Refactor czi_hosted and server into backend directory, pull common code into backend/common, refactor tests (#2102)

* move local_server -> backend/server server-> backend/czi_hosted, pull common code into backend/common update imports, tests and make commands

backend/server/common/annotations/annotations.py

@@ -0,0 +1,144 @@
+from abc import ABCMeta, abstractmethod
+
+import fastobo
+import fsspec
+
+from backend.common.errors import OntologyLoadFailure, DisabledFeatureError
+from backend.common.utils.type_conversion_utils import get_schema_type_hint_of_array
+
+
+class Annotations(metaclass=ABCMeta):
+    """ baseclass for annotations, including ontologies and genesets"""
+
+    """ our default ontology is the PURL for the Cell Ontology.
+    See http://www.obofoundry.org/ontology/cl.html """
+    DefaultOnotology = "http://purl.obolibrary.org/obo/cl.obo"
+
+    def __init__(self, config={}):
+        self.ontology_data = None
+        self.config = config
+
+    def user_annotations_enabled(self):
+        return self.config.get("user-annotations", False)
+
+    def gene_sets_save_enabled(self):
+        return self.config.get("genesets-save", False)
+
+    def check_user_annotations_enabled(self):
+        if not self.user_annotations_enabled():
+            raise DisabledFeatureError("User annotations are disabled.")
+
+    def check_gene_sets_save_enabled(self):
+        if not self.gene_sets_save_enabled():
+            raise DisabledFeatureError("User genesets save is disabled.")
+
+    def load_ontology(self, path):
+        """Load and parse ontologies - currently support OBO files only."""
+        if path is None:
+            path = self.DefaultOnotology
+
+        try:
+            with fsspec.open(path) as f:
+                obo = fastobo.iter(f)
+                terms = filter(lambda stanza: type(stanza) is fastobo.term.TermFrame, obo)
+                names = [tag.name for term in terms for tag in term if type(tag) is fastobo.term.NameClause]
+                self.ontology_data = names
+
+        except FileNotFoundError as e:
+            raise OntologyLoadFailure("Unable to find OBO ontology path") from e
+
+        except SyntaxError as e:
+            raise OntologyLoadFailure("Syntax error loading OBO ontology") from e
+
+        except Exception as e:
+            raise OntologyLoadFailure("Error loading OBO file") from e
+
+    def get_schema(self, data_adaptor):
+        schema = []
+        labels = self.read_labels(data_adaptor)
+        if labels is not None and not labels.empty:
+            for col in labels.columns:
+                col_schema = dict(name=col, writable=True)
+                col_schema.update(get_schema_type_hint_of_array(labels[col]))
+                schema.append(col_schema)
+
+        return schema
+
+    @abstractmethod
+    def set_collection(self, name):
+        """set or create a new annotation collection"""
+        pass
+
+    @abstractmethod
+    def read_labels(self, data_adaptor):
+        """Return the labels as a pandas.DataFrame"""
+        pass
+
+    @abstractmethod
+    def write_labels(self, df, data_adaptor):
+        """Write the labels (df) to a persistent storage such that it can later be read"""
+        pass
+
+    @abstractmethod
+    def read_gene_sets(self, data_adaptor):
+        """Return the genesets from persistent storage """
+        pass
+
+    @abstractmethod
+    def write_gene_sets(self, gs, data_adaptor):
+        """Write the genesets (gs) to a persistent storage such that it can later be read"""
+        pass
+
+    @abstractmethod
+    def update_parameters(self, parameters, data_adaptor):
+        """Update configuration parameters that describe information about the annotations feature"""
+        pass
+
+    Genesets_Header = [
+        "gene_set_name",
+        "gene_set_description",
+        "gene_symbol",
+        "gene_description",
+    ]
+
+    @staticmethod
+    def gene_sets_to_csv(genesets):
+        """
+        Convert the internal genesets format (returned by read_gene_set) into
+        the simple Tidy CSV.
+        """
+        from io import StringIO
+        import csv
+
+        if isinstance(genesets, dict):
+            genesets = genesets.values()
+
+        with StringIO() as sio:
+            writer = csv.writer(sio, dialect='excel')
+            writer.writerow(Annotations.Genesets_Header)
+            for geneset in genesets:
+                # genes may be empty, in which case we skip the geneset entirely
+                genes = geneset["genes"]
+                if not genes:
+                    writer.writerow([geneset["geneset_name"], geneset.get("geneset_description", ""), "", ""])
+                else:
+                    writer.writerows(
+                        [
+                            [
+                                geneset["geneset_name"],
+                                geneset.get("geneset_description", ""),
+                                gene["gene_symbol"],
+                                gene.get("gene_description", ""),
+                            ]
+                            for gene in genes
+                        ]
+                    )
+            return sio.getvalue()
+
+    @staticmethod
+    def gene_sets_to_response(genesets):
+        """
+        Convert the internal genesets format (returned by read_gene_set) into
+        the dict expected by the JSON REST API
+        """
+        return list(genesets.values())

