def query(self, starttime, endtime):
"""Query and retrieve data within the specified range.
Checks for data in the specified range and retrieves any new files.
After execution is completed, the same range is checked again to see
if any new files have appeared since the first execution. This continues
until no new files are found (for xxx minutes?)
"""
urls = []
fmt = '%Y-%m-%d %H:%M:%S'
logging.info("Querying time range %s - %s", starttime.strftime(fmt),
endtime.strftime(fmt))
for browser in self.browsers:
matches = self.query_server(browser, starttime, endtime)
if len(matches) > 0:
urls.append(matches)
# Remove duplicate files, randomizing to spread load across servers
if len(urls) > 1:
urls = self._deduplicate(urls)
# Filter out files that are already in the database
new_urls = []
for url_list in urls:
filtered = None
while filtered is None:
try:
filtered = list(filter(self._filter_new, url_list))
except mysqld.OperationalError:
# MySQL has gone away -- try again in 5s
logging.warning((
"Unable to access database to check for file existence. Will try again in 5 seconds."
))
time.sleep(5)
# Try and reconnect
# @note: May be a good idea to move the reconnect
# functionality to the db module and have it occur
# for all queries.
try:
self._db, self._cursor = get_db_cursor(
self.dbhost, self.dbname, self.dbuser, self.dbpass)
except:
pass
new_urls.append(filtered)
# check disk space
if not self.sent_diskspace_warning:
self._check_free_space()
# acquire the data files
self.acquire(new_urls)
def query(self, starttime, endtime):
"""Query and retrieve data within the specified range.
Checks for data in the specified range and retrieves any new files.
After execution is completed, the same range is checked again to see
if any new files have appeared since the first execution. This continues
until no new files are found (for xxx minutes?)
"""
urls = []
fmt = '%Y-%m-%d %H:%M:%S'
logging.info("Querying time range %s - %s", starttime.strftime(fmt),
endtime.strftime(fmt))
for browser in self.browsers:
matches = self.query_server(browser, starttime, endtime)
if len(matches) > 0:
urls.append(matches)
# Remove duplicate files, randomizing to spread load across servers
if len(urls) > 1:
urls = self._deduplicate(urls)
# Filter out files that are already in the database
new_urls = []
for url_list in urls:
filtered = None
while filtered is None:
try:
filtered = filter(self._filter_new, url_list)
except MySQLdb.OperationalError:
# MySQL has gone away -- try again in 5s
logging.warning(("Unable to access database to check for file"
" existence. Will try again in 5 seconds."))
time.sleep(5)
# Try and reconnect
# @note: May be a good idea to move the reconnect
# functionality to the db module and have it occur
# for all queries.
try:
self._db = get_db_cursor(self.dbname, self.dbuser, self.dbpass)
except:
pass
new_urls.append(filtered)
# check disk space
if not self.sent_diskspace_warning:
self._check_free_space()
# acquire the data files
self.acquire(new_urls)
def __init__(self, servers, browse_method, download_method, conf):
"""Explain."""
# MySQL/Postgres info
self.dbname = conf.get('database', 'dbname')
self.dbuser = conf.get('database', 'user')
self.dbpass = conf.get('database', 'pass')
self.downloaders = []
try:
self._db = get_db_cursor(self.dbname, self.dbuser, self.dbpass)
except MySQLdb.OperationalError:
logging.error(
"Unable to access MySQL. Is the database daemon running?")
