diff --git a/docs/toardb_fastapi.md b/docs/toardb_fastapi.md
index 3c391769d77e0ee22cd752cb2909f98b6976a927..1ba1b576a61d32db8cb50af6b9d143e2585cb146 100644
--- a/docs/toardb_fastapi.md
+++ b/docs/toardb_fastapi.md
@@ -52,6 +52,7 @@
| name | string | Name of person | Yes |
| email | string | Email address of person | Yes |
| phone | string | Phone number of person | Yes |
+| orcid | string | ORCID-iD of person | Yes |
| isprivate | boolean | Set this flag to true if the contact details shall not be exposed publicly | Yes |
#### Stationmeta
@@ -206,13 +207,13 @@
| access_rights | string | Access rights of timeseries data (see controlled vocabulary: Data Access Right) | Yes |
| sampling_frequency | string | Sampling frequency of data in this timeseries (see controlled vocabulary: Sampling Frequency) | Yes |
| aggregation | string | Aggregation type in this timeseries (see controlled vocabulary: Aggregation Type) | Yes |
-| source | string | source of data (see controlled vocabulary: Data Source) | Yes |
| data_start_date | dateTime | Start date of the variable data available for this station | Yes |
| data_end_date | dateTime | End date of the variable data available for this station | Yes |
-| measurement_method | string | instrument principle of measurement (see controlled vocabulary: Measurement Method) | Yes |
+| data_origin | string | origin of data (model name or instrument) (see controlled vocabulary: Data Origin) | Yes |
+| data_origin_type | string | type of data origin (see controlled vocabulary: Data Origin Type) | Yes |
+| version | string | provider data version | Yes |
+| data_license_accepted | dateTime | date when provider accepted the data license agreement | Yes |
| sampling_height | number | Height above the ground of the inlet/instrument/sampler (in m) | Yes |
-| date_added | dateTime | Date of timeseries metadata entry into TOAR database | Yes |
-| date_modified | dateTime | Date of last timeseries metadata modification | Yes |
| additional_metadata | string (json-string) | | No |
| station | [StationmetaCoreBase](#stationmetacorebase) | | Yes |
| variable | [Variable](#variable) | | Yes |
@@ -333,14 +334,15 @@
[4, 'MeanMonth', 'monthly mean'],
[5, 'None', 'none'],
[6, 'Unknown', 'unknown']]
-#### Data Source ####
- * Data Source: [
- [0, 'Model', 'model'],
- [1, 'Measurement', 'measurement']]
-#### Measurement Method ####
- * Measurement Method: [
- [0, 'UVAbsorption', 'UV absorption'],
- [1, 'UnknownInstrument', 'unknown instrument']]
+#### Data Origin Type ####
+ * Data Origin Type: [
+ [0, 'Measurement', 'measurement'],
+ [1, 'Model', 'model']]
+#### Data Origin ####
+ * Data Origin: [
+ [0, 'Instrument', 'instrument'],
+ [1, 'COSMOREA6', 'COSMO REA 6'],
+ [2, 'ERA5', 'ERA 5']]
#### Climatic Zone ####
* Climatic Zone: [
[-1, 'Undefined', 'undefined'],
diff --git a/toardb/contacts/models_person.py b/toardb/contacts/models_person.py
index d02a723593d344ab6ec955677c9b626c856a64bb..f2031867a53d7454b2567030deb45ad51a40d365 100644
--- a/toardb/contacts/models_person.py
+++ b/toardb/contacts/models_person.py
@@ -10,19 +10,21 @@ class Person(Base):
"""
Table "public.persons"
- +-----------+------------------------+-----------+----------+-------------------------------------+
- | Column | Type | Collation | Nullable | Default |
- +===========+========================+===========+==========+=====================================+
- | id | integer | | not null | nextval('persons_id_seq'::regclass) |
- +-----------+------------------------+-----------+----------+-------------------------------------+
- | name | character varying(64) | | not null | |
- +-----------+------------------------+-----------+----------+-------------------------------------+
- | email | character varying(128) | | not null | |
- +-----------+------------------------+-----------+----------+-------------------------------------+
- | phone | character varying(32) | | not null | ''::character varying |
- +-----------+------------------------+-----------+----------+-------------------------------------+
