mpcontribs-client 5.10.4__py3-none-any.whl → 5.10.5rc1__py3-none-any.whl

mpcontribs/client/__init__.py

@@ -1,65 +1,68 @@
-# -*- coding: utf-8 -*-
+import functools
+import gzip
+import importlib.metadata
 import io
-import sys
+import itertools
+import logging
 import os
-import ujson
+import sys
 import time
-import gzip
 import warnings
-import pandas as pd
-import numpy as np
-import plotly.io as pio
-import itertools
-import functools
-import requests
-import logging
-import datetime
-
+from base64 import b64decode, b64encode, urlsafe_b64encode
+from collections import defaultdict
+from concurrent.futures import as_completed
+from copy import deepcopy
+from hashlib import md5
 from inspect import getfullargspec
 from math import isclose
-from semantic_version import Version
-from requests.exceptions import RequestException
-from bson.objectid import ObjectId
-from typing import Union, Type, Optional
-from tqdm.auto import tqdm
-from hashlib import md5
 from pathlib import Path
-from copy import deepcopy
-from filetype import guess
-from flatten_dict import flatten, unflatten
-from base64 import b64encode, b64decode, urlsafe_b64encode
+from tempfile import gettempdir
+from typing import Type
 from urllib.parse import urlparse
-from pyisemail import is_email
-from collections import defaultdict
-from pyisemail.diagnosis import BaseDiagnosis
-from swagger_spec_validator.common import SwaggerValidationError
-from jsonschema.exceptions import ValidationError
-from bravado_core.formatter import SwaggerFormat
+
+import numpy as np
+import pandas as pd
+import plotly.io as pio
+import requests
+import ujson
+from boltons.iterutils import remap
 from bravado.client import SwaggerClient
+from bravado.config import bravado_config_from_config_dict
+from bravado.exception import HTTPNotFound
 from bravado.requests_client import RequestsClient
 from bravado.swagger_model import Loader
-from bravado.config import bravado_config_from_config_dict
-from bravado_core.spec import Spec, build_api_serving_url, _identity
+from bravado_core.formatter import SwaggerFormat
 from bravado_core.model import model_discovery
 from bravado_core.resource import build_resources
-from bravado.exception import HTTPNotFound
+from bravado_core.spec import Spec, _identity, build_api_serving_url
 from bravado_core.validate import validate_object
-from json2html import Json2Html
-from IPython.display import display, HTML, Image, FileLink
-from boltons.iterutils import remap
-from pymatgen.core import Structure as PmgStructure
-from concurrent.futures import as_completed
-from requests_futures.sessions import FuturesSession
-from urllib3.util.retry import Retry
+from bson.objectid import ObjectId
+from cachetools import LRUCache, cached
+from cachetools.keys import hashkey
+from filetype import guess
 from filetype.types.archive import Gz
-from filetype.types.image import Jpeg, Png, Gif, Tiff
+from filetype.types.image import Gif, Jpeg, Png, Tiff
+from flatten_dict import flatten, unflatten
+from IPython.display import HTML, FileLink, Image, display
+from json2html import Json2Html
+from jsonschema.exceptions import ValidationError
 from pint import UnitRegistry
 from pint.errors import DimensionalityError
-from tempfile import gettempdir
 from plotly.express._chart_types import line as line_chart
-from cachetools import cached, LRUCache
-from cachetools.keys import hashkey
-from pymatgen.core import SETTINGS
+from pyisemail import is_email
+from pyisemail.diagnosis import BaseDiagnosis
+from pymatgen.core import Structure as PmgStructure
+from requests.exceptions import RequestException
+from requests_futures.sessions import FuturesSession
+from swagger_spec_validator.common import SwaggerValidationError
+from tqdm.auto import tqdm
+from urllib3.util.retry import Retry
+
+try:
+    __version__ = importlib.metadata.version("mpcontribs-client")
+except Exception:
+    # package is not installed
+    pass
 
 RETRIES = 3
 MAX_WORKERS = 3
@@ -88,6 +91,7 @@ VALID_URLS |= {f"http://localhost.{n}-api.materialsproject.org" for n in SUBDOMA
 SUPPORTED_FILETYPES = (Gz, Jpeg, Png, Gif, Tiff)
 SUPPORTED_MIMES = [t().mime for t in SUPPORTED_FILETYPES]
 DEFAULT_DOWNLOAD_DIR = Path.home() / "mpcontribs-downloads"
+VALID_API_KEY_ALIASES = ["MPCONTRIBS_API_KEY", "MP_API_KEY", "PMG_MAPI_KEY"]
 
 j2h = Json2Html()
 pd.options.plotting.backend = "plotly"
@@ -126,7 +130,7 @@ _ipython = sys.modules["IPython"].get_ipython()
 class LogFilter(logging.Filter):
     def __init__(self, level, *args, **kwargs):
         self.level = level
-        super(LogFilter, self).__init__(*args, **kwargs)
+        super().__init__(*args, **kwargs)
 
     def filter(self, record):
         return record.levelno < self.level
@@ -144,7 +148,7 @@ class TqdmToLogger(io.StringIO):
     buf = ""
 
     def __init__(self, logger, level=None):
-        super(TqdmToLogger, self).__init__()
+        super().__init__()
         self.logger = logger
         self.level = level or logging.INFO
 
@@ -177,7 +181,7 @@ class MPContribsClientError(ValueError):
     """custom error for mpcontribs-client"""
 
 
-def get_md5(d):
+def get_md5(d) -> str:
     s = ujson.dumps(d, sort_keys=True).encode("utf-8")
     return md5(s).hexdigest()
 
@@ -478,7 +482,7 @@ class Attachment(dict):
 
         return unpacked
 
-    def write(self, outdir: Optional[Union[str, Path]] = None) -> Path:
+    def write(self, outdir: str | Path | None = None) -> Path:
         """Write attachment to file using its name
 
         Args:
@@ -490,7 +494,7 @@ class Attachment(dict):
         path.write_bytes(content)
         return path
 
