.

go/neo/t/.gitignore

 /log
 /var
-/zsha1
+/zhash

go/neo/t/zsha1.go → go/neo/t/zhash.go

-// zsha1 - compute sha1 of whole latest objects stream in a ZODB database
+// zhash - compute hash of whole latest objects stream in a ZODB database
 // +build ignore
 
 package main
@@ -6,6 +6,8 @@ package main
 import (
 	"context"
 	"crypto/sha1"
+	"crypto/sha256"
+	"crypto/sha512"
 	"flag"
 	"fmt"
 	"hash"
@@ -25,21 +27,55 @@ import (
 	"github.com/pkg/profile"
 )
 
+// hasher is hash.Hash which also knows its name
+type hasher struct {
+	hash.Hash
+	name      string
+}
+
 func main() {
 	defer log.Flush()
+	fadler32 := flag.Bool("adler32", false, "compute Adler32 checksum")
+	fcrc32   := flag.Bool("crc32", false, "compute CRC32 checksum")
+	fsha1    := flag.Bool("sha1", false, "compute SHA1 cryptographic hash")
+	fsha256  := flag.Bool("sha256", false, "compute SHA256 cryptographic hash")
+	fsha512  := flag.Bool("sha512", false, "compute SHA512 cryptographic hash")
 	useprefetch := flag.Bool("useprefetch", false, "prefetch loaded objects")
 	flag.Parse()
 	url := flag.Args()[0]	// XXX dirty
 
 	ctx := context.Background()
-	err := zsha1(ctx, url, *useprefetch)
+
+	var h hasher
+	inith := func(name string, ctor func() hash.Hash) {
+		if h.name != "" {
+			log.Fatalf(ctx, "duplicate hashes: %s and %s specified", h.name, name)
+		}
+
+		h.name = name
+		h.Hash = ctor()
+	}
+
+	switch {
+	case *fadler32:	inith("adler32", func() hash.Hash { return adler32.New() })
+	case *fcrc32:	inith("crc32",   func() hash.Hash { return crc32.NewIEEE() })
+	case *fsha1:	inith("sha1",    sha1.New)
+	case *fsha256:	inith("sha256",  sha256.New)
+	case *fsha512:	inith("sha512",  sha512.New)
+	}
+
+	if h.Hash == nil {
+		log.Fatal(ctx, "no hash function specified")
+	}
+
+	err := zhash(ctx, url, h, *useprefetch)
 	if err != nil {
 		log.Fatal(ctx, err)
 	}
 }
 
-func zsha1(ctx context.Context, url string, useprefetch bool) (err error) {
-	defer task.Running(&ctx, "zsha1")(&err)
+func zhash(ctx context.Context, url string, h hasher, useprefetch bool) (err error) {
+	defer task.Running(&ctx, "zhash")(&err)
 
 	stor, err := zodb.OpenStorageURL(ctx, url)
 	if err != nil {
@@ -111,18 +147,7 @@ func zsha1(ctx context.Context, url string, useprefetch bool) (err error) {
 
 for qqq := 0; qqq < 10; qqq++ {
 	tstart := time.Now()
-	var m hash.Hash
-	hashName := "crc32"
-	switch hashName {
-	case "sha1":
-		m = sha1.New()
-	case "crc32":
-		m = crc32.NewIEEE()
-	case "adler32":
-		m = adler32.New()
-	default:
-		panic(0)	// XXX
-	}
+	h.Reset()	// XXX temp
 
 	oid := zodb.Oid(0)
 	nread := 0
@@ -143,9 +168,9 @@ loop:
 			return err
 		}
 
-		//m.Write(data)
+		h.Write(data)
 
-		//fmt.Fprintf(os.Stderr, "%d @%s\tsha1: %x\n", uint(oid), serial, m.Sum(nil))
+		//fmt.Fprintf(os.Stderr, "%d @%s\tsha1: %x\n", uint(oid), serial, h.Sum(nil))
 		//fmt.Fprintf(os.Stderr, "\tdata: %x\n", data)
 
 		nread += len(data)
@@ -160,7 +185,7 @@ loop:
 		x += " +prefetch"
 	}
 	fmt.Printf("%s:%x   ; oid=0..%d  nread=%d  t=%s (%s / object)  x=%s\n",
-		hashName,m.Sum(nil), oid-1, nread, δt, δt / time.Duration(oid), x) // XXX /oid cast ?
+		h.name, h.Sum(nil), oid-1, nread, δt, δt / time.Duration(oid), x) // XXX /oid cast ?
 }
 