- | isprivate | boolean | | not null | true |
- +-----------+------------------------+-----------+----------+-------------------------------------+
+ +-----------+------------------------+-----------+----------+------------------------------------------+
+ | Column | Type | Collation | Nullable | Default |
+ +===========+========================+===========+==========+==========================================+
+ | id | integer | | not null | nextval('persons_id_seq'::regclass) |
+ +-----------+------------------------+-----------+----------+------------------------------------------+
+ | name | character varying(64) | | not null | |
+ +-----------+------------------------+-----------+----------+------------------------------------------+
+ | email | character varying(128) | | not null | |
+ +-----------+------------------------+-----------+----------+------------------------------------------+
+ | phone | character varying(32) | | not null | ''::character varying |
+ +-----------+------------------------+-----------+----------+------------------------------------------+
+ | orcid | character varying(19) | | not null | '0000-0002-0309-8010'::character varying |
+ +-----------+------------------------+-----------+----------+------------------------------------------+
+ | isprivate | boolean | | not null | true |
+ +-----------+------------------------+-----------+----------+------------------------------------------+
Indexes:
"persons_pkey" PRIMARY KEY, btree (id)
@@ -41,5 +43,6 @@ class Person(Base):
name = Column(String(64), nullable=False)
email = Column(String(128), nullable=False)
phone = Column(String(32), nullable=False, server_default=text("''::character varying"))
+ orcid = Column(String(19), nullable=False, server_default=text("'0000-0000-0000-0000'::character varying"))
isprivate = Column(Boolean, nullable=False, server_default=text("true"))
diff --git a/toardb/contacts/schemas.py b/toardb/contacts/schemas.py
index 6c52e68bea9c25632c0e44f6fb9a71c24af52b78..c735aa9896b510db55619dbb4faf500a1ed3073a 100644
--- a/toardb/contacts/schemas.py
+++ b/toardb/contacts/schemas.py
@@ -60,6 +60,7 @@ class PersonBase(BaseModel):
name: str = Field(..., description="Name of person")
email: str = Field(..., description="Email address of person")
phone: str = Field(..., description="Phone number of person")
+ orcid: str = Field(..., description="ORCID-iD of person")
isprivate: bool = Field(..., description="Set this flag to true if the contact details shall not be exposed publicly")
def __str__(self):
diff --git a/toardb/timeseries/crud.py b/toardb/timeseries/crud.py
index b289c618975de8f41e51811edb06d80eb2477e02..1c17c30540de75d59faa166be65da9410f242840 100644
--- a/toardb/timeseries/crud.py
+++ b/toardb/timeseries/crud.py
@@ -119,8 +119,8 @@ def create_timeseries(db: Session, timeseries: TimeseriesCreate):
db_timeseries.access_rights = get_value_from_str(toardb.toardb.DA_vocabulary,db_timeseries.access_rights)
db_timeseries.sampling_frequency = get_value_from_str(toardb.toardb.SF_vocabulary,db_timeseries.sampling_frequency)
db_timeseries.aggregation = get_value_from_str(toardb.toardb.AT_vocabulary,db_timeseries.aggregation)
- db_timeseries.source = get_value_from_str(toardb.toardb.DS_vocabulary,db_timeseries.source)
- db_timeseries.measurement_method= get_value_from_str(toardb.toardb.MM_vocabulary,db_timeseries.measurement_method)
+ db_timeseries.data_origin_type = get_value_from_str(toardb.toardb.OT_vocabulary,db_timeseries.data_origin_type)
+ db_timeseries.data_origin = get_value_from_str(toardb.toardb.DO_vocabulary,db_timeseries.data_origin)
db.add(db_timeseries)
result = db.commit()
db.refresh(db_timeseries)
diff --git a/toardb/timeseries/models.py b/toardb/timeseries/models.py
index 815a73d7e8101c245679ab7998e2ceef975e6827..80c28ca31522c75c842b47362c9acd338e3d6333 100644
--- a/toardb/timeseries/models.py
+++ b/toardb/timeseries/models.py
@@ -34,16 +34,16 @@ AT_enum_table = Table("at_vocabulary",
Column("enum_display_str", String)
)
-# Data Sources