-    def display(self, outdir: Optional[Union[str, Path]] = None):
+    def display(self, outdir: str | Path | None = None):
         """Display Image/FileLink for attachment if in IPython/Jupyter
 
         Args:
@@ -519,7 +523,7 @@ class Attachment(dict):
         return self["name"]
 
     @classmethod
-    def from_data(cls, data: Union[list, dict], name: str = "attachment"):
+    def from_data(cls, data: list | dict, name: str = "attachment"):
         """Construct attachment from data dict or list
 
         Args:
@@ -539,7 +543,7 @@ class Attachment(dict):
         )
 
     @classmethod
-    def from_file(cls, path: Union[Path, str]):
+    def from_file(cls, path: str | Path):
         """Construct attachment from file
 
         Args:
@@ -616,7 +620,7 @@ class Attachments(list):
         return attachments
 
     @classmethod
-    def from_data(cls, data: Union[list, dict], prefix: str = "attachment"):
+    def from_data(cls, data: list | dict, prefix: str = "attachment"):
         """Construct list of attachments from data dict or list
 
         Args:
@@ -830,32 +834,24 @@ def _expand_params(protocol, host, version, projects_json, apikey=None):
 def _version(url):
     retries, max_retries = 0, 3
     protocol = urlparse(url).scheme
-    is_mock_test = "pytest" in sys.modules and protocol == "http"
-
-    if is_mock_test:
-        now = datetime.datetime.now()
-        return Version(
-            major=now.year,
-            minor=now.month,
-            patch=now.day,
-            prerelease=(str(now.hour), str(now.minute)),
-        )
-    else:
-        while retries < max_retries:
-            try:
-                r = requests.get(f"{url}/healthcheck", timeout=5)
-                if r.status_code in {200, 403}:
-                    return r.json().get("version")
-                else:
-                    retries += 1
-                    logger.warning(
-                        f"Healthcheck for {url} failed ({r.status_code})! Wait 30s."
-                    )
-                    time.sleep(30)
-            except RequestException as ex:
+    if "pytest" in sys.modules and protocol == "http":
+        return __version__
+
+    while retries < max_retries:
+        try:
+            r = requests.get(f"{url}/healthcheck", timeout=5)
+            if r.status_code in {200, 403}:
+                return r.json().get("version")
+            else:
                 retries += 1
-                logger.warning(f"Could not connect to {url} ({ex})! Wait 30s.")
+                logger.warning(
+                    f"Healthcheck for {url} failed ({r.status_code})! Wait 30s."
+                )
                 time.sleep(30)
+        except RequestException as ex:
+            retries += 1
+            logger.warning(f"Could not connect to {url} ({ex})! Wait 30s.")
+            time.sleep(30)
 
 
 class Client(SwaggerClient):
@@ -870,11 +866,11 @@ class Client(SwaggerClient):
 
     def __init__(
         self,
-        apikey: Optional[str] = None,
-        headers: Optional[dict] = None,
-        host: Optional[str] = None,
-        project: Optional[str] = None,
-        session: Optional[requests.Session] = None,
+        apikey: str | None = None,
+        headers: dict | None = None,
+        host: str | None = None,
+        project: str | None = None,
+        session: requests.Session | None = None,
     ):
         """Initialize the client - only reloads API spec from server as needed
 
@@ -892,7 +888,17 @@ class Client(SwaggerClient):
             host = os.environ.get("MPCONTRIBS_API_HOST", DEFAULT_HOST)
 
         if not apikey:
-            apikey = os.environ.get("MPCONTRIBS_API_KEY", SETTINGS.get("PMG_MAPI_KEY"))
+            try:
+                apikey = next(
+                    os.environ.get(kalias)
+                    for kalias in VALID_API_KEY_ALIASES
+                    if kalias is not None
+                )
+            except StopIteration:
+                from pymatgen.core import SETTINGS
+
+                apikey = SETTINGS.get("PMG_MAPI_KEY")
+
             if apikey and len(apikey) != 32:
                 raise MPContribsClientError(f"Invalid API key: {apikey}")
 
@@ -925,7 +931,7 @@ class Client(SwaggerClient):
     def __enter__(self):
         return self
 
-    def __exit__(self, exc_type, exc_val, exc_tb):
+    def __exit__(self, exc_type, exc_val, exc_tb) -> None:
         return None
 
     @property
@@ -934,17 +940,18 @@ class Client(SwaggerClient):
             self.protocol, self.host, self.headers_json, self.project, self.version
         )
 
-    def __dir__(self):
+    def __dir__(self) -> set[str]:
         members = set(self.swagger_spec.resources.keys())
-        members |= set(k for k in self.__dict__.keys() if not k.startswith("_"))
-        members |= set(k for k in dir(self.__class__) if not k.startswith("_"))
+        members |= {k for k in self.__dict__.keys() if not k.startswith("_")}
+        members |= {k for k in dir(self.__class__) if not k.startswith("_")}
         return members
 
     def _reinit(self):
         _load.cache_clear()
         super().__init__(self.cached_swagger_spec)
 
-    def _is_valid_payload(self, model: str, data: dict):
+    def _is_valid_payload(self, model: str, data: dict) -> None:
+        """Raise an error if a payload is invalid."""
         model_spec = deepcopy(self.get_model(f"{model}sSchema")._model_spec)
         model_spec.pop("required")
         model_spec["additionalProperties"] = False
@@ -952,17 +959,20 @@ class Client(SwaggerClient):
         try:
             validate_object(self.swagger_spec, model_spec, data)
         except ValidationError as ex:
-            return False, str(ex)
-
-        return True, None
+            raise MPContribsClientError(str(ex))
 
