Merge pull request #389 from euroargodev/other-major-breaking-refacto…

…ring

Implement other than bgc-2024 branch major breaking refactoring for major release v1.0.0

argopy/data_fetchers/__init__.py

@@ -6,14 +6,14 @@
 from . import erddap_data
 from . import erddap_index
 from . import argovis_data
-from . import gdacftp_data
-from . import gdacftp_index
+from . import gdac_data
+from . import gdac_index
 
 __all__ = (
     "erddap_data",
     "erddap_index",
     "argovis_data",
-    "gdacftp_data",
-    "gdacftp_index",
+    "gdac_data.py",
+    "gdac_index.py",
     "CTDRefDataFetcher",
 )

argopy/data_fetchers/argovis_data.py

@@ -81,8 +81,8 @@ def __init__(
             Argovis API request time out in seconds. Set to OPTIONS['api_timeout'] by default.
         """
         self.definition = "Argovis Argo data fetcher"
-        self.dataset_id = OPTIONS["dataset"] if ds == "" else ds
-        self.user_mode = kwargs["mode"] if "mode" in kwargs else OPTIONS["mode"]
+        self.dataset_id = OPTIONS["ds"] if ds == "" else ds
+        self.user_mode =  kwargs["mode"] if "mode" in kwargs else OPTIONS["mode"]
         self.server = kwargs["server"] if "server" in kwargs else api_server
         timeout = OPTIONS["api_timeout"] if api_timeout == 0 else api_timeout
         self.store_opts = {
@@ -360,7 +360,7 @@ def to_xarray(self, errors: str = "ignore"):
         ds = ds.set_coords(coords)
 
         # Cast data types and add variable attributes (not available in the csv download):
-        ds["TIME"] = ds["TIME"].astype("datetime64[ns]")
+        ds["TIME"] = pd.to_datetime(ds["TIME"], utc=True)
         ds = self._add_attributes(ds)
         ds = ds.argo.cast_types()
 

argopy/data_fetchers/erddap_data.py

@@ -130,7 +130,7 @@ def __init__(  # noqa: C901
         """
         timeout = OPTIONS["api_timeout"] if api_timeout == 0 else api_timeout
         self.definition = "Ifremer erddap Argo data fetcher"
-        self.dataset_id = OPTIONS["dataset"] if ds == "" else ds
+        self.dataset_id = OPTIONS["ds"] if ds == "" else ds
         self.user_mode =  kwargs["mode"] if "mode" in kwargs else OPTIONS["mode"]
         self.server = kwargs["server"] if "server" in kwargs else OPTIONS["erddap"]
         self.store_opts = {

argopy/data_fetchers/gdacftp_data.py → argopy/data_fetchers/gdac_data.py

@@ -1,5 +1,5 @@
 """
-Argo data fetcher for remote GDAC FTP
+Argo data fetcher for remote GDAC servers
 
 This is not intended to be used directly, only by the facade at fetchers.py
 
@@ -18,18 +18,18 @@
 from ..stores import ArgoIndex
 from .proto import ArgoDataFetcherProto
 
-log = logging.getLogger("argopy.gdacftp.data")
+log = logging.getLogger("argopy.gdac.data")
 access_points = ["wmo", "box"]
 exit_formats = ["xarray"]
 dataset_ids = ["phy", "bgc", "bgc-s", "bgc-b"]  # First is default
-api_server = OPTIONS["ftp"]  # API root url
+api_server = OPTIONS["gdac"]  # API root url
 api_server_check = (
     api_server  # URL to check if the API is alive, used by isAPIconnected
 )
 
 
-class FTPArgoDataFetcher(ArgoDataFetcherProto):
-    """Manage access to Argo data from a remote GDAC FTP.
+class GDACArgoDataFetcher(ArgoDataFetcherProto):
+    """Manage access to Argo data from a GDAC server
 