backend/server/common/annotations/local_file_csv.py

@@ -0,0 +1,374 @@
+import base64
+import os
+import re
+import threading
+from datetime import datetime
+from hashlib import blake2b
+import csv
+
+import pandas as pd
+from flask import session, has_request_context, current_app
+
+from backend.server import __version__ as cellxgene_version
+from backend.server.common.annotations.annotations import Annotations
+from backend.common.errors import AnnotationsError, ObsoleteRequest
+
+
+class AnnotationsLocalFile(Annotations):
+    CXG_ANNO_COLLECTION = "cxg_anno_collection"
+
+    def __init__(self, config, output_dir, label_output_file, gene_sets_output_file):
+        super().__init__(config)
+        self.output_dir = output_dir
+        self.label_output_file = label_output_file
+        self.gene_sets_output_file = gene_sets_output_file
+        # lock used to protect label file write ops
+        self.label_lock = threading.RLock()
+        self.gene_sets_lock = threading.RLock()
+
+        # cache the most recent cell labels/annotations.
+        self.last_label_fname = None
+        self.last_labels = None
+
+        # cache the most recent gene sets.
+        self.last_geneset_fname = None
+        self.last_geneset = None
+
+        # txn ID - used to de-dup geneset writes
+        self.last_geneset_tid = 0
+
+    def is_safe_collection_name(self, name):
+        """
+        return true if this is a safe collection name
+        this is ultra conservative. If we want to allow full legal file name syntax,
+        we could look at modules like `pathvalidate`
+        """
+        if name is None:
+            return False
+        return re.match(r"^[\w\-]+$", name) is not None
+
+    def set_collection(self, name):
+        session[self.CXG_ANNO_COLLECTION] = name
+        session.permanent = True
+
+    def get_collection(self):
+        if session is None:
+            return None
+        return session.get(self.CXG_ANNO_COLLECTION)
+
+    def read_labels(self, data_adaptor):
+        self.check_user_annotations_enabled()  # raises
+
+        if has_request_context():
+            if not current_app.auth.is_user_authenticated():
+                return pd.DataFrame()
+
+        fname = self._get_celllabels_filename(data_adaptor)
+        with self.label_lock:
+            if fname is not None and os.path.exists(fname) and os.path.getsize(fname) > 0:
+                # returned the cached labels if possible, otherwise read them from the file
+                if fname == self.last_label_fname:
+                    return self.last_labels
+                else:
+                    labels = pd.read_csv(
+                        fname, dtype="category", index_col=0, header=0, comment="#", keep_default_na=False
+                    )
+                    # update the cache
+                    self.last_label_fname = fname
+                    self.last_labels = labels
+                    return labels
+            else:
+                return pd.DataFrame()
+
+    def write_labels(self, df, data_adaptor):
+        self.check_user_annotations_enabled()  # raises
+
+        # update our internal state and save it.  Multi-threading often enabled,
+        # so treat this as a critical section.
+        with self.label_lock:
+            lastmod = data_adaptor.get_last_mod_time()
+            lastmodstr = "'unknown'" if lastmod is None else lastmod.isoformat(timespec="seconds")
+            header = (
+                f"# Annotations generated on {datetime.now().isoformat(timespec='seconds')} "
+                f"using cellxgene version {cellxgene_version}\n"
+                f"# Input data file was {data_adaptor.get_location()}, "
+                f"which was last modified on {lastmodstr}\n"
+            )
+
+            fname = self._get_celllabels_filename(data_adaptor)
+            self._backup(fname)
+            if not df.empty:
+                with open(fname, "w", newline="") as f:
+                    if header is not None:
+                        f.write(header)
+                    df.to_csv(f)
+            else:
+                open(fname, "w").close()
+
+            # update the cache
+            self.last_label_fname = fname
+            self.last_labels = df
+
+    def read_gene_sets(self, data_adaptor, context=None):
+        if has_request_context():
+            if not current_app.auth.is_user_authenticated():
+                return ({}, self.last_geneset_tid)
+
+        fname = self._get_genesets_filename(data_adaptor)
+        gene_sets = {}
+        tid = None
+        with self.gene_sets_lock:
+            tid = self.last_geneset_tid  # inside the critical section
+            if fname is not None and os.path.exists(fname) and os.path.getsize(fname) > 0:
+                # return the cached genesets if possible, otherwise read from file and validate them
+                if fname == self.last_geneset_fname:
+                    gene_sets = self.last_geneset
+                else:
+                    with open(fname, newline="") as f:
+                        gene_sets = read_gene_set_tidycsv(f, context)
+
+                    # validate
+                    gene_sets = data_adaptor.check_new_gene_sets(gene_sets, context)
+
+                    # update cache
+                    self.last_geneset_fname = fname
+                    self.last_geneset = gene_sets
+
+        return (gene_sets, tid)
+
+    def write_gene_sets(self, gene_sets, tid, data_adaptor):
+        self.check_gene_sets_save_enabled()  # raises
+
+        if type(tid) != int or tid < 0:
+            raise ValueError("tid must be a positive integer")
+
+        # may raise
+        gene_sets = data_adaptor.check_new_gene_sets(gene_sets)
+
+        with self.gene_sets_lock:
+            # skip if the request is stale
+            if tid is not None:
+                if tid <= self.last_geneset_tid:
+                    raise ObsoleteRequest("TID is stale.")
+                self.last_geneset_tid = tid
+
+            lastmod = data_adaptor.get_last_mod_time()
+            lastmodstr = "'unknown'" if lastmod is None else lastmod.isoformat(timespec="seconds")
+            header = (
+                f"# Gene set generated on {datetime.now().isoformat(timespec='seconds')} "
+                f"using cellxgene version {cellxgene_version}\n"
+                f"# Input data file was {data_adaptor.get_location()}, "
+                f"which was last modified on {lastmodstr}\n"
+            )
+
+            fname = self._get_genesets_filename(data_adaptor)
+            self._backup(fname)
+            with open(fname, "w", newline="") as f:
+                f.write(header)
+                f.write(self.gene_sets_to_csv(gene_sets))
+
+            # update the cache
+            self.last_geneset_fname = fname
+            self.last_geneset = gene_sets if type(gene_sets) == dict else {g["geneset_name"]: g for g in gene_sets}
+
+    def _get_userdata_idhash(self, data_adaptor):
+        """
+        Return a short hash that weakly identifies the user and dataset.
+        Used to create safe annotations output file names.
+        """
+        uid = current_app.auth.get_user_id() or ""
+        id = (uid + data_adaptor.get_location()).encode()
+        idhash = base64.b32encode(blake2b(id, digest_size=5).digest()).decode("utf-8")
+        return idhash
+