-    def _is_serializable_dict(self, dct):
-        for k, v in flatten(dct, reducer="dot").items():
-            if v is not None and not isinstance(v, (str, int, float)):
-                error = f"Value {v} of {type(v)} for key {k} not supported."
-                return False, error
-
-        return True, None
+    def _is_serializable_dict(self, dct: dict) -> None:
+        """Raise an error if an input dict is not JSON serializable."""
+        try:
+            raise MPContribsClientError(
+                next(
+                    f"Value {v} of {type(v)} for key {k} not supported."
+                    for k, v in flatten(dct, reducer="dot").items()
+                    if v is not None and not isinstance(v, (str, int, float))
+                )
+            )
+        except StopIteration:
+            pass
 
     def _get_per_page_default_max(
         self, op: str = "query", resource: str = "contributions"
@@ -1030,14 +1040,10 @@ class Client(SwaggerClient):
 
         for q in queries:
             # copy over missing parameters
-            for k, v in query.items():
-                if k not in q:
-                    q[k] = v
+            q.update({k: v for k, v in query.items() if k not in q})
 
             # comma-separated lists
-            for k, v in q.items():
-                if isinstance(v, list):
-                    q[k] = ",".join(v)
+            q.update({k: ",".join(v) for k, v in q.items() if isinstance(v, list)})
 
         return queries
 
@@ -1047,7 +1053,7 @@ class Client(SwaggerClient):
         params: dict,
         rel_url: str = "contributions",
         op: str = "query",
-        data: Optional[dict] = None,
+        data: dict | None = None,
     ):
         rname = rel_url.split("/", 1)[0]
         resource = self.swagger_spec.resources[rname]
@@ -1066,7 +1072,7 @@ class Client(SwaggerClient):
 
     def available_query_params(
         self,
-        startswith: Optional[tuple] = None,
+        startswith: tuple | None = None,
         resource: str = "contributions",
     ) -> list:
         resources = self.swagger_spec.resources
@@ -1083,9 +1089,7 @@ class Client(SwaggerClient):
 
         return [param for param in params if param.startswith(startswith)]
 
-    def get_project(
-        self, name: Optional[str] = None, fields: Optional[list] = None
-    ) -> Dict:
+    def get_project(self, name: str | None = None, fields: list | None = None) -> Dict:
         """Retrieve a project entry
 
         Args:
@@ -1103,10 +1107,10 @@ class Client(SwaggerClient):
 
     def query_projects(
         self,
-        query: Optional[dict] = None,
-        term: Optional[str] = None,
-        fields: Optional[list] = None,
-        sort: Optional[str] = None,
+        query: dict | None = None,
+        term: str | None = None,
+        fields: list | None = None,
+        sort: str | None = None,
         timeout: int = -1,
     ) -> list[dict]:
         """Query projects by query and/or term (Atlas Search)
@@ -1124,10 +1128,10 @@ class Client(SwaggerClient):
         Returns:
             List of projects
         """
-        query = query or {}
+        q = deepcopy(query) or {}
 
-        if self.project or "name" in query:
-            return [self.get_project(name=query.get("name"), fields=fields)]
+        if self.project or "name" in q:
+            return [self.get_project(name=q.get("name"), fields=fields)]
 
         if term:
 
@@ -1144,38 +1148,78 @@ class Client(SwaggerClient):
             responses = _run_futures(
                 [search_future(term)], timeout=timeout, disable=True
             )
-            query["name__in"] = responses["search"].get("result", [])
+            q["name__in"] = responses["search"].get("result", [])
 
         if fields:
-            query["_fields"] = fields
+            q["_fields"] = fields
         if sort:
-            query["_sort"] = sort
+            q["_sort"] = sort
 
-        ret = self.projects.queryProjects(**query).result()  # first page
+        ret = self.projects.queryProjects(**q).result()  # first page
+        """
+        'ret' type:
+        {
+            "data": [
+                ...
+            ],
+            "has_more": <bool>,
+            "total_count": <int>,
+            "total_pages": <int>
+        }
+        """
         total_count, total_pages = ret["total_count"], ret["total_pages"]
 
         if total_pages < 2:
             return ret["data"]
 
-        for field in ["name__in", "_fields"]:
-            if field in query:
-                query[field] = ",".join(query[field])
+        q.update(
+            {
+                field: ",".join(q[field])
+                for field in ["name__in", "_fields"]
+                if field in q
+            }
+        )
 
         queries = []
 
         for page in range(2, total_pages + 1):
-            queries.append(deepcopy(query))
+            queries.append(deepcopy(q))
             queries[-1]["page"] = page
 
         futures = [
-            self._get_future(i, q, rel_url="projects") for i, q in enumerate(queries)
+            self._get_future(i, _q, rel_url="projects") for i, _q in enumerate(queries)
         ]
         responses = _run_futures(futures, total=total_count, timeout=timeout)
+        """
+        'responses' type:
+        {
+            "0": {
+                "result": {
+                    "data": [
+                        ...
+                    ],
+                    "has_more": <bool>,
+                    "total_count": <int>,
+                    "total_pages": <int>
+                },
+                "count": <int>
+            },
+            "1": ...
+        }
+        """
 
-        for resp in responses.values():
-            ret["data"] += resp["result"]["data"]
-
-        return ret["data"]
+        return list(
+            itertools.chain.from_iterable(
+                [
+                    ret["data"],
+                    itertools.chain.from_iterable(
+                        # did not hit early return, guaranteed
+                        # to have additional pages w/ data
+                        map(lambda x: x["result"]["data"], iter(responses.values()))
+                    ),
+                ]
+            )
+        )
 
     def create_project(
         self, name: str, title: str, authors: str, description: str, url: str
@@ -1210,7 +1254,7 @@ class Client(SwaggerClient):
         else:
             raise MPContribsClientError(resp)
 
-    def update_project(self, update: dict, name: Optional[str] = None):
+    def update_project(self, update: dict, name: str | None = None):
         """Update project info
 
         Args:
@@ -1268,15 +1312,12 @@ class Client(SwaggerClient):
             logger.warning("nothing to update")
             return
 
-        valid, error = self._is_valid_payload("Project", payload)
-        if valid:
-            resp = self.projects.updateProjectByName(pk=name, project=payload).result()
-            if not resp.get("count", 0):
-                raise MPContribsClientError(resp)
-        else:
-            raise MPContribsClientError(error)
+        self._is_valid_payload("Project", payload)
+        resp = self.projects.updateProjectByName(pk=name, project=payload).result()
+        if not resp.get("count", 0):
+            raise MPContribsClientError(resp)
 