     Warnings
     --------
@@ -50,7 +50,7 @@ def init(self, *args, **kwargs):
     ###
     def __init__(
             self,
-            ftp: str = "",
+            gdac: str = "",
             ds: str = "",
             cache: bool = False,
             cachedir: str = "",
@@ -66,8 +66,8 @@ def __init__(
 
         Parameters
         ----------
-        ftp: str (optional)
-            Path to the remote FTP directory where the 'dac' folder is located.
+        gdac: str (optional)
+            Path to the local or remote directory where the 'dac' folder is located
         ds: str (optional)
             Dataset to load: 'phy' or 'bgc'
         cache: bool (optional)
@@ -88,15 +88,15 @@ def __init__(
         progress: bool (optional)
             Show a progress bar or not when fetching data.
         api_timeout: int (optional)
-            FTP request time out in seconds. Set to OPTIONS['api_timeout'] by default.
+            Server request time out in seconds. Set to OPTIONS['api_timeout'] by default.
         """
         self.timeout = OPTIONS["api_timeout"] if api_timeout == 0 else api_timeout
-        self.dataset_id = OPTIONS["dataset"] if ds == "" else ds
+        self.dataset_id = OPTIONS["ds"] if ds == "" else ds
         self.user_mode = kwargs["mode"] if "mode" in kwargs else OPTIONS["mode"]
-        self.server = OPTIONS["ftp"] if ftp == "" else ftp
+        self.server = OPTIONS["gdac"] if gdac == "" else gdac
         self.errors = errors
 
-        # Validate server, raise FtpPathError if not valid.
+        # Validate server, raise GdacPathError if not valid.
         check_gdac_path(self.server, errors="raise")
 
         index_file = "core"
@@ -137,10 +137,10 @@ def __init__(
         self.init(**kwargs)
 
     def __repr__(self):
-        summary = ["<datafetcher.ftp>"]
+        summary = ["<datafetcher.gdac>"]
         summary.append("Name: %s" % self.definition)
         summary.append("Index: %s" % self.indexfs.index_file)
-        summary.append("Host: %s" % self.server)
+        summary.append("Server: %s" % self.server)
         if hasattr(self, "BOX"):
             summary.append("Domain: %s" % self.cname())
         else:
@@ -446,8 +446,8 @@ def filter_researchmode(self, ds: xr.Dataset, *args, **kwargs) -> xr.Dataset:
         return ds
 
 
-class Fetch_wmo(FTPArgoDataFetcher):
-    """Manage access to GDAC ftp Argo data for: a list of WMOs.
+class Fetch_wmo(GDACArgoDataFetcher):
+    """Manage access to GDAC Argo data for: a list of WMOs.
 
     This class is instantiated when a call is made to these facade access points:
 
@@ -474,7 +474,7 @@ def init(self, WMO: list = [], CYC=None, **kwargs):
         if "MAX_FILES" in kwargs:
             self._nrows = kwargs["MAX_FILES"]
 
-        self.definition = "Ifremer GDAC ftp Argo data fetcher"
+        self.definition = "Ifremer GDAC Argo data fetcher"
         if self.CYC is not None:
             self.definition = "%s for profiles" % self.definition
         else:
@@ -503,8 +503,8 @@ def uri(self):
         return self._list_of_argo_files
 
 
-class Fetch_box(FTPArgoDataFetcher):
-    """Manage access to GDAC ftp Argo data for: a rectangular space/time domain.
+class Fetch_box(GDACArgoDataFetcher):
+    """Manage access to GDAC Argo data for: a rectangular space/time domain.
 