+    def _get_output_dir(self):
+        if self.output_dir:
+            return self.output_dir
+
+        output_file = self.label_output_file or self.gene_sets_output_file
+        if output_file:
+            return os.path.dirname(os.path.abspath(output_file))
+
+        return os.getcwd()
+
+    def _get_celllabels_filename(self, data_adaptor):
+        """ return the current annotation file name """
+        if self.label_output_file:
+            return self.label_output_file
+
+        return self._get_filename(data_adaptor, "celllabels")
+
+    def _get_genesets_filename(self, data_adaptor):
+        """ return the current gene sets file name """
+        if self.gene_sets_output_file:
+            return self.gene_sets_output_file
+
+        return self._get_filename(data_adaptor, "genesets")
+
+    def _get_filename(self, data_adaptor, anno_name):
+        # we need to generate a file name, which we can only do if we have a UID and collection name
+        if session is None:
+            raise AnnotationsError("unable to determine file name for annotations")
+
+        collection = self.get_collection()
+        if collection is None:
+            return None
+
+        if data_adaptor is None:
+            raise AnnotationsError("unable to determine file name for annotations")
+
+        idhash = self._get_userdata_idhash(data_adaptor)
+        return os.path.join(self._get_output_dir(), f"{collection}-{anno_name}-{idhash}.csv")
+
+    def _backup(self, fname, max_backups=9):
+        """
+        save N backups of file to backup_dir.
+            1. fname -> backup_dir/fname-TIME
+            2. delete excess files in backup_dir
+        """
+        root, ext = os.path.splitext(fname)
+        backup_dir = f"{root}-backups"
+
+        # Make sure there is work to do
+        if not os.path.exists(fname):
+            return
+
+        # Ensure backup_dir exists
+        if not os.path.exists(backup_dir):
+            os.mkdir(backup_dir)
+
+        # Save current file to backup_dir
+        fname_base = os.path.basename(fname)
+        fname_base_root, fname_base_ext = os.path.splitext(fname_base)
+        # don't use ISO standard time format, as it contains characters illegal on some filesytems.
+        nowish = datetime.now().strftime("%Y-%m-%dT%H-%M-%S")
+        backup_fname = os.path.join(backup_dir, f"{fname_base_root}-{nowish}{fname_base_ext}")
+        if os.path.exists(backup_fname):
+            os.remove(backup_fname)
+        os.rename(fname, backup_fname)
+
+        # prune the backup_dir to max number of backup files, keeping the most recent backups
+        backups = list(filter(lambda s: s.startswith(fname_base_root), os.listdir(backup_dir)))
+        excess_count = len(backups) - max_backups
+        if excess_count > 0:
+            backups.sort()
+            for bu in backups[0:excess_count]:
+                os.remove(os.path.join(backup_dir, bu))
+
+    def update_parameters(self, parameters, data_adaptor):
+        params = {}
+        params["annotations"] = self.user_annotations_enabled()
+        params["annotations_genesets_readonly"] = not self.gene_sets_save_enabled()
+        params["user_annotation_collection_name_enabled"] = True
+
+        if self.ontology_data:
+            params["annotations_cell_ontology_enabled"] = True
+            params["annotations_cell_ontology_terms"] = self.ontology_data
+        else:
+            params["annotations_cell_ontology_enabled"] = False
+
+        if self.label_output_file is not None:
+            # user has hard-wired the name of the annotation cell label data collection
+            fname = os.path.basename(self.label_output_file)
+            collection_fname = os.path.splitext(fname)[0]
+            params["annotations-data-collection-is-read-only"] = True
+            params["annotations-data-collection-name"] = collection_fname
+
+        elif session is not None:
+            collection = self.get_collection()
+            params["annotations-data-collection-is-read-only"] = False
+            params["annotations-data-collection-name"] = collection
+
+        if current_app.auth.is_user_authenticated():
+            params["annotations-user-data-idhash"] = self._get_userdata_idhash(data_adaptor)
+
+        parameters.update(params)
+
+
+def read_gene_set_tidycsv(f, context=None):
+    """
+    Read & parse the Tidy CSV format, applying validation checks for mandatory
+    values, and de-duping rules.
+
+    Format is a four-column CSV, with a mandatory header row, and optional "#" prefixed
+    comments.  Format:
+
+        gene_set_name, gene_set_description, gene_symbol, gene_description
+
+    gene_set_name must be non-null; others are optional.
+
+    Returns: a dictionary of the shape (values in angle-brackets vary):
+
+        {
+            <string, a gene set name>: {
+                "geneset_name": <string, a gene set name>,
+                "geneset_description": <a string or None>,
+                "genes": [
+                    {
+                        "gene_symbol": <string, a gene symbol or name>,
+                        "gene_description": <a string or None>
+                    },
+                    ...
+                ]
+            },
+            ...
+        }
+    """
+
+    class myDialect(csv.excel):
+        skipinitialspace = True
+
+    def just(n, seq):
+        it = iter(seq)
+        for _ in range(n - 1):
+            yield next(it, "")
+        yield tuple(it)
+
+    messagefn = context["messagefn"] if context else (lambda x: None)
+
+    reader = csv.reader(f, dialect=myDialect())
+    gene_sets = {}
+    haveReadHeader = False
+    lineno = 0
+    for row in reader:
+        lineno += 1
+        # ignore empty rows
+        if len(row) == 0:
+            continue
+        # if row starts with '#' it is a comment
+        if row[0].startswith("#"):
+            continue
+        # if this is the first non-comment row, assume it is a header
+        if not haveReadHeader:
+            if row != Annotations.Genesets_Header:
+                raise AnnotationsError("Geneset CSV file missing the required column header.")
+            haveReadHeader = True
+            continue
+
+        geneset_name, geneset_description, gene_symbol, gene_description, _ = just(5, row)
+        if not geneset_name:
+            raise AnnotationsError(f"Geneset CSV missing required geneset or gene name on line {lineno}")
+        if (not gene_symbol) and gene_description:
+            messagefn(f"Warning: Missing gene name in geneset name {geneset_name} on line {lineno}.")
+
+        if geneset_name in gene_sets:
+            gs = gene_sets[geneset_name]
+        else:
+            gs = gene_sets[geneset_name] = {
+                "geneset_name": geneset_name,
+                "geneset_description": geneset_description,
+                "genes": [],
+            }
+        # Use first geneset_description with a value
+        if not gs["geneset_description"] and geneset_description:
+            gs["geneset_description"] = geneset_description
+        # add the gene if the gene_symbol is defined
+        if gene_symbol:
+            gs["genes"].append(
+                {
+                    "gene_symbol": gene_symbol,
+                    "gene_description": gene_description,
+                }
+            )
+
+    return gene_sets