-DS_enum_table = Table("ds_vocabulary",
+# Data Origin Types
+OT_enum_table = Table("ot_vocabulary",
Base.metadata,
Column("enum_val", Integer, primary_key=True),
Column("enum_str", String),
Column("enum_display_str", String)
)
-# Measurement Methods
-MM_enum_table = Table("mm_vocabulary",
+# Data Origins
+DO_enum_table = Table("do_vocabulary",
Base.metadata,
Column("enum_val", Integer, primary_key=True),
Column("enum_str", String),
diff --git a/toardb/timeseries/models_core.py b/toardb/timeseries/models_core.py
index 070d542ca4ac04929548e94067f57d23cc895a44..d4646e97937c97ecf254503127a3b1b2c35a7152 100644
--- a/toardb/timeseries/models_core.py
+++ b/toardb/timeseries/models_core.py
@@ -18,43 +18,43 @@ class Timeseries(Base):
"""
Table "public.timeseries"
- +---------------------+--------------------------+-----------+----------+----------------------------------------+
- | Column | Type | Collation | Nullable | Default |
+ +-----------------------+--------------------------+-----------+----------+----------------------------------------+
+ | Column | Type | Collation | Nullable | Default |
+=====================+==========================+===========+==========+========================================+
- | id | integer | | not null | nextval('timeseries_id_seq'::regclass) |
- +---------------------+--------------------------+-----------+----------+----------------------------------------+
- | label | character varying(128) | | not null | |
- +---------------------+--------------------------+-----------+----------+----------------------------------------+
- | order | integer | | not null | |
- +---------------------+--------------------------+-----------+----------+----------------------------------------+
- | access_rights | integer | | not null | |
- +---------------------+--------------------------+-----------+----------+----------------------------------------+
- | sampling_frequency | integer | | not null | |
- +---------------------+--------------------------+-----------+----------+----------------------------------------+
- | aggregation | integer | | not null | |
- +---------------------+--------------------------+-----------+----------+----------------------------------------+
- | source | integer | | not null | 1 |
- +---------------------+--------------------------+-----------+----------+----------------------------------------+
- | data_start_date | timestamp with time zone | | not null | |
- +---------------------+--------------------------+-----------+----------+----------------------------------------+
- | data_end_date | timestamp with time zone | | not null | |
- +---------------------+--------------------------+-----------+----------+----------------------------------------+
- | measurement_method | integer | | not null | 1 |
- +---------------------+--------------------------+-----------+----------+----------------------------------------+
- | sampling_height | double precision | | not null | |
- +---------------------+--------------------------+-----------+----------+----------------------------------------+
- | additional_metadata | jsonb | | not null | |
- +---------------------+--------------------------+-----------+----------+----------------------------------------+
- | date_added | timestamp with time zone | | not null | now() |
- +---------------------+--------------------------+-----------+----------+----------------------------------------+
- | date_modified | timestamp with time zone | | not null | now() |
- +---------------------+--------------------------+-----------+----------+----------------------------------------+
- | station_id | integer | | | |
- +---------------------+--------------------------+-----------+----------+----------------------------------------+
- | variable_id | integer | | | |
- +---------------------+--------------------------+-----------+----------+----------------------------------------+
- | programme_id | integer | | not null | 0 |
- +---------------------+--------------------------+-----------+----------+----------------------------------------+