-    def delete_project(self, name: Optional[str] = None):
+    def delete_project(self, name: str | None = None):
         """Delete a project
 
         Args:
@@ -1295,7 +1336,7 @@ class Client(SwaggerClient):
         if resp and "error" in resp:
             raise MPContribsClientError(resp["error"])
 
-    def get_contribution(self, cid: str, fields: Optional[list] = None) -> Dict:
+    def get_contribution(self, cid: str, fields: list | None = None) -> Dict:
         """Retrieve a contribution
 
         Args:
@@ -1408,7 +1449,7 @@ class Client(SwaggerClient):
         )
 
     def init_columns(
-        self, columns: Optional[dict] = None, name: Optional[str] = None
+        self, columns: dict | None = None, name: str | None = None
     ) -> dict:
         """initialize columns for a project to set their order and desired units
 
@@ -1532,20 +1573,23 @@ class Client(SwaggerClient):
                     new_unit = new_column.get("unit", "NaN")
                     existing_unit = existing_column.get("unit")
                     if existing_unit != new_unit:
-                        conv_args = []
-                        for u in [existing_unit, new_unit]:
+                        if existing_unit == "NaN" and new_unit == "":
+                            factor = 1
+                        else:
+                            conv_args = []
+                            for u in [existing_unit, new_unit]:
+                                try:
+                                    conv_args.append(ureg.Unit(u))
+                                except ValueError:
+                                    raise MPContribsClientError(
+                                        f"Can't convert {existing_unit} to {new_unit} for {path}"
+                                    )
                             try:
-                                conv_args.append(ureg.Unit(u))
-                            except ValueError:
+                                factor = ureg.convert(1, *conv_args)
+                            except DimensionalityError:
                                 raise MPContribsClientError(
                                     f"Can't convert {existing_unit} to {new_unit} for {path}"
                                 )
-                        try:
-                            factor = ureg.convert(1, *conv_args)
-                        except DimensionalityError:
-                            raise MPContribsClientError(
-                                f"Can't convert {existing_unit} to {new_unit} for {path}"
-                            )
 
                         if not isclose(factor, 1):
                             logger.info(
@@ -1560,13 +1604,11 @@ class Client(SwaggerClient):
                 new_columns.append(new_column)
 
         payload = {"columns": new_columns}
-        valid, error = self._is_valid_payload("Project", payload)
-        if not valid:
-            raise MPContribsClientError(error)
+        self._is_valid_payload("Project", payload)
 
         return self.projects.updateProjectByName(pk=name, project=payload).result()
 
-    def delete_contributions(self, query: Optional[dict] = None, timeout: int = -1):
+    def delete_contributions(self, query: dict | None = None, timeout: int = -1):
         """Remove all contributions for a query
 
         Args:
@@ -1579,25 +1621,25 @@ class Client(SwaggerClient):
             )
 
         tic = time.perf_counter()
-        query = query or {}
+        q = deepcopy(query) or {}
 
         if self.project:
-            query["project"] = self.project
+            q["project"] = self.project
 
-        name = query["project"]
-        cids = list(self.get_all_ids(query).get(name, {}).get("ids", set()))
+        name = q["project"]
+        cids = list(self.get_all_ids(q).get(name, {}).get("ids", set()))
 
         if not cids:
             logger.info(f"There aren't any contributions to delete for {name}")
             return
 
         total = len(cids)
-        query = {"id__in": cids}
-        _, total_pages = self.get_totals(query=query)
-        queries = self._split_query(query, op="delete", pages=total_pages)
-        futures = [self._get_future(i, q, op="delete") for i, q in enumerate(queries)]
+        id_query = {"id__in": cids}
+        _, total_pages = self.get_totals(query=id_query)
+        queries = self._split_query(id_query, op="delete", pages=total_pages)
+        futures = [self._get_future(i, _q, op="delete") for i, _q in enumerate(queries)]
         _run_futures(futures, total=total, timeout=timeout)
-        left, _ = self.get_totals(query=query)
+        left, _ = self.get_totals(query=id_query)
         deleted = total - left
         self.init_columns(name=name)
         self._reinit()
@@ -1612,7 +1654,7 @@ class Client(SwaggerClient):
 
     def get_totals(
         self,
-        query: Optional[dict] = None,
+        query: dict | None = None,
         timeout: int = -1,
         resource: str = "contributions",
         op: str = "query",
@@ -1633,31 +1675,31 @@ class Client(SwaggerClient):
         if op not in ops:
             raise MPContribsClientError(f"`op` has to be one of {ops}")
 
-        query = query or {}
-        if self.project and "project" not in query:
-            query["project"] = self.project
+        q = deepcopy(query) or {}
+        if self.project and "project" not in q:
+            q["project"] = self.project
 
         skip_keys = {"per_page", "_fields", "format", "_sort"}
-        query = {k: v for k, v in query.items() if k not in skip_keys}
-        query["_fields"] = []  # only need totals -> explicitly request no fields
-        queries = self._split_query(query, resource=resource, op=op)  # don't paginate
-        result = {"total_count": 0, "total_pages": 0}
+        q = {k: v for k, v in q.items() if k not in skip_keys}
+        q["_fields"] = []  # only need totals -> explicitly request no fields
+        queries = self._split_query(q, resource=resource, op=op)  # don't paginate
         futures = [
-            self._get_future(i, q, rel_url=resource) for i, q in enumerate(queries)
+            self._get_future(i, _q, rel_url=resource) for i, _q in enumerate(queries)
         ]
         responses = _run_futures(futures, timeout=timeout, desc="Totals")
 
-        for resp in responses.values():
-            for k in result:
-                result[k] += resp.get("result", {}).get(k, 0)
+        result = {
+            k: sum(resp.get("result", {}).get(k, 0) for resp in responses.values())
+            for k in ("total_count", "total_pages")
+        }
 
         return result["total_count"], result["total_pages"]
 
-    def count(self, query: Optional[dict] = None) -> int:
+    def count(self, query: dict | None = None) -> int:
         """shortcut for get_totals()"""
         return self.get_totals(query=query)[0]
 
-    def get_unique_identifiers_flags(self, query: Optional[dict] = None) -> dict:
+    def get_unique_identifiers_flags(self, query: dict | None = None) -> dict:
         """Retrieve values for `unique_identifiers` flags.
 