backend/server/common/config/__init__.py

@@ -0,0 +1,4 @@
+from backend.common.utils.aws_secret_utils import get_secret_key  # noqa F504
+
+DEFAULT_SERVER_PORT = 5005
+BIG_FILE_SIZE_THRESHOLD = 100 * 2 ** 20  # 100MB

backend/server/common/config/app_config.py

@@ -0,0 +1,171 @@
+import yaml
+from flatten_dict import unflatten
+
+from backend.server.default_config import get_default_config
+from backend.server.common.config.dataset_config import DatasetConfig
+from backend.server.common.config.server_config import ServerConfig
+from backend.server.common.config.external_config import ExternalConfig
+from backend.common.errors import ConfigurationError
+
+
+class AppConfig(object):
+    """
+    AppConfig stores all the configuration for cellxgene.
+    AppConfig contains one or more DatasetConfig(s) and one ServerConfig.
+    The server_config contains attributes that refer to the server process as a whole.
+    The dataset_config refers to attributes that are associated with the features and
+    presentations of a dataset.
+    AppConfig has methods to initialize, modify, and access the configuration.
+    """
+
+    def __init__(self):
+
+        # the default configuration (see default_config.py)
+        # TODO @madison -- if we always read from the default config (hard coded path) can we set those values as
+        #  defaults within the config class?
+        self.default_config = get_default_config()
+        # the server configuration
+        self.server_config = ServerConfig(self, self.default_config["server"])
+        # the dataset config
+        self.dataset_config = DatasetConfig(None, self, self.default_config["dataset"])
+        #  external config
+        self.external_config = ExternalConfig(self, self.default_config["external"])
+
+        # Set to true when config_completed is called
+        self.is_completed = False
+
+    def get_dataset_config(self):
+        return self.dataset_config
+
+    def check_config(self):
+        """Verify all the attributes in the config have been type checked"""
+        if not self.is_completed:
+            raise ConfigurationError("The configuration has not been completed")
+        self.server_config.check_config()
+        self.dataset_config.check_config()
+        self.external_config.check_config()
+
+    def update_server_config(self, **kw):
+        self.server_config.update(**kw)
+        self.is_complete = False
+
+    def update_dataset_config(self, **kw):
+        self.dataset_config.update(**kw)
+        self.is_complete = False
+
+    def update_single_config_from_path_and_value(self, path, value):
+        """Update a single config parameter with the value.
+        Path is a list of string, that gives a path to the config parameter to be updated.
+        For example, path may be ["server","app","port"].
+        """
+        self.is_complete = False
+        if not isinstance(path, list):
+            raise ConfigurationError(f"path must be a list of strings, got '{str(path)}'")
+        for part in path:
+            if not isinstance(part, str):
+                raise ConfigurationError(f"path must be a list of strings, got '{str(path)}'")
+
+        if len(path) < 1 or path[0] not in ("server", "dataset"):
+            raise ConfigurationError("path must start with 'server', or 'dataset'")
+
+        if path[0] == "server":
+            attr = "__".join(path[1:])
+            try:
+                self.update_server_config(**{attr: value})
+            except ConfigurationError:
+                raise ConfigurationError(f"unknown config parameter at path: '{str(path)}'")
+        elif path[0] == "dataset":
+            attr = "__".join(path[1:])
+            try:
+                self.update_dataset_config(**{attr: value})
+            except ConfigurationError:
+                raise ConfigurationError(f"unknown config parameter at path: '{str(path)}'")
+
+    def update_from_config_file(self, config_file):
+        try:
+            with open(config_file) as yml_file:
+                config = yaml.safe_load(yml_file)
+        except yaml.YAMLError as e:
+            raise ConfigurationError(f"The specified config file contained an error: {e}")
+        except OSError as e:
+            raise ConfigurationError(f"Issue retrieving the specified config file: {e}")
+
+        if config.get("server"):
+            self.server_config.update_from_config(config["server"], "server")
+        if config.get("dataset"):
+            self.dataset_config.update_from_config(config["dataset"], "dataset")
+
+        if config.get("external"):
+            self.external_config.update_from_config(config["external"], "external")
+
+        self.is_complete = False
+
+    def config_to_dict(self):
+        """return the configuration as an unflattened dict"""
+        server = self.server_config.create_mapping(self.server_config.default_config)
+        dataset = self.dataset_config.create_mapping(self.dataset_config.default_config)
+        external = self.external_config.create_mapping(self.external_config.default_config)
+        config = dict(server={}, dataset={})
+        for attrname in server.keys():
+            config["server__" + attrname] = getattr(self.server_config, attrname)
+        for attrname in dataset.keys():
+            config["dataset__" + attrname] = getattr(self.dataset_config, attrname)
+        for attrname in external.keys():
+            config["external__" + attrname] = getattr(self.external_config, attrname)
+
+        config = unflatten(config, splitter=lambda key: key.split("__"))
+        return config
+
+    def write_config(self, config_file):
+        """output the config to a yaml file"""
+        config = self.config_to_dict()
+        yaml.dump(config, open(config_file, "w"))
+
+    def changes_from_default(self):
+        """Return all the attribute that are different from the default"""
+        diff_server = self.server_config.changes_from_default()
+        diff_dataset = self.dataset_config.changes_from_default()
+        diff_external = self.external.changes_from_default()
+        diff = dict(server=diff_server, dataset=diff_dataset, external=diff_external)
+        return diff
+
+    def complete_config(self, messagefn=None):
+        """The configure options are checked, and any additional setup based on the config
+        parameters is done"""
+
+        if messagefn is None:
+
+            def noop(message):
+                pass
+
+            messagefn = noop
+
+        # TODO: to give better error messages we can add a mapping between where each config
+        # attribute originated (e.g. command line argument or config file), then in the error
+        # messages we can give correct context for attributes with bad value.
+        context = dict(messagefn=messagefn)
+
+        # complete config for external_config first, since this may update values in the other sections
+        self.external_config.complete_config(context)
+        self.server_config.complete_config(context)
+        self.dataset_config.complete_config(context)
+
+        self.is_completed = True
+        self.check_config()
+
+    def get_matrix_data_cache_manager(self):
+        return self.server_config.matrix_data_cache_manager
+
+    def get_title(self, data_adaptor):
+        return (
+            self.server_config.single_dataset__title
+            if self.server_config.single_dataset__title
+            else data_adaptor.get_title()
+        )
+
+    def get_about(self, data_adaptor):
+        return (
+            self.server_config.single_dataset__about
+            if self.server_config.single_dataset__about
+            else data_adaptor.get_about()
+        )