     This class is instantiated when a call is made to these facade access points:
 
@@ -535,7 +535,7 @@ def init(self, box: list, nrows=None, **kwargs):
         if "MAX_FILES" in kwargs:
             self._nrows = kwargs["MAX_FILES"]
 
-        self.definition = "Ifremer GDAC ftp Argo data fetcher for a space/time region"
+        self.definition = "Ifremer GDAC Argo data fetcher for a space/time region"
         return self
 
     @property

argopy/data_fetchers/gdacftp_index.py → argopy/data_fetchers/gdac_index.py

@@ -1,5 +1,5 @@
 """
-Argo index fetcher for remote GDAC FTP
+Argo index fetcher for remote GDAC server
 
 This is not intended to be used directly, only by the facade at fetchers.py
 
@@ -16,7 +16,7 @@
 from ..plot import dashboard
 
 
-log = logging.getLogger("argopy.gdacftp.index")
+log = logging.getLogger("argopy.gdac.index")
 
 has_pyarrow = importlib.util.find_spec('pyarrow') is not None
 if has_pyarrow:
@@ -30,12 +30,12 @@
 access_points = ["wmo", "box"]
 exit_formats = ["xarray"]
 dataset_ids = ["phy", "bgc"]  # First is default
-api_server = OPTIONS['ftp']  # API root url
+api_server = OPTIONS['gdac']  # API root url
 api_server_check = api_server  # URL to check if the API is alive, used by isAPIconnected
 
 
-class FTPArgoIndexFetcher(ABC):
-    """ Manage access to Argo index from a remote GDAC FTP """
+class GDACArgoIndexFetcher(ABC):
+    """Manage access to Argo index from a GDAC server"""
     # N_FILES = None
 
     ###
@@ -51,7 +51,7 @@ def init(self, *args, **kwargs):
     ###
     def __init__(
         self,
-        ftp: str = "",
+        gdac: str = "",
         ds: str = "",
         cache: bool = False,
         cachedir: str = "",
@@ -63,8 +63,8 @@ def __init__(
 
         Parameters
         ----------
-        ftp: str (optional)
-            Path to the remote FTP directory where the 'dac' folder is located.
+        gdac: str (optional)
+            Path to the local or remote directory where the 'dac' folder is located
         ds: str (optional)
             Dataset to load: 'phy' or 'ref' or 'bgc'
         errors: str (optional)
@@ -75,15 +75,15 @@ def __init__(
         cachedir: str (optional)
             Path to cache folder
         api_timeout: int (optional)
-            FTP request time out in seconds. Set to OPTIONS['api_timeout'] by default.
+            Server request time out in seconds. Set to OPTIONS['api_timeout'] by default.
         """
         self.timeout = OPTIONS["api_timeout"] if api_timeout == 0 else api_timeout
-        self.definition = "Ifremer GDAC ftp Argo index fetcher"
-        self.dataset_id = OPTIONS["dataset"] if ds == "" else ds
-        self.server = OPTIONS['ftp'] if ftp == "" else ftp
+        self.definition = "Ifremer GDAC Argo index fetcher"
+        self.dataset_id = OPTIONS["ds"] if ds == "" else ds
+        self.server = OPTIONS['gdac'] if gdac == "" else gdac
         self.errors = errors
 
-        # Validate server, raise FtpPathError if not valid.
+        # Validate server, raise GdacPathError if not valid.
         check_gdac_path(self.server, errors='raise')
 
         if self.dataset_id == 'phy':
@@ -107,10 +107,10 @@ def __init__(
         self.init(**kwargs)
 
     def __repr__(self):
-        summary = ["<indexfetcher.ftp>"]
+        summary = ["<indexfetcher.gdac>"]
         summary.append("Name: %s" % self.definition)
         summary.append("Index: %s" % self.indexfs.index_file)
-        summary.append("FTP: %s" % self.server)
+        summary.append("Server: %s" % self.server)
         summary.append("Domain: %s" % format_oneline(self.cname()))
         if hasattr(self.indexfs, 'index'):
             summary.append("Index loaded: True (%i records)" % self.N_RECORDS)
@@ -177,8 +177,8 @@ def dashboard(self, **kw):
                 warnings.warn("Dashboard only available for a single float or profile request")
 