         See `client.available_query_params(resource="projects")` for available query parameters.
@@ -1677,10 +1719,10 @@ class Client(SwaggerClient):
 
     def get_all_ids(
         self,
-        query: Optional[dict] = None,
-        include: Optional[list[str]] = None,
+        query: dict | None = None,
+        include: list[str] | None = None,
         timeout: int = -1,
-        data_id_fields: Optional[dict] = None,
+        data_id_fields: dict | None = None,
         fmt: str = "sets",
         op: str = "query",
     ) -> dict:
@@ -1731,7 +1773,7 @@ class Client(SwaggerClient):
             }, ...}
         """
         include = include or []
-        components = set(x for x in include if x in COMPONENTS)
+        components = {x for x in include if x in COMPONENTS}
         if include and not components:
             raise MPContribsClientError(f"`include` must be subset of {COMPONENTS}!")
 
@@ -1745,16 +1787,20 @@ class Client(SwaggerClient):
 
         unique_identifiers = self.get_unique_identifiers_flags()
         data_id_fields = data_id_fields or {}
-        for k, v in data_id_fields.items():
-            if k in unique_identifiers and isinstance(v, str):
-                data_id_fields[k] = v
+        data_id_fields.update(
+            {
+                k: v
+                for k, v in data_id_fields.items()
+                if k in unique_identifiers and isinstance(v, str)
+            }
+        )
 
         ret = {}
-        query = query or {}
-        if self.project and "project" not in query:
-            query["project"] = self.project
+        q = deepcopy(query) or {}
+        if self.project and "project" not in q:
+            q["project"] = self.project
 
-        [query.pop(k, None) for k in ["page", "per_page", "_fields"]]
+        [q.pop(k, None) for k in ["page", "per_page", "_fields"]]
         id_fields = {"project", "id", "identifier"}
 
         if data_id_fields:
@@ -1762,10 +1808,10 @@ class Client(SwaggerClient):
                 f"data.{data_id_field}" for data_id_field in data_id_fields.values()
             )
 
-        query["_fields"] = list(id_fields | components)
-        _, total_pages = self.get_totals(query=query, timeout=timeout)
-        queries = self._split_query(query, op=op, pages=total_pages)
-        futures = [self._get_future(i, q) for i, q in enumerate(queries)]
+        q["_fields"] = list(id_fields | components)
+        _, total_pages = self.get_totals(query=q, timeout=timeout)
+        queries = self._split_query(q, op=op, pages=total_pages)
+        futures = [self._get_future(i, _q) for i, _q in enumerate(queries)]
         responses = _run_futures(futures, timeout=timeout, desc="Identifiers")
 
         for resp in responses.values():
@@ -1810,34 +1856,40 @@ class Client(SwaggerClient):
                         if data_id_field and data_id_field_val:
                             ret[project][identifier][data_id_field] = data_id_field_val
 
-                        for component in components:
-                            if component in contrib:
-                                ret[project][identifier][component] = {
+                        ret[project][identifier].update(
+                            {
+                                component: {
                                     d["name"]: {"id": d["id"], "md5": d["md5"]}
                                     for d in contrib[component]
                                 }
+                                for component in components
+                                if component in contrib
+                            }
+                        )
 
                     elif data_id_field and data_id_field_val:
                         ret[project][identifier] = {
                             data_id_field_val: {"id": contrib["id"]}
                         }
 
-                        for component in components:
-                            if component in contrib:
-                                ret[project][identifier][data_id_field_val][
-                                    component
-                                ] = {
+                        ret[project][identifier][data_id_field_val].update(
+                            {
+                                component: {
                                     d["name"]: {"id": d["id"], "md5": d["md5"]}
                                     for d in contrib[component]
                                 }
+                                for component in components
+                                if component in contrib
+                            }
+                        )
 
         return ret
 
     def query_contributions(
         self,
-        query: Optional[dict] = None,
-        fields: Optional[list] = None,
-        sort: Optional[str] = None,
+        query: dict | None = None,
+        fields: list | None = None,
+        sort: str | None = None,
         paginate: bool = False,
         timeout: int = -1,
     ) -> dict:
@@ -1855,18 +1907,17 @@ class Client(SwaggerClient):
         Returns:
             List of contributions
         """
-        query = query or {}
+        q: dict = deepcopy(query) or {}
 
-        if self.project and "project" not in query:
-            query["project"] = self.project
+        if self.project and "project" not in q:
+            q["project"] = self.project
 
         if paginate:
-            cids = []
-
-            for v in self.get_all_ids(query).values():
-                cids_project = v.get("ids")
-                if cids_project:
-                    cids.extend(cids_project)
+            cids = [
+                idx
+                for v in self.get_all_ids(q).values()
+                for idx in (v.get("ids") or [])
+            ]
 
             if not cids:
                 raise MPContribsClientError("No contributions match the query.")
@@ -1875,23 +1926,32 @@ class Client(SwaggerClient):
             cids_query = {"id__in": cids, "_fields": fields, "_sort": sort}
             _, total_pages = self.get_totals(query=cids_query)
             queries = self._split_query(cids_query, pages=total_pages)
-            futures = [self._get_future(i, q) for i, q in enumerate(queries)]
-            responses = _run_futures(futures, total=total, timeout=timeout)
-            ret = {"total_count": 0, "data": []}
-
-            for resp in responses.values():
-                result = resp["result"]
-                ret["data"].extend(result["data"])
-                ret["total_count"] += result["total_count"]
+            futures = [self._get_future(i, _q) for i, _q in enumerate(queries)]
+            responses = [
+                resp
+                for resp in _run_futures(futures, total=total, timeout=timeout).values()
+                if resp.get("result")
+            ]
+            ret = {
+                "total_count": sum(
+                    resp["result"].get("total_count", 0) for resp in responses
+                ),
+                "data": list(
+                    itertools.chain.from_iterable(
+                        [resp["result"].get("data", []) for resp in responses]
+                    )
+                ),
+            }
+
         else:
             ret = self.contributions.queryContributions(
-                _fields=fields, _sort=sort, **query
+                _fields=fields, _sort=sort, **q
             ).result()
 
         return ret
 
     def update_contributions(
-        self, data: dict, query: Optional[dict] = None, timeout: int = -1
+        self, data: dict, query: dict | None = None, timeout: int = -1
     ) -> dict:
         """Apply the same update to all contributions in a project (matching query)
 