backend/server/common/config/base_config.py

@@ -0,0 +1,99 @@
+import copy
+
+from flatten_dict import flatten
+from backend.common.errors import ConfigurationError
+
+
+class BaseConfig(object):
+    """
+    This class handles the mechanics of updating and checking attributes.
+    Derived classes are expected to store the actual attributes
+    Currently DatasetConfig and ServerConfig both inherit from BaseConfig.
+    """
+
+    def __init__(self, app_config, default_config):
+        # reference back to the app_config
+        self.app_config = app_config
+        # the complete set of attributes and their default values (unflattened)
+        self.default_config = default_config
+        # used to make sure every attribute value is checked
+        self.attr_checked = {key_name: False for key_name in self.create_mapping(default_config).keys()}
+
+    def create_mapping(self, config):
+        """
+        Create a dictionary where the keys are the name of attributes (using double underscore convention)
+        For example: authentication__type
+
+        The values are a tuple,
+        - the first item of the tuple is a tuple of path elements (location in config 'tree')
+        - the second item is the value of the config parameter
+
+        For example: (('authentication', 'type'), 'session'))
+        """
+        config_copy = copy.deepcopy(config)
+        mapping = {}
+
+        flat_config = flatten(config_copy)
+        for key, value in flat_config.items():
+            # name of the attribute
+            attr = "__".join(key)
+            mapping[attr] = (key, value)
+
+        return mapping
+
+    def validate_correct_type_of_configuration_attribute(self, attrname, vtype):
+        val = getattr(self, attrname)
+        if type(vtype) in (list, tuple):
+            if type(val) not in vtype:
+                tnames = ",".join([x.__name__ for x in vtype])
+                raise ConfigurationError(
+                    f"Invalid type for attribute: {attrname}, expected types ({tnames}), got {type(val).__name__}"
+                )
+        else:
+            if type(val) != vtype:
+                raise ConfigurationError(
+                    f"Invalid type for attribute: {attrname}, "
+                    f"expected type {vtype.__name__}, got {type(val).__name__}"
+                )
+
+        self.attr_checked[attrname] = True
+
+    def check_config(self):
+        mapping = self.create_mapping(self.default_config)
+        for key in mapping.keys():
+            if not self.attr_checked[key]:
+                raise ConfigurationError(f"The attr '{key}' has not been checked")
+
+    def update(self, **kw):
+        """Update the attributes defined in kw with their new values."""
+        for key, value in kw.items():
+            if not hasattr(self, key):
+                raise ConfigurationError(f"unknown config parameter {key}.")
+            try:
+                if type(value) == tuple:
+                    # convert tuple values to list values
+                    value = list(value)
+                setattr(self, key, value)
+            except KeyError:
+                raise ConfigurationError(f"Unable to set config parameter {key}.")
+
+            self.attr_checked[key] = False
+
+    def update_from_config(self, config, prefix):
+        mapping = self.create_mapping(config)
+        for attr, (key, value) in mapping.items():
+            if not hasattr(self, attr):
+                raise ConfigurationError(f"Unknown key from config file: {prefix}__{attr}")
+            setattr(self, attr, value)
+
+            self.attr_checked[attr] = False
+
+    def changes_from_default(self):
+        """Return all the attribute that are different from the default"""
+        mapping = self.create_mapping(self.default_config)
+        diff = []
+        for attrname, (key, defval) in mapping.items():
+            curval = getattr(self, attrname)
+            if curval != defval:
+                diff.append((attrname, curval, defval))
+        return diff

