(&jsonObject)
if err != nil {
log.Fatalln("Error decoding JSON: ", err)
}
_, err = ds.CommitValue(jsontonoms.NomsValueFromDecodedJSON(jsonObject, true))
d.PanicIfError(err)
ds.Database().Close()
}
func main() {
cpuCount := runtime.NumCPU()
runtime.GOMAXPROCS(cpuCount)
flag.Usage = func() {
fmt.Fprintf(os.Stderr, "Moves datasets between or within databases\n\n")
fmt.Fprintf(os.Stderr, "noms sync [options] <source-object> <dest-dataset>\n\n")
flag.PrintDefaults()
fmt.Fprintf(os.Stderr, "\nFor detailed information on spelling objects and datasets, see: at https://github.com/attic-labs/noms/blob/master/doc/spelling.md.\n\n")
}
spec.RegisterDatabaseFlags()
flag.Parse()
if flag.NArg() != 2 {
util.CheckError(errors.New("expected a source object and destination dataset"))
}
sourceStore, sourceObj, err := spec.GetPath(flag.Arg(0))
util.CheckError(err)
defer sourceStore.Close()
sinkDataset, err := spec.GetDataset(flag.Arg(1))
util.CheckError(err)
defer sinkDataset.Database().Close()
err = d.Try(func() {
defer profile.MaybeStartProfile().Stop()
var err error
sinkDataset, err = sinkDataset.Pull(sourceStore, types.NewRef(sourceObj), int(*p))
d.Exp.NoError(err)
})
if err != nil {
log.Fatal(err)
}
}
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.")
spec.RegisterDatabaseFlags(flag.CommandLine)
profile.RegisterProfileFlags(flag.CommandLine)
flag.Usage = func() {
fmt.Fprintln(os.Stderr, "Usage: csv-export [options] dataset > filename")
flag.PrintDefaults()
}
flag.Parse(true)
if flag.NArg() != 1 {
d.CheckError(errors.New("expected dataset arg"))
}
ds, err := spec.GetDataset(flag.Arg(0))
d.CheckError(err)
defer ds.Database().Close()
comma, err := csv.StringToRune(*delimiter)
d.CheckError(err)
err = d.Try(func() {
defer profile.MaybeStartProfile().Stop()
nomsList, structDesc := csv.ValueToListAndElemDesc(ds.HeadValue(), ds.Database())
csv.Write(nomsList, structDesc, comma, os.Stdout)
})
if err != nil {
fmt.Println("Failed to export dataset as CSV:")
fmt.Println(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")
}
func main() {
err := d.Try(func() {
spec.RegisterDatabaseFlags(flag.CommandLine)
profile.RegisterProfileFlags(flag.CommandLine)
flag.Usage = customUsage
flag.Parse(true)
if flag.NArg() != 2 {
d.CheckError(errors.New("Expected directory path followed by dataset"))
}
dir := flag.Arg(0)
ds, err := spec.GetDataset(flag.Arg(1))
d.CheckError(err)
defer profile.MaybeStartProfile().Stop()
cpuCount := runtime.NumCPU()
filesChan := make(chan fileIndex, 1024)
refsChan := make(chan refIndex, 1024)
getFilePaths := func() {
index := 0
err := filepath.Walk(dir, func(path string, info os.FileInfo, err error) error {
d.PanicIfTrue(err != nil, "Cannot traverse directories")
if !info.IsDir() && filepath.Ext(path) == ".xml" {
filesChan <- fileIndex{path, index}
index++
}
return nil
})
d.PanicIfError(err)
close(filesChan)
}
wg := sync.WaitGroup{}
importXML := func() {
expectedType := types.NewMap()
for f := range filesChan {
file, err := os.Open(f.path)
d.PanicIfTrue(err != nil, "Error getting XML")
xmlObject, err := mxj.NewMapXmlReader(file)
d.PanicIfTrue(err != nil, "Error decoding XML")
object := xmlObject.Old()
file.Close()
nomsObj := jsontonoms.NomsValueFromDecodedJSON(object, false)
d.Chk.IsType(expectedType, nomsObj)
var r types.Ref
if !*noIO {
r = ds.Database().WriteValue(nomsObj)
}
refsChan <- refIndex{r, f.index}
}
wg.Done()
}
go getFilePaths()
for i := 0; i < cpuCount*8; i++ {
wg.Add(1)
go importXML()
}
go func() {
wg.Wait()
close(refsChan) // done converting xml to noms
}()
refList := refIndexList{}
for r := range refsChan {
refList = append(refList, r)
}
sort.Sort(refList)
refs := make([]types.Value, len(refList))
for idx, r := range refList {
refs[idx] = r.ref
}
rl := types.NewList(refs...)