+ | id | integer | | not null | nextval('timeseries_id_seq'::regclass) |
+ +-----------------------+--------------------------+-----------+----------+----------------------------------------+
+ | label | character varying(128) | | not null | |
+ +-----------------------+--------------------------+-----------+----------+----------------------------------------+
+ | order | integer | | not null | |
+ +-----------------------+--------------------------+-----------+----------+----------------------------------------+
+ | access_rights | integer | | not null | |
+ +-----------------------+--------------------------+-----------+----------+----------------------------------------+
+ | sampling_frequency | integer | | not null | |
+ +-----------------------+--------------------------+-----------+----------+----------------------------------------+
+ | aggregation | integer | | not null | |
+ +-----------------------+--------------------------+-----------+----------+----------------------------------------+
+ | data_start_date | timestamp with time zone | | not null | |
+ +-----------------------+--------------------------+-----------+----------+----------------------------------------+
+ | data_end_date | timestamp with time zone | | not null | |
+ +-----------------------+--------------------------+-----------+----------+----------------------------------------+
+ | data_origin_type | integer | | not null | 0 |
+ +-----------------------+--------------------------+-----------+----------+----------------------------------------+
+ | data_origin | integer | | not null | 0 |
+ +-----------------------+--------------------------+-----------+----------+----------------------------------------+
+ | sampling_height | double precision | | not null | |
+ +-----------------------+--------------------------+-----------+----------+----------------------------------------+
+ | additional_metadata | jsonb | | not null | |
+ +-----------------------+--------------------------+-----------+----------+----------------------------------------+
+ | version | character varying(28) | | not null | '' |
+ +-----------------------+--------------------------+-----------+----------+----------------------------------------+
+ | data_license_accepted | timestamp with time zone | | not null | '1900-01-01' |
+ +-----------------------+--------------------------+-----------+----------+----------------------------------------+
+ | station_id | integer | | | |
+ +-----------------------+--------------------------+-----------+----------+----------------------------------------+
+ | variable_id | integer | | | |
+ +-----------------------+--------------------------+-----------+----------+----------------------------------------+
+ | programme_id | integer | | not null | 0 |
+ +-----------------------+--------------------------+-----------+----------+----------------------------------------+
Indexes:
"timeseries_pkey" PRIMARY KEY, btree (id)
@@ -71,9 +71,9 @@ class Timeseries(Base):
"timeseries_variable_id_fk_variables_id" FOREIGN KEY (variable_id) REFERENCES variables(id) DEFERRABLE INITIALLY DEFERREDForeign-key constraints:
"timeseries_access_rights_fk_da_vocabulary_enum_val" FOREIGN KEY (access_rights) REFERENCES da_vocabulary(enum_val)
"timeseries_aggregation_fk_at_vocabulary_enum_val" FOREIGN KEY (aggregation) REFERENCES at_vocabulary(enum_val)
- "timeseries_measurement_method_fk_mm_vocabulary_enum_val" FOREIGN KEY (measurement_method) REFERENCES mm_vocabulary(enum_val)
"timeseries_sampling_frequency_fk_sf_vocabulary_enum_val" FOREIGN KEY (sampling_frequency) REFERENCES sf_vocabulary(enum_val)
- "timeseries_source_fk_ds_vocabulary_enum_val" FOREIGN KEY (source) REFERENCES ds_vocabulary(enum_val)
+ "timeseries_data_origin_fk_do_vocabulary_enum_val" FOREIGN KEY (data_origin) REFERENCES do_vocabulary(enum_val)
+ "timeseries_data_origin_type_fk_ot_vocabulary_enum_val" FOREIGN KEY (data_origin_type) REFERENCES ot_vocabulary(enum_val)
