Skip to content

Add zip to tar function #4

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
yinlinchen wants to merge 3 commits into
base: dev
Choose a base branch
from
Open

Add zip to tar function #4

Changes from 1 commit
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
11aef69
Add zip to tar function
yinlinchen Sep 30, 2020
bf19330
add test cases as requested
yinlinchen Oct 5, 2020
43200cf
fix eperson error exportAipFromDSpaceToStorageFolder
sindtd Oct 8, 2020
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
30 changes: 23 additions & 7 deletions dspace_aip_archiver.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,6 +22,7 @@
from sqlite3 import Error
from subprocess import run
from time import strftime
from zipfile import ZipFile


class ProgressPercentage(object):
Expand Down Expand Up @@ -104,11 +105,19 @@ def exportAipFromDSpaceToStorageFolder(handle, configData):
cli = configData["dspace"]["DSPACE_CLI"]
eperson = "-e " + configData["dspace"]["DSPACE_EPERSON"]
item = "-i " + handle
file_name = handle.replace("/", "-") + ".tar"
file_name = handle.replace("/", "-") + ".zip"
destination = join(configData["dspace"]["EXPORT_LOCATION"], file_name)
run([cli, "packager", "-d", "-t AIP", eperson, item, destination])


def unZipFile(fileName, sourceFilePath):

with ZipFile(sourceFilePath + "/" + fileName, 'r') as zipObj:
zipObj.extractall(sourceFilePath + "/temp/")

os.remove(sourceFilePath + "/" + fileName)


def getHandleId(record):

handleid = ""
Expand Down Expand Up @@ -252,7 +261,7 @@ def saveToTargetFile(fileName, content, path):
file.write(content)


def createTarFile(fileName, sourceFilePath, targetFilePath, title):
def createTarFile(fileName, sourceFilePath, targetFilePath):

allItem = os.listdir(sourceFilePath)
with tarfile.open(os.path.join(targetFilePath, fileName), 'w:gz') as tar:
Expand Down Expand Up @@ -318,15 +327,23 @@ def cleanFolder(folderPath):
title = getValueFromField(record, "title")
desc = getValueFromField(record, "description")
identifier = getHandleId(record.getField("identifier"))
dspaceExportFileName = identifier.replace("/", "-") + ".zip"
bagitFileName = identifier.replace("/", "-") + ".tar"

logging.info(
"Handle %s: Start export handle file and create APTrust bagit",
identifier)
exportAipFromDSpaceToStorageFolder(
identifier,
configData)
if os.path.exists(export_location + bagitFileName):
if os.path.exists(export_location + dspaceExportFileName):
unZipFile(dspaceExportFileName, export_location)
createTarFile(
bagitFileName,
export_location +
"/temp/",
export_location)
cleanFolder(export_location + "/temp/")
os.rmdir(export_location + "/temp/")
noid = getNoidFromDB(conn, identifier, noid_template)
fileCount = [1, 1]
bagitInfo = createBagitInfo(configData, noid, fileCount)
Expand All @@ -339,8 +356,7 @@ def cleanFolder(folderPath):
createTarFile(
bagitFileName,
export_location,
storage_location,
bagitFileName)
storage_location)
uploadFileToS3(
storage_location + bagitFileName,
configData["s3"]["bucket_name"], bagitFileName)
Expand All @@ -351,7 +367,7 @@ def cleanFolder(folderPath):
"Handle %s: APTrust bagit uploaded to s3",
identifier)
else:
logging.info("Handle %s file not found", bagitFileName)
logging.info("Handle %s file not found", dspaceExportFileName)

conn.close()

Expand Down