X-Git-Url: https://git.arvados.org/arvados.git/blobdiff_plain/efaf24041034cbc5de09d80283bd98f3e6434854..5e27876fa4d3faf3b973282bfb4f152c02345bdc:/sdk/go/manifest/manifest.go

diff --git a/sdk/go/manifest/manifest.go b/sdk/go/manifest/manifest.go
index 404a1beda8..4e816cd73b 100644
--- a/sdk/go/manifest/manifest.go
+++ b/sdk/go/manifest/manifest.go
@@ -5,61 +5,29 @@
 package manifest
 
 import (
-	"bufio"
-	"fmt"
+	"git.curoverse.com/arvados.git/sdk/go/blockdigest"
 	"log"
-	"regexp"
-	"strconv"
 	"strings"
 )
 
-var LocatorPattern = regexp.MustCompile(
-	"^[0-9a-fA-F]{32}\\+[0-9]+(\\+[A-Z][A-Za-z0-9@_-]+)*$")
-
 type Manifest struct {
 	Text string
 }
 
-type BlockLocator struct {
-	Digest  string
-	Size    int
-	Hints   []string
-}
-
-type ManifestLine struct {
-	StreamName  string
-	Blocks       []string
-	Files        []string
-}
-
-func parseBlockLocator(s string) (b BlockLocator, err error) {
-	if !LocatorPattern.MatchString(s) {
-		err = fmt.Errorf("String \"%s\" does not match BlockLocator pattern " +
-			"\"%s\".",
-			s,
-			LocatorPattern.String())
-	} else {
-		tokens := strings.Split(s, "+")
-		var blockSize int64
-		// We expect ParseInt to succeed since LocatorPattern restricts
-		// tokens[1] to contain exclusively digits.
-		blockSize, err = strconv.ParseInt(tokens[1], 10, 0)
-		if err == nil {
-			b.Digest = tokens[0]
-			b.Size = int(blockSize)
-			b.Hints = tokens[2:]
-		}
-	}
-	return
+// Represents a single line from a manifest.
+type ManifestStream struct {
+	StreamName string
+	Blocks     []string
+	Files      []string
 }
 
-func parseManifestLine(s string) (m ManifestLine) {
+func parseManifestStream(s string) (m ManifestStream) {
 	tokens := strings.Split(s, " ")
 	m.StreamName = tokens[0]
 	tokens = tokens[1:]
 	var i int
 	for i = range tokens {
-		if !LocatorPattern.MatchString(tokens[i]) {
+		if !blockdigest.IsBlockLocator(tokens[i]) {
 			break
 		}
 	}
@@ -68,34 +36,37 @@ func parseManifestLine(s string) (m ManifestLine) {
 	return
 }
 
-func (m *Manifest) LineIter() <-chan ManifestLine {
-	ch := make(chan ManifestLine)
+func (m *Manifest) StreamIter() <-chan ManifestStream {
+	ch := make(chan ManifestStream)
 	go func(input string) {
-		scanner := bufio.NewScanner(strings.NewReader(input))
-		for scanner.Scan() {
-			// We parse one line at a time, to save effort if we only need
-			// the first few lines.
-			ch <- parseManifestLine(scanner.Text())
-		}
-		if err := scanner.Err(); err != nil {
-			log.Fatalf("Error encountered iterating through manifest lines: %v",
-				err)
+		// This slice holds the current line and the remainder of the
+		// manifest.  We parse one line at a time, to save effort if we
+		// only need the first few lines.
+		lines := []string{"", input}
+		for {
+			lines = strings.SplitN(lines[1], "\n", 2)
+			if len(lines[0]) > 0 {
+				// Only parse non-blank lines
+				ch <- parseManifestStream(lines[0])
+			}
+			if len(lines) == 1 {
+				break
+			}
 		}
 		close(ch)
 	}(m.Text)
 	return ch
 }
 
-
 // Blocks may appear mulitple times within the same manifest if they
 // are used by multiple files. In that case this Iterator will output
 // the same block multiple times.
-func (m *Manifest) BlockIterWithDuplicates() <-chan BlockLocator {
-	blockChannel := make(chan BlockLocator)
-	go func(lineChannel <-chan ManifestLine) {
-		for m := range lineChannel {
+func (m *Manifest) BlockIterWithDuplicates() <-chan blockdigest.BlockLocator {
+	blockChannel := make(chan blockdigest.BlockLocator)
+	go func(streamChannel <-chan ManifestStream) {
+		for m := range streamChannel {
 			for _, block := range m.Blocks {
-				if b, err := parseBlockLocator(block); err == nil {
+				if b, err := blockdigest.ParseBlockLocator(block); err == nil {
 					blockChannel <- b
 				} else {
 					log.Printf("ERROR: Failed to parse block: %v", err)
@@ -103,6 +74,6 @@ func (m *Manifest) BlockIterWithDuplicates() <-chan BlockLocator {
 			}
 		}
 		close(blockChannel)
-	}(m.LineIter())
+	}(m.StreamIter())
 	return blockChannel
 }