'first_feature': 2.,
'second_feature': 12.,
}
# First, we delete any existing `models/` folder on HDFS.
client.delete('models', recursive=True)
# We can now upload the data, first as CSV.
with client.write('models/1.csv', encoding='utf-8') as writer:
for item in model.items():
writer.write(u'%s,%s\n' % item)
# We can also serialize it to JSON and directly upload it.
with client.write('models/1.json', encoding='utf-8') as writer:
dump(model, writer)
# We can check that the files exist and get their properties.
assert client.list('models') == ['1.csv', '1.json']
status = client.status('models/1.csv')
content = client.content('models/1.json')
# Later, we can download the files back. The `delimiter` option makes it
# convenient to read CSV files.
with client.read('models/1.csv', delimiter='\n', encoding='utf-8') as reader:
items = (line.split(',') for line in reader if line)
assert dict((name, float(value)) for name, value in items) == model
# Loading JSON directly from HDFS is even simpler.
with client.read('models/1.json', encoding='utf-8') as reader:
assert load(reader) == model
class SparkHDFSClient(object):
def __init__(self, datasource):
self.datasource = datasource
self.client = Config().get_client("dev")
def get_file_list(self, folder):
files = self.client.list(folder.strip())
files = [folder + '/' + file for file in files]
return files
def list_collections(self):
results = []
status = self.client.status(self.datasource.url, strict=False)
print(status, self.datasource.url)
if status is not None:
if status['type'] == "DIRECTORY":
files = self.get_file_list(self.datasource.url)
while len(files) > 0:
file = files.pop()
status = self.client.status(os.path.join(
self.datasource.url, file),
strict=False)
if status is None:
continue
if status['type'] == "DIRECTORY":
subfiles = self.get_file_list(
os.path.join(self.datasource.url, file))
files.extend(subfiles)
continue
else:
if self.datasource.dstype == DataSourceType.SPARK_CSV and file[-2:] != 'sv' \
or self.datasource.dstype == DataSourceType.SPARK_TSV and file[-2:] != 'sv'\
or self.datasource.dstype == DataSourceType.SPARK_XML and file[-3:] != 'xml'\
or self.datasource.dstype == DataSourceType.SPARK_JSON and file[-4:] != 'json':
continue
row = {
"db":
file[:file.rfind('/')]
if '/' in file else self.datasource.url,
"document":
file[file.rfind('/') +
1:] if '/' in file else file,
"count":
-1
}
results.append(row)
return results
else:
return [{
"db": self.datasource.url,
"document": self.datasource.url,
"count": -1
}]
else:
return results
def get_documents(self, filename, limit=10):
results = []
delimiter = "\n"
header = None
rows = 0
if self.datasource.dstype == DataSourceType.SPARK_CSV or \
self.datasource.dstype == DataSourceType.SPARK_TSV:
delimiter = "\n"
with self.client.read(filename,
encoding='utf-8',
delimiter=delimiter) as reader:
for line in reader:
if len(line.strip()) == 0 or line[0] == '#':
continue
if filename[-3:] == "csv":
line = line.split(',')
else:
line = line.split('\t')
if header is None:
header = line
continue
res = {
header[i]: line[i]
for i in range(len(line)) if i < len(header)
}
results.append(res)
rows += 1
if rows > limit + 1:
break
elif self.datasource.dstype == DataSourceType.SPARK_XML:
with self.client.read(filename, encoding='utf-8',
chunk_size=2048) as reader:
header = ['content']
for chunk in reader:
res = {'content': str(chunk)}
results.append(res)
print(results)
break
elif self.datasource.dstype == DataSourceType.SPARK_JSON:
with self.client.read(filename, encoding='utf-8') as reader:
model = load(reader)
if isinstance(model, list):
model = [{
p:
str(list(md[p][0].keys())) if isinstance(md[p], list)
and isinstance(md[p][0], dict) else str(model[p])
if isinstance(md[p], list) else str(list(md[p].keys()))
if isinstance(md[p], dict) else md[p]
for p in md
} for md in model]
results.extend(model)
else:
model = {
p: str(list(model[p][0].keys()))
if isinstance(model[p], list) and isinstance(
model[p][0], dict) else model[p] if isinstance(
model[p], list) else str(list(model[p].keys()))
if isinstance(model[p], dict) else model[p]
for p in model
}
results.append(model)
return results[:limit], limit