backend/server/common/config/client_config.py

@@ -0,0 +1,123 @@
+from backend.server import display_version as cellxgene_display_version
+
+
+def get_client_config(app_config, data_adaptor):
+    """
+    Return the configuration as required by the /config REST route
+    """
+
+    server_config = app_config.server_config
+    dataset_config = data_adaptor.dataset_config
+    annotation = dataset_config.user_annotations
+    auth = server_config.auth
+
+    # FIXME The current set of config is not consistently presented:
+    # we have camalCase, hyphen-text, and underscore_text
+
+    # make sure the configuration has been checked.
+    app_config.check_config()
+
+    # display_names
+    title = app_config.get_title(data_adaptor)
+    about = app_config.get_about(data_adaptor)
+
+    display_names = dict(engine=data_adaptor.get_name(), dataset=title)
+
+    # library_versions
+    library_versions = {}
+    library_versions.update(data_adaptor.get_library_versions())
+    library_versions["cellxgene"] = cellxgene_display_version
+
+    # links
+    links = {"about-dataset": about}
+
+    # parameters
+    parameters = {
+        "layout": dataset_config.embeddings__names,
+        "max-category-items": dataset_config.presentation__max_categories,
+        "obs_names": server_config.single_dataset__obs_names,
+        "var_names": server_config.single_dataset__var_names,
+        "diffexp_lfc_cutoff": dataset_config.diffexp__lfc_cutoff,
+        "backed": server_config.adaptor__anndata_adaptor__backed,
+        "disable-diffexp": not dataset_config.diffexp__enable,
+        "enable-reembedding": dataset_config.embeddings__enable_reembedding,
+        "annotations": False,
+        "annotations_file": None,
+        "annotations_dir": None,
+        "annotations_genesets": True,  # feature flag
+        "annotations_genesets_readonly": dataset_config.user_annotations__gene_sets__readonly,
+        "annotations_genesets_summary_methods": ["mean"],
+        "annotations_cell_ontology_enabled": False,
+        "annotations_cell_ontology_obopath": None,
+        "annotations_cell_ontology_terms": None,
+        "custom_colors": dataset_config.presentation__custom_colors,
+        "diffexp-may-be-slow": False,
+    }
+
+    # corpora dataset_props
+    # TODO/Note: putting info from the dataset into the /config is not ideal.
+    # However, it is definitely not part of /schema, and we do not have a top-level
+    # route for data properties.  Consider creating one at some point.
+    corpora_props = data_adaptor.get_corpora_props()
+    if corpora_props and "default_embedding" in corpora_props:
+        default_embedding = corpora_props["default_embedding"]
+        if isinstance(default_embedding, str) and default_embedding.startswith("X_"):
+            default_embedding = default_embedding[2:]  # drop X_ prefix
+        if default_embedding in data_adaptor.get_embedding_names():
+            parameters["default_embedding"] = default_embedding
+
+    data_adaptor.update_parameters(parameters)
+    if annotation:
+        annotation.update_parameters(parameters, data_adaptor)
+
+    # gather it all together
+    client_config = {}
+    config = client_config["config"] = {}
+    config["displayNames"] = display_names
+    config["library_versions"] = library_versions
+    config["links"] = links
+    config["parameters"] = parameters
+    config["corpora_props"] = corpora_props
+    config["limits"] = {
+        "column_request_max": server_config.limits__column_request_max,
+        "diffexp_cellcount_max": server_config.limits__diffexp_cellcount_max,
+    }
+
+    if dataset_config.app__authentication_enable and auth.is_valid_authentication_type():
+        config["authentication"] = {
+            "requires_client_login": auth.requires_client_login(),
+        }
+        if auth.requires_client_login():
+            config["authentication"].update(
+                {
+                    # Todo why are these stored on the data_adaptor?
+                    "login": auth.get_login_url(data_adaptor),
+                    "logout": auth.get_logout_url(data_adaptor),
+                }
+            )
+
+    return client_config
+
+
+def get_client_userinfo(app_config, data_adaptor):
+    """
+    Return the userinfo as required by the /userinfo REST route
+    """
+
+    server_config = app_config.server_config
+    dataset_config = data_adaptor.dataset_config
+    auth = server_config.auth
+
+    # make sure the configuration has been checked.
+    app_config.check_config()
+
+    if dataset_config.app__authentication_enable and auth.is_valid_authentication_type():
+        userinfo = {}
+        userinfo["userinfo"] = {
+            "is_authenticated": auth.is_user_authenticated(),
+            "username": auth.get_user_name(),
+            "user_id": auth.get_user_id(),
+            "email": auth.get_user_email(),
+            "picture": auth.get_user_picture(),
+        }
+        return userinfo

