Tf Idf over a set of documents to find words relevance - java

I have 2 books in txt format (6000+ lines). I would like to associate, using Python, to each word its relevance (using td idf algorithm) and order them in descending order.
I tried this code
#- * -coding: utf - 8 - * -
from __future__
import division, unicode_literals
import math
from textblob
import TextBlob as tb
def tf(word, blob):
return blob.words.count(word) / len(blob.words)
def n_containing(word, bloblist):
return sum(1
for blob in bloblist
if word in blob)
def idf(word, bloblist):
return math.log(len(bloblist) / (1 + n_containing(word, bloblist)))
def tfidf(word, blob, bloblist):
return tf(word, blob) * idf(word, bloblist)
document1 = tb(""
"FULL BOOK1 TEST"
"")
document2 = tb(""
"FULL BOOK2 TEST"
"")
bloblist = [document1, document2]
for i, blob in enumerate(bloblist):
with open("result.txt", 'w') as textfile:
print("Top words in document {}".format(i + 1))
scores = {
word: tfidf(word, blob, bloblist) for word in blob.words
}
sorted_words = sorted(scores.items(), key = lambda x: x[1], reverse = True)
for word, score in sorted_words:
textfile.write("Word: {}, TF-IDF: {}".format(word, round(score, 5)) + "\n")
that I found here https://stevenloria.com/tf-idf/ with some changes, but it takes a lot of time and after some minutes, it crashes saying TypeError: coercing to Unicode: need string or buffer, float found.
Why?
I also tried to call this Java program through python https://github.com/mccurdyc/tf-idf/. The program works, but the output is incorrect: there are a lot of words that should have a high relevance level that are instead categorized with 0 relevance.
Is there a way to fix that Python code?
Or, can you suggest me another tf-idf implementation that does correctly what I want?

Related

How to pass input data to an existing tensorflow 2.x model in Java?

I'm doing my first steps with tensorflow. After having created a simple model for MNIST data in Python, I now want to import this model into Java and use it for classification. However, I don't manage to pass the input data to the model.
Here is the Python code for model creation:
from tensorflow.keras.datasets import mnist
from tensorflow.keras.utils import to_categorical.
(train_images, train_labels), (test_images, test_labels) = mnist.load_data()
train_images = train_images.reshape((60000, 28, 28, 1))
train_images = train_images.astype('float32')
train_images /= 255
test_images = test_images.reshape((10000, 28, 28, 1))
test_images = test_images.astype('float32')
test_images /= 255
train_labels = to_categorical(train_labels)
test_labels = to_categorical(test_labels)
NrTrainimages = train_images.shape[0]
NrTestimages = test_images.shape[0]
import os
import numpy as np
from tensorflow.keras.callbacks import TensorBoard
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Dropout, Flatten
from tensorflow.keras.layers import Conv2D, MaxPooling2D
from tensorflow.keras import backend as K
# Network architecture
model = Sequential()
mnist_inputshape = train_images.shape[1:4]
# Convolutional block 1
model.add(Conv2D(32, kernel_size=(5,5),
activation = 'relu',
input_shape=mnist_inputshape,
name = 'Input_Layer'))
model.add(MaxPooling2D(pool_size=(2,2)))
# Convolutional block 2
model.add(Conv2D(64, kernel_size=(5,5),activation= 'relu'))
model.add(MaxPooling2D(pool_size=(2,2)))
model.add(Dropout(0.5))
# Prediction block
model.add(Flatten())
model.add(Dense(128, activation='relu', name='features'))
model.add(Dropout(0.5))
model.add(Dense(64, activation='relu'))
model.add(Dense(10, activation='softmax', name = 'Output_Layer'))
model.compile(loss='categorical_crossentropy',
optimizer='Adam',
metrics=['accuracy'])
LOGDIR = "logs"
my_tensorboard = TensorBoard(log_dir = LOGDIR,
histogram_freq=0,
write_graph=True,
write_images=True)
my_batch_size = 128
my_num_classes = 10
my_epochs = 5
history = model.fit(train_images, train_labels,
batch_size=my_batch_size,
callbacks=[my_tensorboard],
epochs=my_epochs,
use_multiprocessing=False,
verbose=1,
validation_data=(test_images, test_labels))
score = model.evaluate(test_images, test_labels)
modeldir = 'models'
model.save(modeldir, save_format = 'tf')
For Java, I am trying to adapt the App.java code published here.
I am struggling with replacing this snippet:
Tensor result = s.runner()
.feed("input_tensor", inputTensor)
.feed("dropout/keep_prob", keep_prob)
.fetch("output_tensor")
.run().get(0);
While in this code, a particular input tensor is used to pass the data, in my model, there are only layers and no individual named tensors. Thus, the following doesn't work:
Tensor<?> result = s.runner()
.feed("Input_Layer/kernel", inputTensor)
.fetch("Output_Layer/kernel")
.run().get(0);
How do I pass the data to and get the output from my model in Java?
With the newest version of TensorFlow Java, you don't need to search for yourself the name of the input/output tensors from the model signature or from the graph. You can simply call the following:
try (SavedModelBundle model = SavedModelBundle.load("./model", "serve");
Tensor<TFloat32> image = TFloat32.tensorOf(...); // There a many ways to pass you image bytes here
Tensor<TFloat32> result = model.call(image).expect(TFloat32.DTYPE)) {
System.out.println("Result is " + result.data().getFloat());
}
}
TensorFlow Java will automatically take care of mapping your input/output tensors to the right nodes.
I finally managed to find a solution. To get all the tensor names in the graph, I used the following code:
for (Iterator it = smb.graph().operations(); it.hasNext();) {
Operation op = (Operation) it.next();
System.out.println("Operation name: " + op.name());
}
From this, I figured out that the following works:
SavedModelBundle smb = SavedModelBundle.load("./model", "serve");
Session s = smb.session();
Tensor<Float> inputTensor = Tensor.<Float>create(imagesArray, Float.class);
Tensor<Float> result = s.runner()
.feed("serving_default_Input_Layer_input", inputTensor)
.fetch("StatefulPartitionedCall")
.run().get(0).expect(Float.class);

How to read a Delimited Text file in Java?

We have following SEQ file from SFTP:
TSID ,D4 ; TEST ID # (PRIMARY)
TSNAME,A15 ; TEST NAME COMMON (ALTERNATE)
TSRNAM ,A15 ; PORT NAME
TSRELO ,A5 ; TEST REPEAT LOW VALUE
TSREHI ,A5 ; TEST REPEAT HIGH VALUE
TSSSRQ ,D2 ; SAMPLE SIZE REQ.