"timeseries_programme_id_fk_timeseries_programmes_id" FOREIGN KEY (programme_id) REFERENCES timeseries_programmes(id)
Referenced by:
TABLE "data" CONSTRAINT "data_timeseries_id_fk_timeseries_id" FOREIGN KEY (timeseries_id) REFERENCES timeseries(id) DEFERRABLE INITIALLY DEFERRED
@@ -97,13 +97,13 @@ class Timeseries(Base):
access_rights = Column(ForeignKey('da_vocabulary.enum_val'), nullable=False)
sampling_frequency = Column(ForeignKey('sf_vocabulary.enum_val'), nullable=False)
aggregation = Column(ForeignKey('at_vocabulary.enum_val'), nullable=False)
- source = Column(ForeignKey('ds_vocabulary.enum_val'), nullable=False, server_default=text("1"))
data_start_date = Column(DateTime(True), nullable=False)
data_end_date = Column(DateTime(True), nullable=False)
- measurement_method = Column(ForeignKey('mm_vocabulary.enum_val'), nullable=False, server_default=text("1"))
+ data_origin_type = Column(ForeignKey('ot_vocabulary.enum_val'), nullable=False, server_default=text("0"))
+ data_origin = Column(ForeignKey('do_vocabulary.enum_val'), nullable=False, server_default=text("0"))
sampling_height = Column(Float(53), nullable=False)
- date_added = Column(DateTime(True), nullable=False, server_default=text("now()"))
- date_modified = Column(DateTime(True), nullable=False, server_default=text("now()"))
+ version = Column(String(128), nullable=False, server_default=text("''"))
+ data_license_accepted = Column(DateTime(True), nullable=False, server_default=text("'1900-01-01 00:00:00+00'::timestamp with time zone"))
# do not use string declaration here (not working for pytest)
# use the explicit class name here,
# see: https://groups.google.com/forum/#!topic/sqlalchemy/YjGhE4d6K4U
@@ -120,9 +120,3 @@ class Timeseries(Base):
additional_metadata = Column(JSONB(astext_type=Text()), nullable=True)
-# da_vocabulary = relationship('DaVocabulary')
-# at_vocabulary = relationship('AtVocabulary')
-# mm_vocabulary = relationship('MmVocabulary')
-# sf_vocabulary = relationship('SfVocabulary')
-# ds_vocabulary = relationship('DsVocabulary')
-
diff --git a/toardb/timeseries/schemas.py b/toardb/timeseries/schemas.py
index f6a67f540ebde60b09a9b88a8801f9a2b0235e24..fc5fa0accb38d3e05ad4dc5f6960edbad5c16240 100644
--- a/toardb/timeseries/schemas.py
+++ b/toardb/timeseries/schemas.py
@@ -26,13 +26,13 @@ class TimeseriesCoreBase(BaseModel):
access_rights: str = Field(..., description="Access rights of timeseries data (see controlled vocabulary: Data Access Right)")
sampling_frequency: str = Field(..., description="Sampling frequency of data in this timeseries (see controlled vocabulary: Sampling Frequency)")
aggregation: str = Field(..., description="Aggregation type in this timeseries (see controlled vocabulary: Aggregation Type)")
- source: str = Field(..., description="source of data (see controlled vocabulary: Data Source)")
data_start_date: dt.datetime = Field(..., description="Start date of the variable data available for this station")
data_end_date: dt.datetime = Field(..., description="End date of the variable data available for this station")
- measurement_method: str = Field(..., description="instrument principle of measurement (see controlled vocabulary: Measurement Method)")
+ data_origin: str = Field(..., description="origin of data (model name or instrument) (see controlled vocabulary: Data Origin)")
+ data_origin_type: str = Field(..., description="type of data origin (see controlled vocabulary: Data Origin Type)")
+ version: str = Field(..., description="provider data version")
+ data_license_accepted: dt.datetime = Field(..., description="date when provider accepted the data license agreement")
sampling_height: float = Field(..., description="Height above the ground of the inlet/instrument/sampler (in m)")
- date_added: dt.datetime = Field(..., description="Date of timeseries metadata entry into TOAR database")
- date_modified: dt.datetime = Field(..., description="Date of last timeseries metadata modification")
additional_metadata: Json = Field(..., description="Additional information about the timeseries as JSON structure.")