backend/server/common/config/dataset_config.py

@@ -0,0 +1,222 @@
+import os
+from os.path import splitext, isdir
+
+from backend.server.common.annotations.local_file_csv import AnnotationsLocalFile
+from backend.server.common.config.base_config import BaseConfig
+from backend.common.errors import ConfigurationError, OntologyLoadFailure, AnnotationsError
+from backend.server.compute.scanpy import get_scanpy_module
+from backend.server.data_common.matrix_loader import MatrixDataLoader
+
+
+class DatasetConfig(BaseConfig):
+    """Manages the config attribute associated with a dataset."""
+
+    def __init__(self, tag, app_config, default_config):
+        super().__init__(app_config, default_config)
+        self.tag = tag
+        try:
+            self.app__scripts = default_config["app"]["scripts"]
+            self.app__inline_scripts = default_config["app"]["inline_scripts"]
+            self.app__authentication_enable = default_config["app"]["authentication_enable"]
+
+            self.presentation__max_categories = default_config["presentation"]["max_categories"]
+            self.presentation__custom_colors = default_config["presentation"]["custom_colors"]
+
+            self.user_annotations__enable = default_config["user_annotations"]["enable"]
+            self.user_annotations__type = default_config["user_annotations"]["type"]
+            self.user_annotations__local_file_csv__directory = default_config["user_annotations"]["local_file_csv"][
+                "directory"
+            ]
+            self.user_annotations__local_file_csv__file = default_config["user_annotations"]["local_file_csv"]["file"]
+            self.user_annotations__ontology__enable = default_config["user_annotations"]["ontology"]["enable"]
+            self.user_annotations__ontology__obo_location = default_config["user_annotations"]["ontology"][
+                "obo_location"
+            ]
+            self.user_annotations__gene_sets__readonly = default_config["user_annotations"]["gene_sets"]["readonly"]
+            self.user_annotations__local_file_csv__gene_sets_file = default_config["user_annotations"][
+                "local_file_csv"
+            ]["gene_sets_file"]
+
+            self.embeddings__names = default_config["embeddings"]["names"]
+            self.embeddings__enable_reembedding = default_config["embeddings"]["enable_reembedding"]
+
+            self.diffexp__enable = default_config["diffexp"]["enable"]
+            self.diffexp__lfc_cutoff = default_config["diffexp"]["lfc_cutoff"]
+            self.diffexp__top_n = default_config["diffexp"]["top_n"]
+
+        except KeyError as e:
+            raise ConfigurationError(f"Unexpected config: {str(e)}")
+
+        # The annotation object is created during complete_config and stored here.
+        self.user_annotations = None
+
+    def complete_config(self, context):
+        self.handle_app()
+        self.handle_presentation()
+        self.handle_user_annotations(context)
+        self.handle_embeddings()
+        self.handle_diffexp(context)
+
+    def get_data_adaptor(self):
+        server_config = self.app_config.server_config
+        if not server_config.data_adaptor:
+            matrix_data_loader = MatrixDataLoader(server_config.single_dataset__datapath, app_config=self.app_config)
+            server_config.data_adaptor = matrix_data_loader.open(self.app_config)
+
+        return server_config.data_adaptor
+
+    def handle_app(self):
+        self.validate_correct_type_of_configuration_attribute("app__scripts", list)
+        self.validate_correct_type_of_configuration_attribute("app__inline_scripts", list)
+        self.validate_correct_type_of_configuration_attribute("app__authentication_enable", bool)
+
+        # scripts can be string (filename) or dict (attributes). Convert string to dict.
+        scripts = []
+        for script in self.app__scripts:
+            try:
+                if isinstance(script, str):
+                    scripts.append({"src": script})
+                elif isinstance(script, dict) and isinstance(script["src"], str):
+                    scripts.append(script)
+                else:
+                    raise Exception
+            except Exception as e:
+                raise ConfigurationError(f"Scripts must be string or a dict containing an src key: {e}")
+
+        self.app__scripts = scripts
+
+    def handle_presentation(self):
+        self.validate_correct_type_of_configuration_attribute("presentation__max_categories", int)
+        self.validate_correct_type_of_configuration_attribute("presentation__custom_colors", bool)
+
+    def handle_user_annotations(self, context):
+        self.validate_correct_type_of_configuration_attribute("user_annotations__enable", bool)
+        self.validate_correct_type_of_configuration_attribute("user_annotations__type", str)
+        self.validate_correct_type_of_configuration_attribute(
+            "user_annotations__local_file_csv__directory", (type(None), str)
+        )
+        self.validate_correct_type_of_configuration_attribute(
+            "user_annotations__local_file_csv__file", (type(None), str)
+        )
+        self.validate_correct_type_of_configuration_attribute(
+            "user_annotations__local_file_csv__gene_sets_file", (type(None), str)
+        )
+        self.validate_correct_type_of_configuration_attribute("user_annotations__ontology__enable", bool)
+        self.validate_correct_type_of_configuration_attribute(
+            "user_annotations__ontology__obo_location", (type(None), str)
+        )
+        self.validate_correct_type_of_configuration_attribute("user_annotations__gene_sets__readonly", bool)
+
+        if self.user_annotations__enable or not self.user_annotations__gene_sets__readonly:
+            server_config = self.app_config.server_config
+            if not self.app__authentication_enable:
+                raise ConfigurationError("user annotations requires authentication to be enabled")
+            if not server_config.auth.is_valid_authentication_type():
+                auth_type = server_config.authentication__type
+                raise ConfigurationError(f"authentication method {auth_type} is not compatible with user annotations")
+
+        # Must always have an annotations instance to support genesets. User annotation (cell labels) are optional
+        # as are writable gene sets
+        if self.user_annotations__type == "local_file_csv":
+            self.handle_local_file_csv_annotations(context)
+        else:
+            raise ConfigurationError('The only annotation type support is "local_file_csv"')
+
+        if self.user_annotations__enable:
+            if self.user_annotations__ontology__enable or self.user_annotations__ontology__obo_location:
+                try:
+                    self.user_annotations.load_ontology(self.user_annotations__ontology__obo_location)
+                except OntologyLoadFailure as e:
+                    raise ConfigurationError("Unable to load ontology terms\n" + str(e))
+
+        self.check_annotation_config_vars_not_set(context)
+
+    def handle_local_file_csv_annotations(self, context):
+        dirname = self.user_annotations__local_file_csv__directory
+        filename = self.user_annotations__local_file_csv__file
+        genesets_filename = self.user_annotations__local_file_csv__gene_sets_file
+
+        if dirname is not None and (filename is not None or genesets_filename is not None):
+            raise ConfigurationError(
+                "'user-generated-data-dir' may not be used with annotations-file' or 'genesets-file'."
+            )
+
+        if filename is not None:
+            lf_name, lf_ext = splitext(filename)
+            if lf_ext and lf_ext != ".csv":
+                raise ConfigurationError(f"annotation file type must be .csv: {filename}")
+
+        if genesets_filename is not None:
+            lf_name, lf_ext = splitext(genesets_filename)
+            if lf_ext and lf_ext != ".csv":
+                raise ConfigurationError(f"genesets file type must be .csv: {genesets_filename}")
+
+        if dirname is not None and not isdir(dirname):
+            try:
+                os.mkdir(dirname)
+            except OSError:
+                raise ConfigurationError("Unable to create directory specified by --user-generated-data-dir")
+
+        anno_config = {
+            "user-annotations": self.user_annotations__enable,
+            "genesets-save": not self.user_annotations__gene_sets__readonly,
+        }
+        self.user_annotations = AnnotationsLocalFile(anno_config, dirname, filename, genesets_filename)
+
+        # if the user has specified a fixed label file, go ahead and validate it
+        # so that we can remove errors early in the process.
+        server_config = self.app_config.server_config
+        if server_config.single_dataset__datapath:
+            data_adaptor = self.get_data_adaptor()
+            if self.user_annotations__local_file_csv__file:
+                self.user_annotations.read_labels(data_adaptor)
+            if self.user_annotations__local_file_csv__gene_sets_file:
+                try:
+                    self.user_annotations.read_gene_sets(data_adaptor, context)
+                except (ValueError, AnnotationsError, KeyError) as e:
+                    raise ConfigurationError(f"Unable to read genesets CSV file: {str(e)}") from e
+
+    def check_annotation_config_vars_not_set(self, context):
+        if self.user_annotations__type is not None:
+            dirname = self.user_annotations__local_file_csv__directory
+            filename = self.user_annotations__local_file_csv__file
+            if not self.user_annotations__enable:
+                if filename is not None:
+                    context["messagefn"]("Warning: --annotations-file ignored as annotations are disabled.")
+                if self.user_annotations__ontology__enable:
+                    context["messagefn"](
+                        "Warning: --experimental-annotations-ontology ignored as annotations are disabled."
+                    )
+                if self.user_annotations__ontology__obo_location is not None:
+                    context["messagefn"](
+                        "Warning: --experimental-annotations-ontology-obo ignored as annotations are disabled."
+                    )
+                if dirname is not None:
+                    context["messagefn"]("Warning: --user-generated-data-dir ignored as annotations are disabled.")
+
+    def handle_embeddings(self):
+        self.validate_correct_type_of_configuration_attribute("embeddings__names", list)
+        self.validate_correct_type_of_configuration_attribute("embeddings__enable_reembedding", bool)
+
+        server_config = self.app_config.server_config
+        if self.embeddings__enable_reembedding:
+            if server_config.single_dataset__datapath:
+                if server_config.adaptor__anndata_adaptor__backed:
+                    raise ConfigurationError("enable-reembedding is not supported when run in --backed mode.")
+
+            try:
+                get_scanpy_module()
+            except NotImplementedError:
+                # Todo add scanpy to requirements.txt and remove this check once re-embeddings is fully supported
+                raise ConfigurationError("Please install scanpy to enable UMAP re-embedding")
+
+    def handle_diffexp(self, context):
+        self.validate_correct_type_of_configuration_attribute("diffexp__enable", bool)
+        self.validate_correct_type_of_configuration_attribute("diffexp__lfc_cutoff", float)
+        self.validate_correct_type_of_configuration_attribute("diffexp__top_n", int)
+
+        data_adaptor = self.get_data_adaptor()
+        if self.diffexp__enable and data_adaptor.parameters.get("diffexp_may_be_slow", False):
+            context["messagefn"](
+                "CAUTION: due to the size of your dataset, " "running differential expression may take longer or fail."
+            )

