nmdc-runtime 2.10.0__py3-none-any.whl → 2.11.0__py3-none-any.whl

nmdc_runtime/core/exceptions/base.py

@@ -1,47 +0,0 @@
-from http import HTTPStatus
-
-
-class CustomException(Exception):
-    code = HTTPStatus.BAD_GATEWAY
-    error_code = HTTPStatus.BAD_GATEWAY
-    message = HTTPStatus.BAD_GATEWAY.description
-
-    def __init__(self, message=None):
-        if message:
-            self.message = message
-
-
-class BadRequestException(CustomException):
-    code = HTTPStatus.BAD_REQUEST
-    error_code = HTTPStatus.BAD_REQUEST
-    message = HTTPStatus.BAD_REQUEST.description
-
-
-class NotFoundException(CustomException):
-    code = HTTPStatus.NOT_FOUND
-    error_code = HTTPStatus.NOT_FOUND
-    message = HTTPStatus.NOT_FOUND.description
-
-
-class ForbiddenException(CustomException):
-    code = HTTPStatus.FORBIDDEN
-    error_code = HTTPStatus.FORBIDDEN
-    message = HTTPStatus.FORBIDDEN.description
-
-
-class UnauthorizedException(CustomException):
-    code = HTTPStatus.UNAUTHORIZED
-    error_code = HTTPStatus.UNAUTHORIZED
-    message = HTTPStatus.UNAUTHORIZED.description
-
-
-class UnprocessableEntity(CustomException):
-    code = HTTPStatus.UNPROCESSABLE_ENTITY
-    error_code = HTTPStatus.UNPROCESSABLE_ENTITY
-    message = HTTPStatus.UNPROCESSABLE_ENTITY.description
-
-
-class DuplicateValueException(CustomException):
-    code = HTTPStatus.UNPROCESSABLE_ENTITY
-    error_code = HTTPStatus.UNPROCESSABLE_ENTITY
-    message = HTTPStatus.UNPROCESSABLE_ENTITY.description

nmdc_runtime/core/exceptions/token.py

@@ -1,13 +0,0 @@
-from nmdc_runtime.core.exceptions import CustomException
-
-
-class DecodeTokenException(CustomException):
-    code = 400
-    error_code = 10000
-    message = "token decode error"
-
-
-class ExpiredTokenException(CustomException):
-    code = 400
-    error_code = 10001
-    message = "expired token"

nmdc_runtime/domain/users/queriesInterface.py

@@ -1,18 +0,0 @@
-from __future__ import annotations
-from abc import ABC
-
-from abc import abstractmethod
-
-from nmdc_runtime.domain.users.userSchema import UserAuth, UserUpdate, UserOut
-
-
-class IUserQueries(ABC):
-    @abstractmethod
-    async def create(self, user: UserAuth) -> UserOut:
-        """Create new user"""
-        raise NotImplementedError
-
-    @abstractmethod
-    async def update(self, user: UserUpdate) -> UserOut:
-        """Update user data"""
-        raise NotImplementedError

nmdc_runtime/domain/users/userSchema.py

@@ -1,37 +0,0 @@
-from typing import Optional, List
-
-
-from pydantic import BaseModel, EmailStr
-
-
-class UserBase(BaseModel):
-    username: Optional[str] = None
-    email: Optional[str] = None
-    full_name: Optional[str] = None
-    site_admin: Optional[List[str]] = []
-    disabled: Optional[bool] = False
-
-
-class UserAuth(UserBase):
-    """User register and login auth"""
-
-    username: str
-    password: str
-
-
-# Properties to receive via API on update
-class UserUpdate(UserBase):
-    """Updatable user fields"""
-
-    email: Optional[EmailStr] = None
-
-    # User information
-    full_name: Optional[str] = None
-    password: Optional[str] = None
-
-
-class UserOut(UserUpdate):
-    """User fields pushed to the client"""
-
-    email: EmailStr
-    disabled: Optional[bool] = False

nmdc_runtime/domain/users/userService.py

@@ -1,14 +0,0 @@
-from typing import Any
-
-from nmdc_runtime.domain.users.userSchema import UserAuth, UserUpdate, UserOut
-
-
-class UserService:
-    def __init__(self, user_queries: Any) -> None:
-        self.__user_queries = user_queries
-
-    async def create_user(self, user: UserAuth) -> UserOut:
-        return await self.__user_queries.create(user)
-
-    async def update_user(self, username: str, new_user: UserUpdate) -> UserOut:
-        pass

nmdc_runtime/infrastructure/database/db.py

@@ -1,3 +0,0 @@
-"""
-Database initialization
-"""