class HadoopWebExplorer:
def __init__(self, debug=False):
path = os.path.join(os.path.dirname(os.path.abspath(__file__)),
'.hdfscli.cfg')
self.client = Config(path).get_client()
self.debug = debug
def print(self, *args):
if self.debug:
print(*args)
def path_exists(self, path):
"""
Checks whether such path already exists
:param path: path to check
:type path: unicode
:return: boolean flag indicating whether path already exists or not
:rtype: bool
"""
return self.client.status(path, strict=False) is not None
@catch_hdfs_error
def create_folder(self, folder_name):
"""
Creates folder with the given name if it does not exist
:param folder_name: the name of the folder we want to add
:type folder_name: unicode
:return: returns true if created folder or it already exists, otherwise false
:rtype: bool
"""
if self.path_exists(folder_name):
print(f'Folder already exists: {folder_name}')
return True
self.print(f'Folder does not exist: {folder_name}')
self.client.makedirs(folder_name)
self.print(f'Folder created: {folder_name}')
@catch_hdfs_error
def write_to_file(self,
folder_name,
file_name,
data,
overwrite=False,
append=False):
"""
Writes provided data into file in the specified folder
:param folder_name: name of the folder where file is located
:type folder_name: unicode
:param file_name: name of the file where data should be written to
:type file_name: unicode
:param data: data to be written
:type data: unicode
:param overwrite: overwrite any existing file or directory
:type overwrite: bool
:param append: append to a file rather than create a new one.
:type append: bool
:return: returns true if it successfully wrote the data, otherwise false
:rtype: bool
"""
path = os.path.join(folder_name, file_name)
if append and not self.path_exists(path):
self.client.write(path,
data,
encoding='utf-8',
overwrite=overwrite)
else:
self.client.write(path,
data,
encoding='utf-8',
overwrite=overwrite,
append=append)
self.print("Written data to HDFS file")
@catch_hdfs_error
def read_from_file(self, folder_name, file_name):
"""
Reads from file in the specified folder
:param folder_name: name of the folder where file is located
:type folder_name: unicode
:param file_name: name of the file where data should be read from
:type file_name: unicode
"""
path = os.path.join(folder_name, file_name)
if not self.path_exists(path):
self.print(f'File does not exists: {path}')
return None
return self.client.read(path)
@catch_hdfs_error
def delete_file(self, folder_name, file_name):
"""
Deletes file in the specified folder
:param folder_name: name of the folder where file is located
:type folder_name: unicode
:param file_name: name of the file to be deleted
:type file_name: unicode
:return: returns true if it successfully deleted the file, otherwise false
:rtype: bool
"""
path = os.path.join(folder_name, file_name)
return self.client.delete(path)
@catch_hdfs_error
def delete_folder(self, folder_name):
"""
Deletes the specified folder
:param folder_name: name of the folder where file is located
:type folder_name: unicode
:return: returns true if it successfully deleted the folder, otherwise false
:rtype: bool
"""
return self.client.delete(folder_name, recursive=True)
@catch_hdfs_error
def explore_folder(self, folder_name):
"""
Explores the specified folder
:param folder_name: name of the folder to be observed
:type folder_name: unicode
"""
if not self.path_exists(folder_name):
self.print(f'Folder does not exists: {folder_name}')
self.print(f'Exploring folder: {folder_name}')
for path, dirs, files in self.client.walk(folder_name, status=True):
for file in files:
block_size = file[1]['blockSize']
size = file[1]['length']
owner = file[1]['owner']
self.print(
f'\tFile: {file[0]}, blockSize: {block_size}, size: {size}, owner: {owner}'
)
from hdfs import Config, InsecureClient
import cPickle as pickle
from tuple import Tuple
client = Config().get_client('dev')
client.write('a/p', 'aaa', overwrite=True)
print client.status('a')
from hdfs import Config from sys import argv from math import ceil script, filename = argv client = Config().get_client() status = client.status(filename) print(ceil(status['length'] / status['blockSize']))