if !*noIO {
_, err := ds.CommitValue(rl)
d.PanicIfError(err)
}
})
if err != nil {
log.Fatal(err)
}
}
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() {
flag.Usage = func() {
fmt.Fprintf(os.Stderr, "Fetches a URL into a noms blob\n\nUsage: %s <dataset> <url>:\n", os.Args[0])
flag.PrintDefaults()
}
spec.RegisterDatabaseFlags()
flag.Parse()
if flag.NArg() != 2 {
util.CheckError(errors.New("expected dataset and url arguments"))
}
ds, err := spec.GetDataset(flag.Arg(0))
util.CheckError(err)
defer ds.Database().Close()
url := flag.Arg(1)
start = time.Now()
var pr io.Reader
if 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
}
pr = progressreader.New(resp.Body, getStatusPrinter(resp.ContentLength))
} 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
}
pr = progressreader.New(f, getStatusPrinter(s.Size()))
}
b := types.NewBlob(pr)
ds, err = ds.Commit(b)
if err != nil {
d.Chk.True(datas.ErrMergeNeeded == err)
fmt.Fprintf(os.Stderr, "Could not commit, optimistic concurrency failed.")
return
}
status.Done()
fmt.Println("Done")
}
func main() {
var (
// 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.")
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")
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")
destTypePattern = regexp.MustCompile("^(list|map):(\\d+)$")
)
spec.RegisterDatabaseFlags()
cpuCount := runtime.NumCPU()
runtime.GOMAXPROCS(cpuCount)
flag.Usage = func() {
fmt.Fprintf(os.Stderr, "Usage: csv-import [options] <dataset> <csvfile>\n\n")
flag.PrintDefaults()
}
flag.Parse()
if flag.NArg() != 2 {
err := fmt.Errorf("Expected exactly two parameters (dataset and path) after flags, but you have %d. Maybe you put a flag after the path?", flag.NArg())
util.CheckError(err)
}
path := flag.Arg(1)
defer profile.MaybeStartProfile().Stop()
res, err := os.Open(path)
d.Exp.NoError(err)
defer res.Close()
comma, err := csv.StringToRune(*delimiter)
if err != nil {
util.CheckError(err)
return
}
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.Chk.NoError(err)
} else {
fmt.Println("Invalid dest-type: ", *destType)
return
}
fi, err := res.Stat()
d.Chk.NoError(err)
var r io.Reader = res
if !*noProgress {
r = progressreader.New(r, getStatusPrinter(uint64(fi.Size())))
}
cr := csv.NewCSVReader(r, comma)
var headers []string
if *header == "" {
headers, err = cr.Read()
d.Exp.NoError(err)
} else {
headers = strings.Split(*header, string(comma))
}
ds, err := spec.GetDataset(flag.Arg(0))
util.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())
}
_, err = ds.Commit(value)
if !*noProgress {
status.Clear()
}
d.Exp.NoError(err)
}
func main() {
comment := flag.String("comment", "", "comment to add to commit's meta data")
spec.RegisterDatabaseFlags(flag.CommandLine)
flag.Usage = func() {
fmt.Fprintf(os.Stderr, "Fetches a URL (or file) into a noms blob\n\nUsage: %s <url-or-local-path> <dataset>:\n", os.Args[0])
flag.PrintDefaults()
}
flag.Parse(true)
if flag.NArg() != 2 {
d.CheckErrorNoUsage(errors.New("expected dataset and url arguments"))
}
ds, err := spec.GetDataset(flag.Arg(1))
d.CheckErrorNoUsage(err)
defer ds.Database().Close()
url := flag.Arg(0)
fileOrUrl := "file"
start = time.Now()
var pr io.Reader
if 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
}
pr = progressreader.New(resp.Body, getStatusPrinter(resp.ContentLength))
fileOrUrl = "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
}
pr = progressreader.New(f, getStatusPrinter(s.Size()))
fileOrUrl = "file"
}
b := types.NewStreamingBlob(pr, ds.Database())
mi := metaInfoForCommit(fileOrUrl, url, *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")
}