# still missing: "Score values from automated data QA (5-star evaluation)"
@@ -51,13 +51,13 @@ class TimeseriesCoreBase(BaseModel):
def check_aggregation(cls, v):
return tuple(filter(lambda x: x.value == int(v), toardb.toardb.AT_vocabulary))[0].display_str
- @validator('source')
+ @validator('data_origin_type')
def check_source(cls, v):
- return tuple(filter(lambda x: x.value == int(v), toardb.toardb.DS_vocabulary))[0].display_str
+ return tuple(filter(lambda x: x.value == int(v), toardb.toardb.OT_vocabulary))[0].display_str
- @validator('measurement_method')
+ @validator('data_origin')
def check_measurement_method(cls, v):
- return tuple(filter(lambda x: x.value == int(v), toardb.toardb.MM_vocabulary))[0].display_str
+ return tuple(filter(lambda x: x.value == int(v), toardb.toardb.DO_vocabulary))[0].display_str
class TimeseriesCoreCreate(TimeseriesCoreBase):
@@ -86,16 +86,16 @@ class TimeseriesCoreCreate(TimeseriesCoreBase):
else:
raise ValueError(f"aggregation type not known: {v}")
- @validator('source')
+ @validator('data_origin_type')
def check_source(cls, v):
- if tuple(filter(lambda x: x.string == v, toardb.toardb.DS_vocabulary)):
+ if tuple(filter(lambda x: x.string == v, toardb.toardb.OT_vocabulary)):
return v
else:
raise ValueError(f"data source not known: {v}")
- @validator('measurement_method')
+ @validator('data_origin')
def check_measurement_method(cls, v):
- if tuple(filter(lambda x: x.string == v, toardb.toardb.MM_vocabulary)):
+ if tuple(filter(lambda x: x.string == v, toardb.toardb.DO_vocabulary)):
return v
else:
raise ValueError(f"measurement method not known: {v}")
@@ -264,8 +264,6 @@ class TimeseriesPatch(BaseModel):
data_end_date: dt.datetime = None
measurement_method: str = None
sampling_height: float = None
- date_added: dt.datetime = None
- date_modified: dt.datetime = None
# roles: List[TimeseriesRole] = None
# annotations: List[TimeseriesAnnotation] = None
# variable: Variable = None
diff --git a/toardb/toardb.py b/toardb/toardb.py
index 706fa6afbe157584e80dad9c7ff160bb74a4ae48..6558508f6129a7bb5b9461bf2babd6cd4928b9fc 100644
--- a/toardb/toardb.py
+++ b/toardb/toardb.py
@@ -27,8 +27,8 @@ OK_vocabulary = 0
DA_vocabulary = 0
SF_vocabulary = 0
AT_vocabulary = 0
-DS_vocabulary = 0
-MM_vocabulary = 0
+OT_vocabulary = 0
+DO_vocabulary = 0
CZ_vocabulary = 0
CV_vocabulary = 0
CN_vocabulary = 0
@@ -61,8 +61,8 @@ async def info():
"Data Access Right": DA_vocabulary,
"Sampling Frequency": SF_vocabulary,
"Aggregation Type": AT_vocabulary,
- "Data Source": DS_vocabulary,
- "Measurement Method": MM_vocabulary,
+ "Data Origin Type": OT_vocabulary,
+ "Data Origin": DO_vocabulary,
"Climatic Zone": CZ_vocabulary,
"Country Code": CN_vocabulary,
"Timezone": TZ_vocabulary,
@@ -88,8 +88,8 @@ async def info(name: str):
"data access right": DA_vocabulary,
"sampling frequency": SF_vocabulary,
"aggregation type": AT_vocabulary,
- "data source": DS_vocabulary,
- "measurement method": MM_vocabulary,
+ "data origin": DO_vocabulary,
+ "data origin type": OT_vocabulary,
"climatic zone": CZ_vocabulary,
"coordinate validity": CV_vocabulary,
"country code": CN_vocabulary,
@@ -161,8 +161,8 @@ async def startup_event():
global DA_vocabulary
global SF_vocabulary
global AT_vocabulary
- global DS_vocabulary
- global MM_vocabulary
+ global OT_vocabulary
+ global DO_vocabulary
global CZ_vocabulary
global CV_vocabulary
global CN_vocabulary
@@ -185,8 +185,8 @@ async def startup_event():
DA_vocabulary = __get_enum_dict(fake_cur, "da_vocabulary")
SF_vocabulary = __get_enum_dict(fake_cur, "sf_vocabulary")
AT_vocabulary = __get_enum_dict(fake_cur, "at_vocabulary")
- DS_vocabulary = __get_enum_dict(fake_cur, "ds_vocabulary")
- MM_vocabulary = __get_enum_dict(fake_cur, "mm_vocabulary")
+ OT_vocabulary = __get_enum_dict(fake_cur, "ot_vocabulary")
+ DO_vocabulary = __get_enum_dict(fake_cur, "do_vocabulary")
CZ_vocabulary = __get_enum_dict(fake_cur, "cz_vocabulary")
CV_vocabulary = __get_enum_dict(fake_cur, "cv_vocabulary")
CN_vocabulary = __get_enum_dict(fake_cur, "cn_vocabulary")