TSCTYP ,D2 ; CONTAINER TYPE
TSSUOM,A6 ; SAMPLE UNIT OF MEAS
TSINDX ,D4 ; WIDE REPORTING INDEX (ALTERNATE)
TSWKLF ,D2 ; WORKLIST FORMAT
TSMCCD,A8 ; MEDICARE CODE + MODIFIER 1 (ALTERNATE)
TSTADY ,D3 ; RESULT TURN-AROUND TIME IN DAYS
TSENOR ,A1 ; TEST HAS EXPANDED NORMALS Y/N
TSSRPT ,A1 ; ELIGIBLE FOR STATE NOTIFICATION REPORT Y/N
TSPLAB ,D2 ; SENDOUT LAB
The content of file are simple text like:
0001MONTH COMPOSITE 12319909110940 MONTH COMPOSITE
0002MONTHLY CAPD 12319909120944 MONTHLY CAPD
0003CAPD MONTHLY LS 123199100110021004100510081010101210151016101811620944105917931794 CAPD MONTHLY LS
0004CCPD MONTHLY LS 12319910011002100410051007100810101012101510161018116209400942105917931794 CCPD MONTHLY LS
0005HD MONTHLY LS 1231991001100210041005100710081010101210151016101809400942105917931794 HD MONTHLY LS
Is there any Java Internal package (or Third party Java library) available to read file Delimited file (.SEQ) in such a way to assign each value to POJO directly using some sort of converters?
For ex:
public class ra(){
#SomethigLength (0,4)
private String tsId;
#SomethigLength (4,15)
private String tsName;
}
(Note we are using Apache Camel here but i think camel may be complicated compare to any simple library?)
You can use camel-bindy with Fixed-Length records(https://camel.apache.org/components/latest/bindy-dataformat.html#_4_fixedlengthrecord)
So your class will be like:
#FixedLengthRecord(length = 15, paddingChar = ' ')
public class Fastbox {
#DataField(pos = 1, length = 4, align = "L")
private String tsId;
#DataField(pos = 2, length = 11, align = "L")
private String tsName;
}
and with unmarshal() you can convert the file to Java object.
More details are in the link above.
Hope it will help!
After so much introspection i will use
http://fixedformat4j.ancientprogramming.com/usage/index.html

Mapping characters to keycodes for international keysets

so I built a pi zero keyboard emulator as mentioned here:
https://www.rmedgar.com/blog/using-rpi-zero-as-keyboard-setup-and-device-definition
I make it type text that it reads from a local text-file (everything developed in java - for reasons :) ).
My problem now is that the configured keysets on the various computers my pi zero is attached to differ very much (german, english, french, ...). Depending on the computer this leads to several typing mistakes (e.g., z instead of y).
So I now built some "translation tables" that map characters to the keycodes fitting to the computer. Such a table looks like this:
public scancodes_en_us() {
//We have (Character, (scancode, modifier))
table.put("a",Pair.create("4","0"));
table.put("b",Pair.create("5","0"));
table.put("c",Pair.create("6","0"));
table.put("d",Pair.create("7","0"));
table.put("e",Pair.create("8","0"));
table.put("f",Pair.create("9","0"));
table.put("g",Pair.create("10","0"));
table.put("h",Pair.create("11","0"));
table.put("i",Pair.create("12","0"));
table.put("j",Pair.create("13","0"));
table.put("k",Pair.create("14","0"));
table.put("l",Pair.create("15","0"));
table.put("m",Pair.create("16","0"));
table.put("n",Pair.create("17","0"));
table.put("o",Pair.create("18","0"));
table.put("p",Pair.create("19","0"));
table.put("q",Pair.create("20","0"));
table.put("r",Pair.create("21","0"));
table.put("s",Pair.create("22","0"));
table.put("t",Pair.create("23","0"));
table.put("u",Pair.create("24","0"));
table.put("v",Pair.create("25","0"));
table.put("w",Pair.create("26","0"));
table.put("x",Pair.create("27","0"));
table.put("y",Pair.create("28","0"));
table.put("z",Pair.create("29","0"));
table.put("A",Pair.create("4","2"));
table.put("B",Pair.create("5","2"));
table.put("C",Pair.create("6","2"));
table.put("D",Pair.create("7","2"));
table.put("E",Pair.create("8","2"));
table.put("F",Pair.create("9","2"));
table.put("G",Pair.create("10","2"));
table.put("H",Pair.create("11","2"));
table.put("I",Pair.create("12","2"));
table.put("J",Pair.create("13","2"));
table.put("K",Pair.create("14","2"));
table.put("L",Pair.create("15","2"));
table.put("M",Pair.create("16","2"));
table.put("N",Pair.create("17","2"));
table.put("O",Pair.create("18","2"));
table.put("P",Pair.create("19","2"));
table.put("Q",Pair.create("20","2"));
table.put("R",Pair.create("21","2"));
table.put("S",Pair.create("22","2"));
table.put("V",Pair.create("25","2"));
table.put("W",Pair.create("26","2"));
table.put("X",Pair.create("27","2"));
table.put("Y",Pair.create("28","2"));
table.put("Z",Pair.create("29","2"));
table.put("1",Pair.create("30","0"));
table.put("2",Pair.create("31","0"));
table.put("5",Pair.create("34","0"));
table.put("6",Pair.create("35","0"));
table.put("7",Pair.create("36","0"));
table.put("8",Pair.create("37","0"));
table.put("9",Pair.create("38","0"));
table.put("0",Pair.create("39","0"));
table.put("!",Pair.create("30","2"));
table.put("#",Pair.create("31","2"));
table.put("#",Pair.create("32","2"));
table.put("$",Pair.create("33","2"));
table.put("%",Pair.create("34","2"));
table.put("^",Pair.create("35","2"));
table.put("&",Pair.create("36","2"));
table.put("*",Pair.create("37","2"));
table.put("(",Pair.create("38","2"));
table.put(")",Pair.create("39","2"));
table.put(" ",Pair.create("44","0"));
table.put("-",Pair.create("45","0"));
table.put("=",Pair.create("46","0"));
table.put("[",Pair.create("47","0"));
table.put("]",Pair.create("48","0"));
table.put("\\",Pair.create("49","0"));
table.put(";",Pair.create("51","0"));
table.put("'",Pair.create("52","0"));
table.put("`",Pair.create("53","0"));
table.put(",",Pair.create("54","0"));
table.put(".",Pair.create("55","0"));
table.put("/",Pair.create("56","0"));
table.put("_",Pair.create("45","2"));
table.put("+",Pair.create("46","2"));
table.put("{",Pair.create("47","2"));
table.put("}",Pair.create("48","2"));
table.put("|",Pair.create("49","2"));
table.put(":",Pair.create("51","2"));
table.put("\"",Pair.create("52","2"));
table.put("~",Pair.create("53","2"));
table.put("<",Pair.create("54","2"));
table.put(">",Pair.create("55","2"));
table.put("?",Pair.create("56","2"));
Having such a table for many different keyboard layouts is a pain. Is there some more clever version to map a character to the scancode for a specific keyboard layout?
If not - is there some kind of archive where I can find such a character to scancode mapping for many different keyboard layouts?