@@ -1906,31 +1966,27 @@ class Client(SwaggerClient):
             raise MPContribsClientError("Nothing to update.")
 
         tic = time.perf_counter()
-        valid, error = self._is_valid_payload("Contribution", data)
-        if not valid:
-            raise MPContribsClientError(error)
+        self._is_valid_payload("Contribution", data)
 
         if "data" in data:
-            serializable, error = self._is_serializable_dict(data["data"])
-            if not serializable:
-                raise MPContribsClientError(error)
+            self._is_serializable_dict(data["data"])
 
-        query = query or {}
+        q = deepcopy(query) or {}
 
         if self.project:
-            if "project" in query and self.project != query["project"]:
+            if "project" in q and self.project != q["project"]:
                 raise MPContribsClientError(
                     f"client initialized with different project {self.project}!"
                 )
-            query["project"] = self.project
+            q["project"] = self.project
         else:
-            if not query or "project" not in query:
+            if not q or "project" not in q:
                 raise MPContribsClientError(
                     "initialize client with project, or include project in query!"
                 )
 
-        name = query["project"]
-        cids = list(self.get_all_ids(query).get(name, {}).get("ids", set()))
+        name = q["project"]
+        cids = list(self.get_all_ids(q).get(name, {}).get("ids", set()))
 
         if not cids:
             raise MPContribsClientError(
@@ -1939,22 +1995,22 @@ class Client(SwaggerClient):
 
         # get current list of data columns to decide if swagger reload is needed
         resp = self.projects.getProjectByName(pk=name, _fields=["columns"]).result()
-        old_paths = set(c["path"] for c in resp["columns"])
+        old_paths = {c["path"] for c in resp["columns"]}
 
         total = len(cids)
         cids_query = {"id__in": cids}
         _, total_pages = self.get_totals(query=cids_query)
         queries = self._split_query(cids_query, op="update", pages=total_pages)
         futures = [
-            self._get_future(i, q, op="update", data=data)
-            for i, q in enumerate(queries)
+            self._get_future(i, _q, op="update", data=data)
+            for i, _q in enumerate(queries)
         ]
         responses = _run_futures(futures, total=total, timeout=timeout)
         updated = sum(resp["count"] for _, resp in responses.items())
 
         if updated:
             resp = self.projects.getProjectByName(pk=name, _fields=["columns"]).result()
-            new_paths = set(c["path"] for c in resp["columns"])
+            new_paths = {c["path"] for c in resp["columns"]}
 
             if new_paths != old_paths:
                 self.init_columns(name=name)
@@ -1964,7 +2020,7 @@ class Client(SwaggerClient):
         return {"updated": updated, "total": total, "seconds_elapsed": toc - tic}
 
     def make_public(
-        self, query: Optional[dict] = None, recursive: bool = False, timeout: int = -1
+        self, query: dict | None = None, recursive: bool = False, timeout: int = -1
     ) -> dict:
         """Publish a project and optionally its contributions
 
@@ -1977,7 +2033,7 @@ class Client(SwaggerClient):
         )
 
     def make_private(
-        self, query: Optional[dict] = None, recursive: bool = False, timeout: int = -1
+        self, query: dict | None = None, recursive: bool = False, timeout: int = -1
     ) -> dict:
         """Make a project and optionally its contributions private
 
@@ -1992,7 +2048,7 @@ class Client(SwaggerClient):
     def _set_is_public(
         self,
         is_public: bool,
-        query: Optional[dict] = None,
+        query: dict | None = None,
         recursive: bool = False,
         timeout: int = -1,
     ) -> dict:
@@ -2009,23 +2065,23 @@ class Client(SwaggerClient):
                 "initialize client with project, or include project in query!"
             )
 
-        query = query or {}
+        q = deepcopy(query) or {}
 
         if self.project:
-            query["project"] = self.project
+            q["project"] = self.project
 
         try:
             resp = self.projects.getProjectByName(
-                pk=query["project"], _fields=["is_public", "is_approved"]
+                pk=q["project"], _fields=["is_public", "is_approved"]
             ).result()
         except HTTPNotFound:
             raise MPContribsClientError(
-                f"project `{query['project']}` not found or access denied!"
+                f"project `{q['project']}` not found or access denied!"
             )
 
         if not recursive and resp["is_public"] == is_public:
             return {
-                "warning": f"`is_public` already set to {is_public} for `{query['project']}`."
+                "warning": f"`is_public` already set to {is_public} for `{q['project']}`."
             }
 
         ret = {}
@@ -2033,19 +2089,19 @@ class Client(SwaggerClient):
         if resp["is_public"] != is_public:
             if is_public and not resp["is_approved"]:
                 raise MPContribsClientError(
-                    f"project `{query['project']}` is not approved yet!"
+                    f"project `{q['project']}` is not approved yet!"
                 )
 
             resp = self.projects.updateProjectByName(
-                pk=query["project"], project={"is_public": is_public}
+                pk=q["project"], project={"is_public": is_public}
             ).result()
             ret["published"] = resp["count"] == 1
 
         if recursive:
-            query = query or {}
-            query["is_public"] = not is_public
+            q = deepcopy(query) or {}
+            q["is_public"] = not is_public
             ret["contributions"] = self.update_contributions(
-                {"is_public": is_public}, query=query, timeout=timeout
+                {"is_public": is_public}, query=q, timeout=timeout
             )
 
         return ret
@@ -2124,9 +2180,13 @@ class Client(SwaggerClient):
             resp = self.get_all_ids(dict(id__in=collect_ids), timeout=timeout)
             project_names |= set(resp.keys())
 
