def pull(self,pattern='.*'):
""" Pulls the Easy CORA file from the copernicus FTP server , and unpacks them
:param pattern (string) only download data which obey this regular expression file pattern (e.g. 20[0-9][0-9] to download from 2000 and onward)
"""
ftproot="ftp://my.cmems-du.eu/Core/INSITU_GLO_TS_REP_OBSERVATIONS_013_001_b/CORIOLIS-GLOBAL-EasyCORA-OBS/global"
#get cmems authentication details from database
cred=self.conf.authCred("cmems")
ftpcr=ftpCrawler(ftproot,auth=cred, pattern=pattern)
updated=ftpcr.parallelDownload(self.cacheDir(),check=True,maxconn=10,continueonError=True)
#unpack the downloaded files in the data directory
datadir=self.dataDir()
for tarf in [UriFile(f) for f in findFiles(self.cacheDir(),".*tgz$")]:
succesfile=os.path.join(datadir,os.path.basename(tarf.url)+".isextracted")
try:
#check if the files need unpacking (only unpack when needed)
#check if the last file is already extracted
if os.path.exists(succesfile):
slurplogger().info(f"{tarf.url} is already extracted, skipping")
else:
with tarfile.open(tarf.url,"r:gz") as tf:
slurplogger().info(f"Extracting trajectory files from {tarf.url}")
tf.extractall(datadir)
#touch the sucessfile to indcate this archive has been sucessfully extracted
Path(succesfile).touch()
except tarfile.ReadError as exc:
raise exc
def register(self, center=None):
"""register downloaded commbined prof files"""
#create a list of files which need to be (re)registered
if self.updated:
files = self.updated
else:
slurplogger().info("Building file list..")
files = [
UriFile(file) for file in findFiles(self.dataDir(), '.*nc',
self._dbinvent.lastupdate)
]
if len(files) == 0:
slurplogger().info("Argo: No new files found since last update")
return
filesnew = self.retainnewUris(files)
if len(filesnew) == 0:
slurplogger().info("Argo: No database update needed")
return
#loop over files
for uri in filesnew:
if center and not re.search(center, uri.url):
continue
meta = argoMetaExtractor(uri)
if meta:
self.addEntry(meta)
self.updateInvent()
def register(self):
slurplogger().info("Building file list..")
files=[UriFile(file) for file in findFiles(self.dataDir(),'.*gz',self._dbinvent.lastupdate)]
# import pdb;pdb.set_trace()
filesnew=self.retainnewUris(files)
if len(filesnew) == 0:
slurplogger().info("GRDC: No database update needed")
return
# filesnew=[UriFile(os.path.join(self.dataDir(),"4208270_Q_Month.txt.gz"))]
#loop over files
for uri in filesnew:
meta=GRDCmetaExtractor(uri)
self.addEntry(meta)
self.updateInvent()
def register(self):
slurplogger().info("Building file list..")
files=[UriFile(file) for file in findFiles(self.dataDir(),'.*love',self._dbinvent.lastupdate)]
if len(files) == 0:
slurplogger().info("LLove: No new files found since last update")
return
filesnew=self.retainnewUris(files)
if len(filesnew) == 0:
slurplogger().info("LLove: No database update needed")
return
#loop over files
for uri in filesnew:
self.addEntry(lloveMetaExtractor(uri))
self.updateInvent()
def register(self,pattern='.*\.nc$'):
"""Register downloaded trajectory files from CORA
:param pattern (string) file pattern to look for (defaults to all files ending with .nc)
"""
#create a list of files which need to be (re)registered
newfiles=self.retainnewUris([UriFile(file) for file in findFiles(self.dataDir(),pattern)])
for uri in newfiles:
meta=coraMetaExtractor(uri)
if not meta:
#don't register empty entries
continue
self.addEntry(meta)
self._dbinvent.data["Description"]="EasyCora output data table"
self._dbinvent.data["CORAversion"] = "5.2"
self.updateInvent()
def register(self):
slurplogger().info("Building file list..")
files = [
UriFile(file) for file in findFiles(self.cacheDir(), '.*love',
self._dbinvent.lastupdate)
]
if len(files) == 0:
slurplogger().info("LLove: No new files found since last update")
return
self.truncateTable()
#loop over files
for uri in files:
self.addEntry(lloveMetaExtractor(uri))
self.updateInvent()
def register(self):
#create a list of files which need to be (re)registered
if self.updated:
files = self.updated
else:
files = [
UriFile(file) for file in findFiles(self.dataDir(), 'G.*\.gz',
self._dbinvent.lastupdate)
]
filesnew = self.retainnewUris(files)
#loop over the newer files
for uri in filesnew:
meta = graceMetaExtractor(uri)
self.addEntry(meta)
self.updateInvent()
def register(self):
if not self.table:
#create a new table on the fly
self.createTable(self.columns)
#create a list of files which need to be (re)registered
newfiles = self.retainnewUris([
UriFile(file)
for file in findFiles(self.dataDir(), f".*\{self.app}$")
])
for uri in newfiles:
meta = self.metaExtractor(uri)
if not meta:
#don't register empty entries
continue
slurplogger().info(f"Adding metadata from {uri.url}")
self.addEntry(meta)
self._dbinvent.data["Description"] = self.description
self.updateInvent()
def register(self):
""" Register all downloaded fronts (in text files)"""
slurplogger().info("Building file list..")
files = [
UriFile(file) for file in findFiles(self.cacheDir(), '.*txt',
self._dbinvent.lastupdate)
]
if len(files) == 0:
slurplogger().info(
"Orsifronts: No new files found since last update")
return
#possibly empty table
self.truncateTable()
#loop over files
for uri in files:
slurplogger().info("adding %s" % (uri.url))
self.addEntry(orsiMetaExtractor(uri))
self.updateInvent()