Thank you very much
Look at how localization works, they all share the same approach: Create a special version for each localization as a property file, then have an abstract class to load the property based on locale.
You will develop a loader class like this:
public scancodes(Locale locale) {
// load locale property file or download if missing
// read the property and store to the table
ResourceBundle scanCodes = ResourceBundle.getBundle("codes",locale);
}
And your codes_locale looks like:
codes_de.properties
a=4,0
b=5,0
By doing this, you separate the locale specific character with your logic code, and you don't need to bundle all keyboards in side your app. You can download them as needed.
You can access a tutorial here
If I understood what you are trying to do correctly then you don't have to map anything at all, just use a pre-made format (like unicode which works for all languages I know of), just send a char code and translate it to it's matching char.
Example file reader - char interpreter:
JFileChooser fc = new JFileChooser();
fc.setFileSelectionMode(JFileChooser.FILES_ONLY);
fc.showOpenDialog(null);
File textFile = fc.getSelectedFile();
if(textFile.getName().endsWith(".txt")) {
System.out.println(textFile.getAbsolutePath());
FileInputStream input = new FileInputStream(textFile);
BufferedReader reader = new BufferedReader(new InputStreamReader(input, "UNICODE"));
char[] buffer = new char[input.available() / 2 - 1];
System.out.println("Bytes left: " + input.available());
int read = reader.read(buffer);
System.out.println("Read " + read + " characters");
for(int i = 0; i < read; i++) {
System.out.print("The letter is: " + buffer[i]);
System.out.println(", The key code is: " + (int) buffer[i]);
}
}
you can later use the key code to emulate a key press on your computer
For scan-code mappings you can visit following sites:
Keyboard scancodes
Scan Codes Demystified
My solution is to determine the list of keycode on runtime, it'll save you a lot of caffeine and headache
package test;
import java.util.HashMap;
import java.util.Map;
import javax.swing.KeyStroke;
public class Keycode {
/**
* List of chars, can be stored in file
* #return
*/
public String getCharsets() {
return "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSVWXYZ12567890!##$%^&*() -=[]\\;'`,./_+{}|:\\~<>?";
}
/**
* Determines the keycode on runtime
* #return
*/
public Map<Character, Integer> getScancode() {
Map<Character, Integer> table = new HashMap<>();
String charsets = this.getCharsets();
for( int index = 0 ; index < charsets.length() ; index++ ) {
Character currentChar = charsets.charAt(index);
KeyStroke keyStroke = KeyStroke.getKeyStroke(currentChar.charValue(), 0);
// only for example i've used Map, but you should populate it by your table
// table.put("a",Pair.create("4","0"));
table.put(currentChar, keyStroke.getKeyCode());
}
return table;
}
public static void main(String[] args) {
System.out.println(new Keycode().getScancode());
}
}

MD5 calculation for multipart amazon s3 uploading. android/java [duplicate]

Files uploaded to Amazon S3 that are smaller than 5GB have an ETag that is simply the MD5 hash of the file, which makes it easy to check if your local files are the same as what you put on S3.
But if your file is larger than 5GB, then Amazon computes the ETag differently.
For example, I did a multipart upload of a 5,970,150,664 byte file in 380 parts. Now S3 shows it to have an ETag of 6bcf86bed8807b8e78f0fc6e0a53079d-380. My local file has an md5 hash of 702242d3703818ddefe6bf7da2bed757. I think the number after the dash is the number of parts in the multipart upload.
I also suspect that the new ETag (before the dash) is still an MD5 hash, but with some meta data included along the way from the multipart upload somehow.
Does anyone know how to compute the ETag using the same algorithm as Amazon S3?
Say you uploaded a 14MB file to a bucket without server-side encryption, and your part size is 5MB. Calculate 3 MD5 checksums corresponding to each part, i.e. the checksum of the first 5MB, the second 5MB, and the last 4MB. Then take the checksum of their concatenation. MD5 checksums are often printed as hex representations of binary data, so make sure you take the MD5 of the decoded binary concatenation, not of the ASCII or UTF-8 encoded concatenation. When that's done, add a hyphen and the number of parts to get the ETag.
Here are the commands to do it on Mac OS X from the console:
$ dd bs=1m count=5 skip=0 if=someFile | md5 >>checksums.txt
5+0 records in
5+0 records out
5242880 bytes transferred in 0.019611 secs (267345449 bytes/sec)
$ dd bs=1m count=5 skip=5 if=someFile | md5 >>checksums.txt
5+0 records in
5+0 records out
5242880 bytes transferred in 0.019182 secs (273323380 bytes/sec)
$ dd bs=1m count=5 skip=10 if=someFile | md5 >>checksums.txt
2+1 records in
2+1 records out
2599812 bytes transferred in 0.011112 secs (233964895 bytes/sec)
At this point all the checksums are in checksums.txt. To concatenate them and decode the hex and get the MD5 checksum of the lot, just use
$ xxd -r -p checksums.txt | md5
And now append "-3" to get the ETag, since there were 3 parts.
Notes
If you uploaded with aws-cli via aws s3 cp then you most likely have a 8MB chunksize. According to the docs, that is the default.
If the bucket has server-side encryption (SSE) turned on, the ETag won't be the MD5 checksum (see the API documentation). But if you're just trying to verify that an uploaded part matches what you sent, you can use the Content-MD5 header and S3 will compare it for you.
md5 on macOS just writes out the checksum, but md5sum on Linux/brew also outputs the filename. You'll need to strip that, but I'm sure there's some option to only output the checksums. You don't need to worry about whitespace cause xxd will ignore it.
Code Links
A Gist I wrote with a working script for macOS.
The project at s3md5.
Based on answers here, I wrote a Python implementation which correctly calculates both multi-part and single-part file ETags.
def calculate_s3_etag(file_path, chunk_size=8 * 1024 * 1024):
md5s = []
with open(file_path, 'rb') as fp:
while True:
data = fp.read(chunk_size)
if not data:
break
md5s.append(hashlib.md5(data))
if len(md5s) < 1:
return '"{}"'.format(hashlib.md5().hexdigest())
if len(md5s) == 1:
return '"{}"'.format(md5s[0].hexdigest())
digests = b''.join(m.digest() for m in md5s)
digests_md5 = hashlib.md5(digests)
return '"{}-{}"'.format(digests_md5.hexdigest(), len(md5s))
The default chunk_size is 8 MB used by the official aws cli tool, and it does multipart upload for 2+ chunks. It should work under both Python 2 and 3.
bash implementation
python implementation
The algorithm literally is (copied from the readme in the python implementation) :
md5 the chunks
glob the md5 strings together
convert the glob to binary
md5 the binary of the globbed chunk md5s
append "-Number_of_chunks" to the end of the md5 string of the binary
Here's yet another piece in this crazy AWS challenge puzzle.
FWIW, this answer assumes you already have figured out how to calculate the "MD5 of MD5 parts" and can rebuild your AWS Multi-part ETag from all the other answers already provided here.