nmdc_runtime/infrastructure/database/models/user.py

@@ -1 +0,0 @@
-from __future__ import annotations

nmdc_runtime/lib/__init__.py

@@ -1 +0,0 @@
-

nmdc_runtime/lib/extract_nmdc_data.py

@@ -1,33 +0,0 @@
-## author: Bill Duncan
-## summary: Contains methods for extracting data for the NMDC ETL pipeline.
-
-## system level modules
-import pandas as pds
-
-
-def extract_table(merged_df, table_name):
-    df = unpivot_dataframe(merged_df[merged_df.nmdc_data_source == table_name])
-    return df
-
-
-def unpivot_dataframe(
-    df,
-    index="nmdc_record_id",
-    columns="attribute",
-    value="value",
-    splice=["nmdc_record_id", "attribute", "value"],
-):
-    ## reshape eav structure to row-column structure
-    ## see: https://www.journaldev.com/33398/pandas-melt-unmelt-pivot-function
-    if len(splice) > 0:
-        df = df[splice].pivot(index=index, columns=columns)
-    else:
-        df = df.pivot(index=index, columns=columns)
-
-    if len(df) > 0:
-        df = df[value].reset_index()  # drop value hierarchical index
-    if len(df) > 0:
-        df = df.where(pds.notnull(df), None)  # replace an NaN values with None
-    df.columns.name = None  # remove column name attribute
-
-    return df

nmdc_runtime/lib/load_nmdc_data.py

@@ -1,121 +0,0 @@
-## author: Bill Duncan
-## summary: Contains methods for saving or loading NMDC data into a resource.
-
-import json
-import jq
-
-
-def save_json(json_data, file_path: str):
-    ## save json with changed data types
-    with open(file_path, "w") as out_file:
-        json.dump(json_data, out_file, indent=2)
-    return json_data
-
-
-def get_json_from_file(file_path: str, replace_single_quote=False):
-    ## load json
-    with open(file_path, "r") as in_file:
-        if replace_single_quote:  # json
-            text = in_file.read()
-            json_data = json.loads(text.replace("'", '"'))
-        else:
-            json_data = json.load(in_file)
-    return json_data
-
-
-def get_json(file_path="", replace_single_quote=False):
-    if len(file_path) > 0:
-        return get_json_from_file(file_path, replace_single_quote)
-
-
-def save_nmdc_dict_as_json_to_file(nmdc_dict: dict, file_path: str):
-    with open(file_path, "w") as f:
-        json.dump(nmdc_dict, f, indent=2)
-    return json.dumps(nmdc_dict, indent=2)
-
-
-def save_nmdc_dict(nmdc_dict: dict, file_path="", data_format="json"):
-    if len(file_path) > 0:
-        if "json" == data_format:
-            return save_nmdc_dict_as_json_to_file(nmdc_dict, file_path)
-
-
-def make_nmdc_example_database(
-    gold_study_file="output/nmdc_etl/gold_study.json",
-    gold_omics_processing_file="output/nmdc_etl/gold_omics_processing.json",
-    gold_biosample_file="output/nmdc_etl/gold_biosample.json",
-    jgi_fastq_data_object_file="output/nmdc_etl/jgi_fastq_data_objects.json",
-    output_file="output/nmdc_example-database.json",
-):
-    ## load json files
-    biosample_json = get_json(gold_biosample_file)
-    projects_json = get_json(gold_omics_processing_file)
-    study_json = get_json(gold_study_file)
-    data_objects_json = get_json(jgi_fastq_data_object_file)
-
-    ## get a list of distinct omics processing study ids, and choose the first 3 studies
-    study_ids = set(
-        jq.compile(".[] | .part_of[]").input(projects_json).all()
-    )  # all returns a list
-    study_ids = list(study_ids)[0:3]
-    # study_ids =
-
-    ## build a test set of studies from the study ids
-    study_test = (
-        jq.compile(
-            ".[] | select( .id == ("
-            + ", ".join('"{0}"'.format(id) for id in study_ids)
-            + "))"
-        )
-        .input(study_json)
-        .all()
-    )  # all() returns a list
-
-    ## build a test set of projects from the study ids
-    ## note: the jq query only selects first omics found for a given study id
-    projects_test = []
-    for id in study_ids:
-        j = (
-            jq.compile(f'[.[] | select( .part_of[]? |  . == "{id}")][0]')
-            .input(projects_json)
-            .all()
-        )
-        projects_test.append(*j)
-
-    ## get list of unique biossample ids from omics processing and build biosample test set
-    biosample_ids = (
-        jq.compile(".[] | .has_input[]?").input(projects_test).all()
-    )  # all() returns a list
-    biosample_test = (
-        jq.compile(
-            ".[] | select( .id == ("
-            + ", ".join('"{0}"'.format(id) for id in biosample_ids)
-            + "))"
-        )
-        .input(biosample_json)
-        .all()
-    )  # all() returns a list
-
-    ## get a list of data object ids and build data objects test set
-    data_objects_ids = (
-        jq.compile(".[] | .has_output[]?").input(projects_test).all()
-    )  # all() returns a list
-    data_objects_test = (
-        jq.compile(
-            ".[] | select( .id == ("
-            + ", ".join('"{0}"'.format(id) for id in data_objects_ids)
-            + "))"
-        )
-        .input(data_objects_json)
-        .all()
-    )  # all() returns a list
-
-    ## compile into database object
-    database = {
-        "study_set": [*study_test],
-        "omics_processing_set": [*projects_test],
-        "biosample_set": [*biosample_test],
-        "data_object_set": [*data_objects_test],
-    }
-
-    save_json(database, output_file)