self.shutdown()
self.stop()
# Email notification
self.email_server = conf.get('notifications', 'server')
self.email_from = conf.get('notifications', 'from')
self.email_to = conf.get('notifications', 'to')
# Warning flags
self.sent_diskspace_warning = False
# Maximum number of simultaneous downloads
self.max_downloads = conf.getint('network', 'max_downloads')
# Directories
self.working_dir = os.path.expanduser(
conf.get('directories', 'working_dir'))
self.image_archive = os.path.expanduser(
conf.get('directories', 'image_archive'))
self.incoming = os.path.join(self.working_dir, 'incoming')
self.quarantine = os.path.join(self.working_dir, 'quarantine')
# Check directory permission
self._init_directories()
# Load data server, browser, and downloader
self.servers = self._load_servers(servers)
self.browsers = []
self.downloaders = []
self.queues = []
# For each server instantiate a browser and one or more downloaders
for server in self.servers:
self.browsers.append(self._load_browser(browse_method, server))
queue = Queue.Queue()
self.queues.append(queue)
self.downloaders.append([
self._load_downloader(download_method, queue)
for i in range(self.max_downloads)
])
# Shutdown switch
self.shutdown_requested = False
def __init__(self, servers, browse_method, download_method, conf):
"""Explain."""
# MySQL/Postgres info
self.dbname = conf.get('database', 'dbname')
self.dbuser = conf.get('database', 'user')
self.dbpass = conf.get('database', 'pass')
self.downloaders = []
try:
self._db = get_db_cursor(self.dbname, self.dbuser, self.dbpass)
except MySQLdb.OperationalError:
logging.error("Unable to access MySQL. Is the database daemon running?")
self.shutdown()
self.stop()
# Email notification
self.email_server = conf.get('notifications', 'server')
self.email_from = conf.get('notifications', 'from')
self.email_to = conf.get('notifications', 'to')
# Warning flags
self.sent_diskspace_warning = False
# Maximum number of simultaneous downloads
self.max_downloads = conf.getint('network', 'max_downloads')
# Directories
self.working_dir = os.path.expanduser(conf.get('directories',
'working_dir'))
self.image_archive = os.path.expanduser(conf.get('directories',
'image_archive'))
self.incoming = os.path.join(self.working_dir, 'incoming')
self.quarantine = os.path.join(self.working_dir, 'quarantine')
# Check directory permission
self._init_directories()
# Load data server, browser, and downloader
self.servers = self._load_servers(servers)
self.browsers = []
self.downloaders = []
self.queues = []
# For each server instantiate a browser and one or more downloaders
for server in self.servers:
self.browsers.append(self._load_browser(browse_method, server))
queue = Queue.Queue()
self.queues.append(queue)
self.downloaders.append([self._load_downloader(download_method, queue)
for i in range(self.max_downloads)])
# Shutdown switch
self.shutdown_requested = False
def main(argv):
'''Main application access point'''
options = get_options()
init_logger('update.log')
print('Processing Images...')
# Get a list of images to process
filepaths = find_images(options.source)
if len(filepaths) is 0:
return
images = []
# Move images to main archive
for filepath in filepaths:
dest = os.path.join(options.destination,
os.path.relpath(filepath, options.source))
# Parse image header
image_params = create_image_data(filepath)
image_params['filepath'] = dest
images.append(image_params)
directory = os.path.dirname(dest)
if not os.path.isdir(directory):
os.makedirs(directory)
shutil.move(filepath, dest)
# Add images to the database
db, cursor = get_db_cursor(options.dbhost, options.dbname, options.dbuser,
options.dbpass)
process_jp2_images(images, options.destination, cursor, True)
cursor.close()
print('Finished!')
def main(argv):
'''Main application access point'''
options = get_options()
init_logger('update.log')
print('Processing Images...')
# Get a list of images to process
filepaths = find_images(options.source)
if len(filepaths) is 0:
return
images = []
# Move images to main archive
for filepath in filepaths:
dest = os.path.join(options.destination,
os.path.relpath(filepath, options.source))
# Parse image header
image_params = sunpy.read_header(filepath)
image_params['filepath'] = dest
images.append(image_params)
directory = os.path.dirname(dest)
if not os.path.isdir(directory):
os.makedirs(directory)
shutil.move(filepath, dest)
# Add images to the database
cursor = get_db_cursor(options.dbname, options.dbuser, options.dbpass)
process_jp2_images(images, options.destination, cursor, True)
cursor.close()
print('Finished!')