What this answer addresses is the annoyance of having to "guess" or otherwise "divine" the original upload part size.
We use several different tools for uploading to S3 and they all seem to have different upload part sizes, so "guessing" really wasn't an option. Also, we have a lot of files that were historically uploaded when part sizes seemed to be different. Also, the old trick of using an internal server copy to force the creation of an MD5-type ETag also no longer works as AWS has changed their internal server copies to also use multi-part (just with a fairly large part size).
So...
How can you figure out the object's part size?
Well, if you first make a head_object request and detect that the ETag is a multi-part type ETag (includes a '-<partcount>' at the end), then you can make another head_object request, but with an additional part_number attribute of 1 (the first part). This follow-on head_object request will then return you the content_length of the first part. Viola... Now you know the part size that was used and you can use that size to re-create your local ETag which should match the original uploaded S3 ETag created when the object was uploaded.
Additionally, if you wanted to be exact (perhaps some multi-part uploads were to use variable part sizes), then you could continue to call head_object requests with each part_number specified and calculate each part's MD5 from the returned parts content_length.
Hope that helps...
Not sure if it can help:
We're currently doing an ugly (but so far useful) hack to fix those wrong ETags in multipart uploaded files, which consists on applying a change to the file in the bucket; that triggers a md5 recalculation from Amazon that changes the ETag to matches with the actual md5 signature.
In our case:
File: bucket/Foo.mpg.gpg
ETag obtained: "3f92dffef0a11d175e60fb8b958b4e6e-2"
Do something with the file (rename it, add a meta-data like a fake header, among others)
Etag obtained: "c1d903ca1bb6dc68778ef21e74cc15b0"
We don't know the algorithm, but since we can "fix" the ETag we don't need to worry about it either.
Same algorithm, java version:
(BaseEncoding, Hasher, Hashing, etc comes from the guava library
/**
* Generate checksum for object came from multipart upload</p>
* </p>
* AWS S3 spec: Entity tag that identifies the newly created object's data. Objects with different object data will have different entity tags. The entity tag is an opaque string. The entity tag may or may not be an MD5 digest of the object data. If the entity tag is not an MD5 digest of the object data, it will contain one or more nonhexadecimal characters and/or will consist of less than 32 or more than 32 hexadecimal digits.</p>
* Algorithm follows AWS S3 implementation: https://github.com/Teachnova/s3md5</p>
*/
private static String calculateChecksumForMultipartUpload(List<String> md5s) {
StringBuilder stringBuilder = new StringBuilder();
for (String md5:md5s) {
stringBuilder.append(md5);
}
String hex = stringBuilder.toString();
byte raw[] = BaseEncoding.base16().decode(hex.toUpperCase());
Hasher hasher = Hashing.md5().newHasher();
hasher.putBytes(raw);
String digest = hasher.hash().toString();
return digest + "-" + md5s.size();
}
According to the AWS documentation the ETag isn't an MD5 hash for a multi-part upload nor for an encrypted object: http://docs.aws.amazon.com/AmazonS3/latest/API/RESTCommonResponseHeaders.html
Objects created by the PUT Object, POST Object, or Copy operation, or through the AWS Management Console, and are encrypted by SSE-S3 or plaintext, have ETags that are an MD5 digest of their object data.
Objects created by the PUT Object, POST Object, or Copy operation, or through the AWS Management Console, and are encrypted by SSE-C or SSE-KMS, have ETags that are not an MD5 digest of their object data.
If an object is created by either the Multipart Upload or Part Copy operation, the ETag is not an MD5 digest, regardless of the method of encryption.
In an above answer, someone asked if there was a way to get the md5 for files larger than 5G.
An answer that I could give for getting the MD5 value (for files larger than 5G) would be to either add it manually to the metadata, or use a program to do your uploads which will add the information.
For example, I used s3cmd to upload a file, and it added the following metadata.
$ aws s3api head-object --bucket xxxxxxx --key noarch/epel-release-6-8.noarch.rpm
{
"AcceptRanges": "bytes",
"ContentType": "binary/octet-stream",
"LastModified": "Sat, 19 Sep 2015 03:27:25 GMT",
"ContentLength": 14540,
"ETag": "\"2cd0ae668a585a14e07c2ea4f264d79b\"",
"Metadata": {
"s3cmd-attrs": "uid:502/gname:staff/uname:xxxxxx/gid:20/mode:33188/mtime:1352129496/atime:1441758431/md5:2cd0ae668a585a14e07c2ea4f264d79b/ctime:1441385182"
}
}
It isn't a direct solution using the ETag, but it is a way to populate the metadata you want (MD5) in a way you can access it. It will still fail if someone uploads the file without metadata.
Here is the algorithm in ruby...
require 'digest'
# PART_SIZE should match the chosen part size of the multipart upload
# Set here as 10MB
PART_SIZE = 1024*1024*10
class File
def each_part(part_size = PART_SIZE)
yield read(part_size) until eof?
end
end
file = File.new('<path_to_file>')
hashes = []
file.each_part do |part|
hashes << Digest::MD5.hexdigest(part)
end
multipart_hash = Digest::MD5.hexdigest([hashes.join].pack('H*'))
multipart_etag = "#{multipart_hash}-#{hashes.count}"
Thanks to Shortest Hex2Bin in Ruby and Multipart Uploads to S3 ...
node.js implementation -
const fs = require('fs');
const crypto = require('crypto');
const chunk = 1024 * 1024 * 5; // 5MB
const md5 = data => crypto.createHash('md5').update(data).digest('hex');
const getEtagOfFile = (filePath) => {
const stream = fs.readFileSync(filePath);
if (stream.length <= chunk) {
return md5(stream);
}
const md5Chunks = [];
const chunksNumber = Math.ceil(stream.length / chunk);
for (let i = 0; i < chunksNumber; i++) {
const chunkStream = stream.slice(i * chunk, (i + 1) * chunk);
md5Chunks.push(md5(chunkStream));
}
return `${md5(Buffer.from(md5Chunks.join(''), 'hex'))}-${chunksNumber}`;
};
And here is a PHP version of calculating the ETag:
function calculate_aws_etag($filename, $chunksize) {
/*
DESCRIPTION:
- calculate Amazon AWS ETag used on the S3 service
INPUT:
- $filename : path to file to check
- $chunksize : chunk size in Megabytes
OUTPUT:
- ETag (string)
*/
$chunkbytes = $chunksize*1024*1024;
if (filesize($filename) < $chunkbytes) {
return md5_file($filename);
} else {
$md5s = array();
$handle = fopen($filename, 'rb');
if ($handle === false) {
return false;
}
while (!feof($handle)) {
$buffer = fread($handle, $chunkbytes);
$md5s[] = md5($buffer);
unset($buffer);
}
fclose($handle);
$concat = '';
foreach ($md5s as $indx => $md5) {
$concat .= hex2bin($md5);
}
return md5($concat) .'-'. count($md5s);
}
}
$etag = calculate_aws_etag('path/to/myfile.ext', 8);
And here is an enhanced version that can verify against an expected ETag - and even guess the chunksize if you don't know it!
