You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
64 lines
2.2 KiB
64 lines
2.2 KiB
"""Contains data helper functions."""
|
|
from __future__ import absolute_import
|
|
from __future__ import division
|
|
from __future__ import print_function
|
|
|
|
import json
|
|
import codecs
|
|
import os
|
|
import tarfile
|
|
from paddle.v2.dataset.common import md5file
|
|
|
|
|
|
def read_manifest(manifest_path, max_duration=float('inf'), min_duration=0.0):
|
|
"""Load and parse manifest file.
|
|
|
|
Instances with durations outside [min_duration, max_duration] will be
|
|
filtered out.
|
|
|
|
:param manifest_path: Manifest file to load and parse.
|
|
:type manifest_path: basestring
|
|
:param max_duration: Maximal duration in seconds for instance filter.
|
|
:type max_duration: float
|
|
:param min_duration: Minimal duration in seconds for instance filter.
|
|
:type min_duration: float
|
|
:return: Manifest parsing results. List of dict.
|
|
:rtype: list
|
|
:raises IOError: If failed to parse the manifest.
|
|
"""
|
|
manifest = []
|
|
for json_line in codecs.open(manifest_path, 'r', 'utf-8'):
|
|
try:
|
|
json_data = json.loads(json_line)
|
|
except Exception as e:
|
|
raise IOError("Error reading manifest: %s" % str(e))
|
|
if (json_data["duration"] <= max_duration and
|
|
json_data["duration"] >= min_duration):
|
|
manifest.append(json_data)
|
|
return manifest
|
|
|
|
|
|
def download(url, md5sum, target_dir):
|
|
"""Download file from url to target_dir, and check md5sum."""
|
|
if not os.path.exists(target_dir): os.makedirs(target_dir)
|
|
filepath = os.path.join(target_dir, url.split("/")[-1])
|
|
if not (os.path.exists(filepath) and md5file(filepath) == md5sum):
|
|
print("Downloading %s ..." % url)
|
|
os.system("wget -c " + url + " -P " + target_dir)
|
|
print("\nMD5 Chesksum %s ..." % filepath)
|
|
if not md5file(filepath) == md5sum:
|
|
raise RuntimeError("MD5 checksum failed.")
|
|
else:
|
|
print("File exists, skip downloading. (%s)" % filepath)
|
|
return filepath
|
|
|
|
|
|
def unpack(filepath, target_dir, rm_tar=False):
|
|
"""Unpack the file to the target_dir."""
|
|
print("Unpacking %s ..." % filepath)
|
|
tar = tarfile.open(filepath)
|
|
tar.extractall(target_dir)
|
|
tar.close()
|
|
if rm_tar == True:
|
|
os.remove(filepath)
|