-            for project_name, values in resp.items():
-                for cid in values["ids"]:
-                    id2project[cid] = project_name
+            id2project.update(
+                {
+                    cid: project_name
+                    for project_name, values in resp.items()
+                    for cid in values["ids"]
+                }
+            )
 
         existing = defaultdict(dict)
         unique_identifiers = defaultdict(dict)
@@ -2160,9 +2220,7 @@ class Client(SwaggerClient):
         for contrib in tqdm(contributions, desc="Prepare"):
             if "data" in contrib:
                 contrib["data"] = unflatten(contrib["data"], splitter="dot")
-                serializable, error = self._is_serializable_dict(contrib["data"])
-                if not serializable:
-                    raise MPContribsClientError(error)
+                self._is_serializable_dict(contrib["data"])
 
             update = "id" in contrib
             project_name = id2project[contrib["id"]] if update else contrib["project"]
@@ -2282,13 +2340,7 @@ class Client(SwaggerClient):
                     digests[project_name][component].add(digest)
                     contribs[project_name][-1][component].append(dct)
 
-                valid, error = self._is_valid_payload(
-                    "Contribution", contribs[project_name][-1]
-                )
-                if not valid:
-                    raise MPContribsClientError(
-                        f"{contrib['identifier']} invalid: {error}!"
-                    )
+                self._is_valid_payload("Contribution", contribs[project_name][-1])
 
         # submit contributions
         if contribs:
@@ -2425,10 +2477,10 @@ class Client(SwaggerClient):
 
     def download_contributions(
         self,
-        query: Optional[dict] = None,
-        outdir: Union[str, Path] = DEFAULT_DOWNLOAD_DIR,
+        query: dict | None = None,
+        outdir: str | Path = DEFAULT_DOWNLOAD_DIR,
         overwrite: bool = False,
-        include: Optional[list[str]] = None,
+        include: list[str] | None = None,
         timeout: int = -1,
     ) -> list:
         """Download a list of contributions as .json.gz file(s)
@@ -2444,16 +2496,16 @@ class Client(SwaggerClient):
             Number of new downloads written to disk.
         """
         start = time.perf_counter()
-        query = query or {}
+        q = deepcopy(query) or {}
         include = include or []
         outdir = Path(outdir) or Path(".")
         outdir.mkdir(parents=True, exist_ok=True)
-        components = set(x for x in include if x in COMPONENTS)
+        components = {x for x in include if x in COMPONENTS}
         if include and not components:
             raise MPContribsClientError(f"`include` must be subset of {COMPONENTS}!")
 
-        all_ids = self.get_all_ids(query, include=list(components), timeout=timeout)
-        fmt = query.get("format", "json")
+        all_ids = self.get_all_ids(q, include=list(components), timeout=timeout)
+        fmt = q.get("format", "json")
         contributions, components_loaded = [], defaultdict(dict)
 
         for name, values in all_ids.items():
@@ -2527,7 +2579,7 @@ class Client(SwaggerClient):
     def download_structures(
         self,
         ids: list[str],
-        outdir: Union[str, Path] = DEFAULT_DOWNLOAD_DIR,
+        outdir: str | Path = DEFAULT_DOWNLOAD_DIR,
         overwrite: bool = False,
         timeout: int = -1,
         fmt: str = "json",
@@ -2556,7 +2608,7 @@ class Client(SwaggerClient):
     def download_tables(
         self,
         ids: list[str],
-        outdir: Union[str, Path] = DEFAULT_DOWNLOAD_DIR,
+        outdir: str | Path = DEFAULT_DOWNLOAD_DIR,
         overwrite: bool = False,
         timeout: int = -1,
         fmt: str = "json",
@@ -2585,7 +2637,7 @@ class Client(SwaggerClient):
     def download_attachments(
         self,
         ids: list[str],
-        outdir: Union[str, Path] = DEFAULT_DOWNLOAD_DIR,
+        outdir: str | Path = DEFAULT_DOWNLOAD_DIR,
         overwrite: bool = False,
         timeout: int = -1,
         fmt: str = "json",
@@ -2615,7 +2667,7 @@ class Client(SwaggerClient):
         self,
         resource: str,
         ids: list[str],
-        outdir: Union[str, Path] = DEFAULT_DOWNLOAD_DIR,
+        outdir: str | Path = DEFAULT_DOWNLOAD_DIR,
         overwrite: bool = False,
         timeout: int = -1,
         fmt: str = "json",

mpcontribs_client-5.10.5rc1.dist-info/METADATA

@@ -0,0 +1,39 @@
+Metadata-Version: 2.4
+Name: mpcontribs-client
+Version: 5.10.5rc1
+Summary: Client library for MPContribs API
+Author-email: Patrick Huck <phuck@lbl.gov>, The Materials Project <feedback@materialsproject.org>
+License-Expression: BSD-3-Clause-LBNL
+Project-URL: Homepage, https://github.com/materialsproject/MPContribs
+Project-URL: Documentation, https://docs.materialsproject.org/services/mpcontribs
+Requires-Python: >=3.11
+License-File: LICENSE
+Requires-Dist: numpy
+Requires-Dist: boltons
+Requires-Dist: bravado
+Requires-Dist: filetype
+Requires-Dist: flatten-dict
+Requires-Dist: ipython
+Requires-Dist: json2html
+Requires-Dist: pandas
+Requires-Dist: pint
+Requires-Dist: plotly
+Requires-Dist: pyIsEmail
+Requires-Dist: pymatgen
+Requires-Dist: pymongo
+Requires-Dist: requests-futures
+Requires-Dist: swagger-spec-validator
+Requires-Dist: tqdm
+Requires-Dist: ujson
+Requires-Dist: cachetools
+Provides-Extra: dev
+Requires-Dist: flake8; extra == "dev"
+Requires-Dist: pytest; extra == "dev"
+Requires-Dist: pytest-flake8; extra == "dev"
+Requires-Dist: pytest-pycodestyle; extra == "dev"
+Requires-Dist: pytest-cov; extra == "dev"
+Requires-Dist: pytest-xdist; extra == "dev"
+Requires-Dist: py; extra == "dev"
+Provides-Extra: all
+Requires-Dist: mpcontribs-client[dev]; extra == "all"
+Dynamic: license-file