function calculate_etag($filename, $chunksize, $expected = false) {
/*
DESCRIPTION:
- calculate Amazon AWS ETag used on the S3 service
INPUT:
- $filename : path to file to check
- $chunksize : chunk size in Megabytes
- $expected : verify calculated etag against this specified etag and return true or false instead
- if you make chunksize negative (eg. -8 instead of 8) the function will guess the chunksize by checking all possible sizes given the number of parts mentioned in $expected
OUTPUT:
- ETag (string)
- or boolean true|false if $expected is set
*/
if ($chunksize < 0) {
$do_guess = true;
$chunksize = 0 - $chunksize;
} else {
$do_guess = false;
}
$chunkbytes = $chunksize*1024*1024;
$filesize = filesize($filename);
if ($filesize < $chunkbytes && (!$expected || !preg_match("/^\\w{32}-\\w+$/", $expected))) {
$return = md5_file($filename);
if ($expected) {
$expected = strtolower($expected);
return ($expected === $return ? true : false);
} else {
return $return;
}
} else {
$md5s = array();
$handle = fopen($filename, 'rb');
if ($handle === false) {
return false;
}
while (!feof($handle)) {
$buffer = fread($handle, $chunkbytes);
$md5s[] = md5($buffer);
unset($buffer);
}
fclose($handle);
$concat = '';
foreach ($md5s as $indx => $md5) {
$concat .= hex2bin($md5);
}
$return = md5($concat) .'-'. count($md5s);
if ($expected) {
$expected = strtolower($expected);
$matches = ($expected === $return ? true : false);
if ($matches || $do_guess == false || strlen($expected) == 32) {
return $matches;
} else {
// Guess the chunk size
preg_match("/-(\\d+)$/", $expected, $match);
$parts = $match[1];
$min_chunk = ceil($filesize / $parts /1024/1024);
$max_chunk = floor($filesize / ($parts-1) /1024/1024);
$found_match = false;
for ($i = $min_chunk; $i <= $max_chunk; $i++) {
if (calculate_aws_etag($filename, $i) === $expected) {
$found_match = true;
break;
}
}
return $found_match;
}
} else {
return $return;
}
}
}
The short answer is that you take the 128bit binary md5 digest of each part, concatenate them into a document, and hash that document. The algorithm presented in this answer is accurate.
Note: the multipart ETAG form with the hyphen will change to the form without the hyphen if you "touch" the blob (even without modifying the content). That is, if you copy, or do an in-place copy of your completed multipart-uploaded object (aka PUT-COPY), S3 will recompute the ETAG with the simple version of the algorithm. i.e. the destination object will have an etag without the hyphen.
You've probably considered this already, but if your files are less than 5GB, and you already know their MD5s, and upload parallelization provides little to no benefit (e.g. you are streaming the upload from a slow network, or uploading from a slow disk), then you may also consider using a simple PUT instead of a multipart PUT, and pass your known Content-MD5 in your request headers -- amazon will fail the upload if they don't match. Keep in mind that you get charged for each UploadPart.
Furthermore, in some clients, passing a known MD5 for the input of a PUT operation will save the client from recomputing the MD5 during the transfer. In boto3 (python), you would use the ContentMD5 parameter of the client.put_object() method, for instance. If you omit the parameter, and you already knew the MD5, then the client would be wasting cycles computing it again before the transfer.
Working algorithm implemented in Node.js (TypeScript).
/**
* Generate an S3 ETAG for multipart uploads in Node.js
* An implementation of this algorithm: https://stackoverflow.com/a/19896823/492325
* Author: Richard Willis <willis.rh#gmail.com>
*/
import fs from 'node:fs';
import crypto, { BinaryLike } from 'node:crypto';
const defaultPartSizeInBytes = 5 * 1024 * 1024; // 5MB
function md5(contents: string | BinaryLike): string {
return crypto.createHash('md5').update(contents).digest('hex');
}
export function getS3Etag(
filePath: string,
partSizeInBytes = defaultPartSizeInBytes
): string {
const { size: fileSizeInBytes } = fs.statSync(filePath);
let parts = Math.floor(fileSizeInBytes / partSizeInBytes);
if (fileSizeInBytes % partSizeInBytes > 0) {
parts += 1;
}
const fileDescriptor = fs.openSync(filePath, 'r');
let totalMd5 = '';
for (let part = 0; part < parts; part++) {
const skipBytes = partSizeInBytes * part;
const totalBytesLeft = fileSizeInBytes - skipBytes;
const bytesToRead = Math.min(totalBytesLeft, partSizeInBytes);
const buffer = Buffer.alloc(bytesToRead);
fs.readSync(fileDescriptor, buffer, 0, bytesToRead, skipBytes);
totalMd5 += md5(buffer);
}
const combinedHash = md5(Buffer.from(totalMd5, 'hex'));
const etag = `${combinedHash}-${parts}`;
return etag;
}
I've published this to npm
npm install s3-etag
import { generateETag } from 's3-etag';
const etag = generateETag(absoluteFilePath, partSizeInBytes);
View project here: https://github.com/badsyntax/s3-etag
A version in Rust:
use crypto::digest::Digest;
use crypto::md5::Md5;
use std::fs::File;
use std::io::prelude::*;
use std::iter::repeat;
fn calculate_etag_from_read(f: &mut dyn Read, chunk_size: usize) -> Result<String> {
let mut md5 = Md5::new();
let mut concat_md5 = Md5::new();
let mut input_buffer = vec![0u8; chunk_size];
let mut chunk_count = 0;
let mut current_md5: Vec<u8> = repeat(0).take((md5.output_bits() + 7) / 8).collect();
let md5_result = loop {
let amount_read = f.read(&mut input_buffer)?;
if amount_read > 0 {
md5.reset();
md5.input(&input_buffer[0..amount_read]);
chunk_count += 1;
md5.result(&mut current_md5);
concat_md5.input(&current_md5);
} else {
if chunk_count > 1 {
break format!("{}-{}", concat_md5.result_str(), chunk_count);
} else {
break md5.result_str();
}
}
};
Ok(md5_result)
}
fn calculate_etag(file: &String, chunk_size: usize) -> Result<String> {
let mut f = File::open(file)?;
calculate_etag_from_read(&mut f, chunk_size)
}
See a repo with a simple implementation: https://github.com/bn3t/calculate-etag/tree/master
Regarding chunk size, I noticed that it seems to depend of number of parts.
The maximun number of parts are 10000 as AWS documents.
So starting on a default of 8MB and knowing the filesize, chunk size and parts can be calculated as follows:
chunk_size=8*1024*1024
flsz=os.path.getsize(fl)
while flsz/chunk_size>10000:
chunk_size*=2
parts=math.ceil(flsz/chunk_size)
Parts have to be up-rounded
Extending Timothy Gonzalez's answer:
Identical files will have different etag when using multipart upload.