 
-class Fetch_wmo(FTPArgoIndexFetcher):
-    """ Manage access to GDAC ftp Argo index for: a list of WMOs, CYCs  """
+class Fetch_wmo(GDACArgoIndexFetcher):
+    """ Manage access to GDAC Argo index for: a list of WMOs, CYCs  """
 
     def init(self, WMO: list = [], CYC=None, **kwargs):
         """ Create Argo index fetcher for WMOs
@@ -217,8 +217,8 @@ def uri(self):
         return self._list_of_argo_files
 
 
-class Fetch_box(FTPArgoIndexFetcher):
-    """ Manage access to GDAC ftp Argo index for: a rectangular space/time domain  """
+class Fetch_box(GDACArgoIndexFetcher):
+    """ Manage access to GDAC Argo index for: a rectangular space/time domain  """
 
     def init(self, box: list, **kwargs):
         """ Create Argo index fetcher
@@ -238,7 +238,7 @@ def init(self, box: list, **kwargs):
         """
         # We use a full domain definition (x, y, z, t) as argument for compatibility with the other fetchers
         # but at this point, we internally work only with x, y and t.
-        # log.debug("Create FTPArgoIndexFetcher.Fetch_box instance with index BOX: %s" % box)
+        # log.debug("Create GDACArgoIndexFetcher.Fetch_box instance with index BOX: %s" % box)
         self.indexBOX = box.copy()
 
         self._nrows = None

argopy/errors.py

@@ -26,20 +26,20 @@ class NoDataLeft(NoData):
     pass
 
 
-class FtpPathError(ValueError):
-    """Raise when a ftp path is not appropriate."""
+class GdacPathError(ValueError):
+    """Raise when a GDAC compliant path is not appropriate"""
 
     pass
 
 
 class ErddapPathError(ValueError):
-    """Raise when a erddap path is not appropriate."""
+    """Raise when an erddap path is not appropriate"""
 
     pass
 
 
 class S3PathError(ValueError):
-    """Raise when a S3 path is not appropriate."""
+    """Raise when a S3 path is not appropriate"""
 
     pass
 

argopy/fetchers.py

@@ -78,7 +78,7 @@ class ArgoDataFetcher:
     src: str, optional
          Source of the data to use. Eg: ``erddap``. Set to OPTIONS['src'] by default if empty.
     ds: str, optional
-        Name of the dataset to load. Eg: ``phy``. Set to OPTIONS['dataset'] by default if empty.
+        Name of the dataset to load. Eg: ``phy``. Set to OPTIONS['ds'] by default if empty.
     **fetcher_kwargs: optional
         Additional arguments passed on data source fetcher creation of each access points.
 
@@ -102,7 +102,7 @@ def __init__(self, mode: str = "", src: str = "", ds: str = "", **fetcher_kwargs
 
         # Facade options :
         self._mode = OPTIONS["mode"] if mode == "" else mode
-        self._dataset_id = OPTIONS["dataset"] if ds == "" else ds
+        self._dataset_id = OPTIONS["ds"] if ds == "" else ds
         self._src = OPTIONS["src"] if src == "" else src
 
         if self._dataset_id == "bgc":
@@ -112,9 +112,9 @@ def __init__(self, mode: str = "", src: str = "", ds: str = "", **fetcher_kwargs
             raise OptionValueError(
                 f"option 'mode' given an invalid value: {self._mode}"
             )
-        if not _VALIDATORS["dataset"](self._dataset_id):
+        if not _VALIDATORS["ds"](self._dataset_id):
             raise OptionValueError(
-                f"option 'dataset' given an invalid value: {self._dataset_id}"
+                f"option 'ds' given an invalid value: {self._dataset_id}"
             )
         if not _VALIDATORS["src"](self._src):
             raise OptionValueError(f"option 'src' given an invalid value: {self._src}")
@@ -817,7 +817,7 @@ def __init__(
         self,
         mode: str = OPTIONS["mode"],
         src: str = OPTIONS["src"],
-        ds: str = OPTIONS["dataset"],
+        ds: str = OPTIONS["ds"],
         **fetcher_kwargs,
     ):
         """Facade for Argo index fetchers