mpcontribs_client-5.10.5rc1.dist-info/RECORD

@@ -0,0 +1,6 @@
+mpcontribs/client/__init__.py,sha256=AwKIDzTg30ZMW97QxQZ1OCwJAFrXT3XMdRktgL356Jc,98456
+mpcontribs_client-5.10.5rc1.dist-info/licenses/LICENSE,sha256=5tG0Niaqw2hnuyZZYkRXLSnfVrZA47COwduU_6caPLM,1074
+mpcontribs_client-5.10.5rc1.dist-info/METADATA,sha256=APCeqCMlQLDEAEBwUYk6CFqHdawo-JDmCgz3VA9R8bg,1289
+mpcontribs_client-5.10.5rc1.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
+mpcontribs_client-5.10.5rc1.dist-info/top_level.txt,sha256=t8R5L_Dg9oDQMh2gyRFdZGnrzZsr7OjCBTrhTcmimC8,11
+mpcontribs_client-5.10.5rc1.dist-info/RECORD,,

{mpcontribs_client-5.10.4.dist-info → mpcontribs_client-5.10.5rc1.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (80.9.0)
+Generator: setuptools (80.10.2)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

mpcontribs_client-5.10.4.dist-info/METADATA

@@ -1,88 +0,0 @@
-Metadata-Version: 2.4
-Name: mpcontribs-client
-Version: 5.10.4
-Summary: client library for MPContribs API
-Home-page: https://github.com/materialsproject/MPContribs/tree/master/mpcontribs-client
-Author: Patrick Huck
-Author-email: phuck@lbl.gov
-License: MIT
-Requires-Python: >=3.8
-Description-Content-Type: text/markdown
-License-File: LICENSE
-Requires-Dist: numpy
-Requires-Dist: boltons
-Requires-Dist: bravado
-Requires-Dist: filetype
-Requires-Dist: flatten-dict
-Requires-Dist: ipython
-Requires-Dist: json2html
-Requires-Dist: pandas
-Requires-Dist: pint
-Requires-Dist: plotly
-Requires-Dist: pyIsEmail
-Requires-Dist: pymatgen
-Requires-Dist: pymongo
-Requires-Dist: requests-futures
-Requires-Dist: swagger-spec-validator
-Requires-Dist: tqdm
-Requires-Dist: ujson
-Requires-Dist: semantic-version
-Requires-Dist: cachetools
-Provides-Extra: dev
-Requires-Dist: flake8; extra == "dev"
-Requires-Dist: pytest; extra == "dev"
-Requires-Dist: pytest-flake8; extra == "dev"
-Requires-Dist: pytest-pycodestyle; extra == "dev"
-Requires-Dist: pytest-cov; extra == "dev"
-Requires-Dist: py; extra == "dev"
-Dynamic: author
-Dynamic: author-email
-Dynamic: description
-Dynamic: description-content-type
-Dynamic: home-page
-Dynamic: license
-Dynamic: license-file
-Dynamic: provides-extra
-Dynamic: requires-dist
-Dynamic: requires-python
-Dynamic: summary
-
-![PyPI](https://img.shields.io/pypi/v/mpcontribs-client?style=flat-square)
-![Libraries.io dependency status for latest release](https://img.shields.io/librariesio/release/pypi/mpcontribs-client?style=flat-square)
-
-Small, dynamic python client library to connect to [MPContribs](https://docs.mpcontribs.org)
-APIs based on Yelp's [bravado](https://bravado.readthedocs.io).
-
-```python
-from mpcontribs.client import Client
-client = Client()
-dir(client) # show available resources
-```
-
-By default, the client connects to https://contribs-api.materialsproject.org and uses the environment variable
-`MPCONTRIBS_API_KEY` to set the API key. The key can alternatively be set explicitly via the
-`apikey` argument to the constructor. The `host` argument or the `MPCONTRIBS_API_HOST`
-environment variable can be set to connect to other MPContribs-style APIs:
-
-```python
-client = Client(host='ml-api.materialsproject.org')
-```
-
-**Troubleshooting**
-
-```
-twisted.web._newclient.ResponseNeverReceived:
-[<twisted.python.failure.Failure OpenSSL.SSL.Error:
-[('SSL routines', 'tls_process_server_certificate', 'certificate verify failed')]>]
-```
-
-Set the environment variable `SSL_CERT_FILE` to `$(python -m certifi)`.
-
-```
-OverflowError: timeout value is too large
-```
-
-Install the bravado fork ([PR](https://github.com/Yelp/bravado/pull/472)) manually via  
-```
-pip install "bravado[fido] @ git+https://github.com/tschaume/bravado@9ce06f2df7118e16af4a3d3fdc21ccfeedc5cd50#egg=bravado-11.0.3"
-```

mpcontribs_client-5.10.4.dist-info/RECORD

@@ -1,6 +0,0 @@
-mpcontribs/client/__init__.py,sha256=9BAtCiXfx38ueipZB5sxVw7208-n6sxDrQ6MGNG8Cuw,97518
-mpcontribs_client-5.10.4.dist-info/licenses/LICENSE,sha256=5tG0Niaqw2hnuyZZYkRXLSnfVrZA47COwduU_6caPLM,1074
-mpcontribs_client-5.10.4.dist-info/METADATA,sha256=wXAUbmYkDzPOcQqIAGVyTliExfTPjbtS7KpP4NuUpM8,2798
-mpcontribs_client-5.10.4.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-mpcontribs_client-5.10.4.dist-info/top_level.txt,sha256=t8R5L_Dg9oDQMh2gyRFdZGnrzZsr7OjCBTrhTcmimC8,11
-mpcontribs_client-5.10.4.dist-info/RECORD,,