It's easy to test it with WinSCP, because it uses multipart upload.
When I upload multiple indentical copies of the same file to S3 via WinSCP then each has different etag. When I download them and calculate md5, then they are still indentical.
So from what I tested different etags doesn't mean that files are different.
I see no alternative way to obtain any hash for S3 files without downloading them first.
This is true for multipart uploads. For not-multipart it should still be possible to calculate etag locally.
I have a solution for iOS and macOS without using external helpers like dd and xxd. I have just found it, so I report it as it is, planning to improve it at a later stage. For the moment, it relies on both Objective-C and Swift code. First of all, create this helper class in Objective-C:
AWS3MD5Hash.h
#import <Foundation/Foundation.h>
NS_ASSUME_NONNULL_BEGIN
#interface AWS3MD5Hash : NSObject
- (NSData *)dataFromFile:(FILE *)theFile startingOnByte:(UInt64)startByte length:(UInt64)length filePath:(NSString *)path singlePartSize:(NSUInteger)partSizeInMb;
- (NSData *)dataFromBigData:(NSData *)theData startingOnByte:(UInt64)startByte length:(UInt64)length;
- (NSData *)dataFromHexString:(NSString *)sourceString;
#end
NS_ASSUME_NONNULL_END
AWS3MD5Hash.m
#import "AWS3MD5Hash.h"
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#define SIZE 256
#implementation AWS3MD5Hash
- (NSData *)dataFromFile:(FILE *)theFile startingOnByte:(UInt64)startByte length:(UInt64)length filePath:(NSString *)path singlePartSize:(NSUInteger)partSizeInMb {
char *buffer = malloc(length);
NSURL *fileURL = [NSURL fileURLWithPath:path];
NSNumber *fileSizeValue = nil;
NSError *fileSizeError = nil;
[fileURL getResourceValue:&fileSizeValue
forKey:NSURLFileSizeKey
error:&fileSizeError];
NSInteger __unused result = fseek(theFile,startByte,SEEK_SET);
if (result != 0) {
free(buffer);
return nil;
}
NSInteger result2 = fread(buffer, length, 1, theFile);
NSUInteger difference = fileSizeValue.integerValue - startByte;
NSData *toReturn;
if (result2 == 0) {
toReturn = [NSData dataWithBytes:buffer length:difference];
} else {
toReturn = [NSData dataWithBytes:buffer length:result2 * length];
}
free(buffer);
return toReturn;
}
- (NSData *)dataFromBigData:(NSData *)theData startingOnByte: (UInt64)startByte length:(UInt64)length {
NSUInteger fileSizeValue = theData.length;
NSData *subData;
if (startByte + length > fileSizeValue) {
subData = [theData subdataWithRange:NSMakeRange(startByte, fileSizeValue - startByte)];
} else {
subData = [theData subdataWithRange:NSMakeRange(startByte, length)];
}
return subData;
}
- (NSData *)dataFromHexString:(NSString *)string {
string = [string lowercaseString];
NSMutableData *data= [NSMutableData new];
unsigned char whole_byte;
char byte_chars[3] = {'\0','\0','\0'};
NSInteger i = 0;
NSInteger length = string.length;
while (i < length-1) {
char c = [string characterAtIndex:i++];
if (c < '0' || (c > '9' && c < 'a') || c > 'f')
continue;
byte_chars[0] = c;
byte_chars[1] = [string characterAtIndex:i++];
whole_byte = strtol(byte_chars, NULL, 16);
[data appendBytes:&whole_byte length:1];
}
return data;
}
#end
Now create a plain swift file:
AWS Extensions.swift
import UIKit
import CommonCrypto
extension URL {
func calculateAWSS3MD5Hash(_ numberOfParts: UInt64) -> String? {
do {
var fileSize: UInt64!
var calculatedPartSize: UInt64!
let attr:NSDictionary? = try FileManager.default.attributesOfItem(atPath: self.path) as NSDictionary
if let _attr = attr {
fileSize = _attr.fileSize();
if numberOfParts != 0 {
let partSize = Double(fileSize / numberOfParts)
var partSizeInMegabytes = Double(partSize / (1024.0 * 1024.0))
partSizeInMegabytes = ceil(partSizeInMegabytes)
calculatedPartSize = UInt64(partSizeInMegabytes)
if calculatedPartSize % 2 != 0 {
calculatedPartSize += 1
}
if numberOfParts == 2 || numberOfParts == 3 { // Very important when there are 2 or 3 parts, in the majority of times
// the calculatedPartSize is already 8. In the remaining cases we force it.
calculatedPartSize = 8
}
if mainLogToggling {
print("The calculated part size is \(calculatedPartSize!) Megabytes")
}
}
}
if numberOfParts == 0 {
let string = self.memoryFriendlyMd5Hash()
return string
}
let hasher = AWS3MD5Hash.init()
let file = fopen(self.path, "r")
defer { let result = fclose(file)}
var index: UInt64 = 0
var bigString: String! = ""
var data: Data!
while autoreleasepool(invoking: {
if index == (numberOfParts-1) {
if mainLogToggling {
//print("Siamo all'ultima linea.")
}
}
data = hasher.data(from: file!, startingOnByte: index * calculatedPartSize * 1024 * 1024, length: calculatedPartSize * 1024 * 1024, filePath: self.path, singlePartSize: UInt(calculatedPartSize))
bigString = bigString + MD5.get(data: data) + "\n"
index += 1
if index == numberOfParts {
return false
}
return true
}) {}
let final = MD5.get(data :hasher.data(fromHexString: bigString)) + "-\(numberOfParts)"
return final
} catch {
}
return nil
}
func memoryFriendlyMd5Hash() -> String? {
let bufferSize = 1024 * 1024
do {
// Open file for reading:
let file = try FileHandle(forReadingFrom: self)
defer {
file.closeFile()
}
// Create and initialize MD5 context:
var context = CC_MD5_CTX()
CC_MD5_Init(&context)
// Read up to `bufferSize` bytes, until EOF is reached, and update MD5 context:
while autoreleasepool(invoking: {
let data = file.readData(ofLength: bufferSize)
if data.count > 0 {
data.withUnsafeBytes {
_ = CC_MD5_Update(&context, $0, numericCast(data.count))
}
return true // Continue
} else {
return false // End of file
}
}) { }
// Compute the MD5 digest:
var digest = Data(count: Int(CC_MD5_DIGEST_LENGTH))
digest.withUnsafeMutableBytes {
_ = CC_MD5_Final($0, &context)
}
let hexDigest = digest.map { String(format: "%02hhx", $0) }.joined()
return hexDigest
} catch {
print("Cannot open file:", error.localizedDescription)
return nil
}
}
struct MD5 {
static func get(data: Data) -> String {
var digest = [UInt8](repeating: 0, count: Int(CC_MD5_DIGEST_LENGTH))
let _ = data.withUnsafeBytes { bytes in
CC_MD5(bytes, CC_LONG(data.count), &digest)
}
var digestHex = ""
for index in 0..<Int(CC_MD5_DIGEST_LENGTH) {
digestHex += String(format: "%02x", digest[index])
}
return digestHex
}
// The following is a memory friendly version
static func get2(data: Data) -> String {
var currentIndex = 0
let bufferSize = 1024 * 1024
//var digest = [UInt8](repeating: 0, count: Int(CC_MD5_DIGEST_LENGTH))
// Create and initialize MD5 context:
var context = CC_MD5_CTX()
CC_MD5_Init(&context)
while autoreleasepool(invoking: {
var subData: Data!