 	return nil

go/neo/t/zsha1.py → go/neo/t/zhash.py

 #!/usr/bin/env python
 # -*- coding: utf-8 -*-
-"""zsha1 - compute sha1 of whole latest objects stream in a ZODB database"""
+"""zhash - compute hash of whole latest objects stream in a ZODB database"""
 
 from __future__ import print_function
 
@@ -12,10 +12,23 @@ import hashlib
 from zlib import crc32, adler32
 import sys
 from time import time
+from getopt import getopt, GetoptError
+
+# adler32 in hashlib interface
+class Adler32Hasher:
+    name = "adler32"
+
+    def __init__(self):
+        self.h = adler32('')
+
+    def update(self, data):
+        self.h = adler32(data, self.h)
+
+    def hexdigest(self):
+        return '%x' % (self.h & 0xffffffff)
 
 # crc32 in hashlib interface
 class CRC32Hasher:
-
     name = "crc32"
 
     def __init__(self):
@@ -27,34 +40,64 @@ class CRC32Hasher:
     def hexdigest(self):
         return '%x' % (self.h & 0xffffffff)
 
-# adler32 in hashlib interface
-class Adler32Hasher:
-
-    name = "adler32"
+# {} name -> hasher
+hashRegistry = {
+    "adler32":  Adler32Hasher,
+    "crc32":    CRC32Hasher,
+    "sha1":     hashlib.sha1,
+    "sha256":   hashlib.sha256,
+    "sha512":   hashlib.sha512,
+}
 
-    def __init__(self):
-        self.h = adler32('')
+def usage(w):
+    print(\
+"""Usage: zhash [options] url
 
-    def update(self, data):
-        self.h = adler32(data, self.h)
+options:
 
-    def hexdigest(self):
-        return '%x' % (self.h & 0xffffffff)
+    --adler32       compute Adler32 checksum
+    --crc32         compute CRC32 checksum
+    --sha1          compute SHA1 cryptographic hash
+    --sha256        compute SHA256 cryptographic hash
+    --sha512        compute SHA512 cryptographic hash
+""", file=w)
 
 def main():
-    url = sys.argv[1]
+    try:
+        optv, argv = getopt(sys.argv[1:], "h", ["help"] + hashRegistry.keys())
+    except GetoptError as e:
+        print("E: %s" % e, file=sys.stderr)
+        usage(sys.stderr)
+        exit(1)
+
+    for opt, _ in optv:
+        if opt in ("-h", "--help"):
+            usage(sys.stdout)
+            sys.exit()
+
+        opt = opt.lstrip("-")
+        hctor = hashRegistry[opt]
+        h = hctor()
+
+    if len(argv) != 1:
+        usage(sys.stderr)
+        sys.exit(1)
+
+    url = argv[0]
 
     stor = zodbtools.util.storageFromURL(url, read_only=True)
     last_tid = stor.lastTransaction()
     before = p64(u64(last_tid) + 1)
 
     for zzz in range(10):
-        #m = hashlib.sha1()
-        m = CRC32Hasher()
-        #m = Adler32Hasher()
-
         tstart = time()
 
+        # vvv h.reset() XXX temp
+        try:
+            h = h.__class__()
+        except:
+            h = hashlib.new(h.name)
+
         oid = 0
         nread = 0
         while 1:
@@ -63,9 +106,9 @@ def main():
             except POSKeyError:
                 break
 
-            m.update(data)
+            h.update(data)
 
-            #print('%s @%s\tsha1: %s' % (oid, u64(serial), m.hexdigest()), file=sys.stderr)
+            #print('%s @%s\tsha1: %s' % (oid, u64(serial), h.hexdigest()), file=sys.stderr)
             #print('\tdata: %s' % (data.encode('hex'),), file=sys.stderr)
 
             nread += len(data)
@@ -75,7 +118,7 @@ def main():
         dt = tend - tstart
 
         print('%s:%s   ; oid=0..%d  nread=%d  t=%.3fs (%.1fμs / object)  x=zsha1.py' % \
-                (m.name, m.hexdigest(), oid-1, nread, dt, dt * 1E6 / oid))
+                (h.name, h.hexdigest(), oid-1, nread, dt, dt * 1E6 / oid))
 
 
 if __name__ == '__main__':