if (currentIndex + bufferSize) < data.count {
subData = data.subdata(in: Range.init(NSMakeRange(currentIndex, bufferSize))!)
currentIndex = currentIndex + bufferSize
} else {
subData = data.subdata(in: Range.init(NSMakeRange(currentIndex, data.count - currentIndex))!)
currentIndex = currentIndex + (data.count - currentIndex)
}
if subData.count > 0 {
subData.withUnsafeBytes {
_ = CC_MD5_Update(&context, $0, numericCast(subData.count))
}
return true
} else {
return false
}
}) { }
// Compute the MD5 digest:
var digest = Data(count: Int(CC_MD5_DIGEST_LENGTH))
digest.withUnsafeMutableBytes {
_ = CC_MD5_Final($0, &context)
}
var digestHex = ""
for index in 0..<Int(CC_MD5_DIGEST_LENGTH) {
digestHex += String(format: "%02x", digest[index])
}
return digestHex
}
}
Now add:
#import "AWS3MD5Hash.h"
to your Objective-C Bridging header. You should be ok with this setup.
Example usage
To test this setup, you could be calling the following method inside the object that is in charge of handling the AWS connections:
func getMd5HashForFile() {
let credentialProvider = AWSCognitoCredentialsProvider(regionType: AWSRegionType.USEast2, identityPoolId: "<INSERT_POOL_ID>")
let configuration = AWSServiceConfiguration(region: AWSRegionType.APSoutheast2, credentialsProvider: credentialProvider)
configuration?.timeoutIntervalForRequest = 3.0
configuration?.timeoutIntervalForResource = 3.0
AWSServiceManager.default().defaultServiceConfiguration = configuration
AWSS3.register(with: configuration!, forKey: "defaultKey")
let s3 = AWSS3.s3(forKey: "defaultKey")
let headObjectRequest = AWSS3HeadObjectRequest()!
headObjectRequest.bucket = "<NAME_OF_YOUR_BUCKET>"
headObjectRequest.key = self.latestMapOnServer.key
let _: AWSTask? = s3.headObject(headObjectRequest).continueOnSuccessWith { (awstask) -> Any? in
let headObjectOutput: AWSS3HeadObjectOutput? = awstask.result
var ETag = headObjectOutput?.eTag!
// Here you should parse the returned Etag and extract the number of parts to provide to the helper function. Etags end with a "-" followed by the number of parts. If you don't see this format, then pass 0 as the number of parts.
ETag = ETag!.replacingOccurrences(of: "\"", with: "")
print("headObjectOutput.ETag \(ETag!)")
let mapOnDiskUrl = self.getMapsDirectory().appendingPathComponent(self.latestMapOnDisk!)
let hash = mapOnDiskUrl.calculateAWSS3MD5Hash(<Take the number of parts from the ETag returned by the server>)
if hash == ETag {
print("They are the same.")
}
print ("\(hash!)")
return nil
}
}
If the ETag returned by the server does not have "-" at the end of the ETag, just pass 0 to calculateAWSS3MD5Hash. Please comment if you encounter any problems. I am working on a swift only solution, I will update this answer as soon as I finish. Thanks
I just saw that the AWS S3 Console 'upload' uses an unusual part (chunk) size of 17,179,870 - at least for larger files.
Using that part size gave me the correct ETag hash using the methods described earlier. Thanks to #TheStoryCoder for the php version.
Thanks to #hans for his idea to use head-object to see the actual sizes of each part.
I used the AWS S3 Console (on Nov28 2020) to upload about 50 files ranging in size from 190MB to 2.3GB and all of them had the same part size of 17,179,870.
I liked Emerson's leading answer above - especially the xxd part - but I was too lazy to use dd so I went with split, guessing at an 8M chunk size because I uploaded with aws s3 cp:
$ split -b 8M large.iso XXX
$ md5sum XXX* > checksums.txt
$ sed -i 's/ .*$//' checksums.txt
$ xxd -r -p checksums.txt | md5sum
99a090df013d375783f0f0be89288529 -
$ wc -l checksums.txt
80 checksums.txt
$
It was immediately obvious that both parts of my S3 etag matched my file's calculated etag.
UPDATE:
This has been working nicely:
$ ll large.iso
-rw-rw-r-- 1 user user 669134848 Apr 12 2021 large.iso
$
$ etag large.iso
99a090df013d375783f0f0be89288529-80
$
$ type etag
etag is a function
etag ()
{
split -b 8M --filter=md5sum $1 | cut -d' ' -f1 | pee "xxd -r -p | md5sum | cut -d' ' -f1" "wc -l" | paste -d'-' - -
}
$
All the other answers assume a standard and regular part size. But that assumption may not be true. Across the console and various SDKs there are different defaults. And the low-level API does allow a lot of variety.
Complications:
S3 multi-part uploads can have parts of any size (within a min and max for non-last parts).
Even the non-last parts can be different sizes.
When you upload they don't have to be consecutive part numbers.
If you do a multi-part upload with only 1 part, the etag is the more complicated version, not the simple MD5
etags tend to be wrapped in double-quotes. I don't know why. But that's just a thing that might trip you up.
So we need find find out how many parts there are, and how big they are.
You cannot reliably get the part count from boto3's Object.parts_count attribute. I don't know if the same is true of other SDKs.
The get_object_attributes API documentation claims that it returns a list of parts and sizes. But when I tested those fields were missing. Even for multi-part uploads that were not completed.
Even if you assume equal part sizes (except the last part), you cannot deduce part size from content length and part count. e.g. if a 90MB file has 3 parts, was that 30MBx3, or 40MB+40MB+10MB?
Let's assume that you have a local file and you want to check whether it matches the content of the object in S3.
(And assume that you've already checked whether the lengths differ, because that's a faster check.)
Here's a python3 script to do that. (I chose python just because that's what I'm familiar with.)
We use head_object to get the e-tag. With the e-tag we can deduce whether it was a single-part upload or multi-part, and how many parts.
We use head_object passing in PartNumber, calling that for each part, to get the length of each part. You could use multiprocessing to speed that up. (Noting that boto3's client should not be passed between processes.)
import boto3
from hashlib import md5
def content_matches(local_path, bucket, key) -> bool:
client = boto3.client('s3')
resp = client.head_object(Bucket=bucket, Key=key)
remote_e_tag = resp['ETag']
total_length = resp['ContentLength']
if '-' not in remote_e_tag:
# it was a single-part upload
m = md5()
# you could read from the file in chunks to avoid loading the whole thing into memory
# the chunks would not have to match any SDK standard. It can be whatever you want.
# (The MD5 library will act as if you hashed in one go)
with open(file, 'rb') as f:
local_etag = f'"md5(f.read()).hexdigest()"'
return local_etag == remote_e_tag
else:
# multi-part upload
# to find the number of parts, get it from the e-tag
# e.g. 123-56 has 56 parts
num_parts = int(remote_e_tag.strip('"').split('-')[-1])
print(f"Assuming {num_parts=} from {remote_e_tag=}")
md5s = []
with open(local_path, 'rb') as f:
sz_read = 0
for part_num in range(1,num_parts+1):
resp = client.head_object(Bucket=bucket, Key=key, PartNumber=part_num)
sz_read += resp['ContentLength']
local_data_part = f.read(resp['ContentLength'])
assert len(local_data_part) == resp['ContentLength'] # sanity check
md5s.append(md5(local_data_part))
assert sz_read == total_length, "Sum of part sizes doesn't equal total file size"
digests = b''.join(m.digest() for m in md5s)
digests_md5 = md5(digests)
local_etag = f'"{digests_md5.hexdigest()}-{len(md5s)}"'
return remote_e_tag == local_etag
And a script to test it with all those edge cases:
import boto3
from pprint import pprint
from hashlib import md5
from main import content_matches
MB = 2 ** 20
bucket = 'mybucket'
key = 'test-multi-part-upload'
local_path = 'test-data'
# first upload the object
s3 = boto3.resource('s3')
obj = s3.Object(bucket, key)
mpu = obj.initiate_multipart_upload()
parts = []
part_sizes = [6 * MB, 5 * MB, 5] # deliberately non-standard and not consistent
upload_part_nums = [1,3,8] # test non-consecutive part numbers for upload
with open(local_path, 'wb') as fw:
with open('/dev/random', 'rb') as fr:
for (part_num, part_size) in zip(upload_part_nums, part_sizes):
part = mpu.Part(part_num)
data = fr.read(part_size)
print(f"Uploading part {part_num}")
resp = part.upload(Body=data)
parts.append({
'ETag': resp['ETag'],
'PartNumber': part_num
})
fw.write(data)
resp = mpu.complete(MultipartUpload={
'Parts': parts
})
obj.reload()
assert content_matches(local_path, bucket, key)
"#wim Any idea how to calculate the ETag when SSE is enabled?"
in my testing, multipart+SEE-C, the Etag is valid.
can be calculated from the individual Etag returned for each part.
and this is easy to prove.
let's say we have a multipart upload with SEE-C, with 10 parts.
take the 10 Etags, put them in a file, and run "xxd -r -p checksums.txt | md5sum", the calculdated value with match the value returned from aws
etag parts
-------------------------------
1330e1275b556ab6702bca9438f62c15 -
ae55d3ddf52e33d45140a5be6dacb925 -
16dc956e05962b84ad9cd74a05e86797 -
64be66992a5110c4b1151a8249258a1a -
4926df0200fe24499524176d6a85e347 -
2b6655c3506481eb1fae6b2e2e7c4b8b -
a02e9dbd49039eaf4d6de1fddc5e1a30 -
afb7bc1f6e0c1f23671cb7116f3b0c63 -
dddf3a1ab192f26bb483a3e2778bab13 -
adb8b2b761640418856853f3810ac45a -
-------------------------------
etag_from_aws = c68db040f8a36c164259bcca40c36410-10
etag_calculated = c68db040f8a36c164259bcca40c36410-10
No,
Till now there is not solution to match normal file ETag and Multipart file ETag and MD5 of local file.

Batch file renaming – inserting text from a list (in Python or Java)

I'm finishing a business card production flow (excel > xml > indesign > single page pdfs) and I would like to insert the employees' names in the filenames.
What I have now:
BusinessCard_01_Blue.pdf
BusinessCard_02_Blue.pdf
BusinessCard_03_Blue.pdf (they are gonna go up to the hundreds)
What I need (I can manipulate the name list with regex easily):
BusinessCard_01_CarlosJorgeSantos_Blue.pdf
BusinessCard_02_TaniaMartins_Blue.pdf
BusinessCard_03_MarciaLima_Blue.pdf
I'm a Java and Python toddler. I've read the related questions, tried this in Automator (Mac) and Name Mangler, but couldn't get it to work.
Thanks in advance,
Gus
Granted you have a map where to look at the right name you could do something like this in Java:
List<Files> originalFiles = ...
for( File f : originalFiles ) {
f.renameTo( new File( getNameFor( f ) ) );
}
And define the getNameFor to something like:
public String getNameFor( File f ) {
Map<String,String> namesMap = ...
return namesMap.get( f.getName() );
}
In the map you'll have the associations:
BusinessCard_01_Blue.pdf => BusinessCard_01_CarlosJorgeSantos_Blue.pdf
Does it make sense?
In Python (tested):
#!/usr/bin/python
import sys, os, shutil, re
try:
pdfpath = sys.argv[1]
except IndexError:
pdfpath = os.curdir
employees = {1:'Bob', 2:'Joe', 3:'Sara'} # emp_id:'name'
files = [f for f in os.listdir(pdfpath) if re.match("BusinessCard_[0-9]+_Blue.pdf", f)]
idnumbers = [int(re.search("[0-9]+", f).group(0)) for f in files]
filenamemap = zip(files, [employees[i] for i in idnumbers])
newfiles = [re.sub('Blue.pdf', e + '_Blue.pdf', f) for f, e in filenamemap]
for old, new in zip(files, newfiles):
shutil.move(os.path.join(pdfpath, old), os.path.join(pdfpath, new))
EDIT: This now alters only those files that have not yet been altered.
Let me know if you want something that will build the the employees dictionary automatically.
If you have a list of names in the same order the files are produced, in Python it goes like this untested fragment:
#!/usr/bin/python
import os
f = open('list.txt', 'r')
for n, name in enumerate(f):
original_name = 'BusinessCard_%02d_Blue.pdf' % (n + 1)
new_name = 'BusinessCard_%02d_%s_Blue.pdf' % (
n, ''.join(name.title().split()))
if os.path.isfile(original_name):
print "Renaming %s to %s" % (original_name, new_name),
os.rename(original_name, new_name)
print "OK!"
else:
print "File %s not found." % original_name
Python:
Assuming you have implemented the naming logic already:
for f in os.listdir(<directory>):
try:
os.rename(f, new_name(f.name))
except OSError:
# fail
You will, of course, need to write a function new_name which takes the string "BusinessCard_01_Blue.pdf" and returns the string "BusinessCard_01_CarlosJorgeSantos_Blue.pdf".

Categories