backend/server/common/config/external_config.py

@@ -0,0 +1,96 @@
+import os
+
+from backend.server.common.config.base_config import BaseConfig
+from backend.common.errors import ConfigurationError
+from backend.server.common.config import get_secret_key
+from backend.common.errors import SecretKeyRetrievalError
+from backend.common.utils.type_conversion_utils import convert_string_to_value
+
+
+class ExternalConfig(BaseConfig):
+    """Manages the config attribute associated with external configuration sources, such as
+    environment variables or the AWS Secrets Manager."""
+
+    def __init__(self, app_config, default_config):
+        super().__init__(app_config, default_config)
+        try:
+            self.environment = default_config["environment"]
+            self.aws_secrets_manager__region = default_config["aws_secrets_manager"]["region"]
+            self.aws_secrets_manager__secrets = default_config["aws_secrets_manager"]["secrets"]
+
+        except KeyError as e:
+            raise ConfigurationError(f"Unexpected config: {str(e)}")
+
+    def complete_config(self, context):
+        self.handle_environment(context)
+        self.handle_aws_secrets_manager(context)
+
+    def handle_environment(self, context):
+        """For each environment variable defined, get the value (if it is set),
+        and set the specified config parameter"""
+        self.validate_correct_type_of_configuration_attribute("environment", list)
+        for envdict in self.environment:
+            name = envdict.get("name")
+            if name is None:
+                raise ConfigurationError("environment: 'name' is missing")
+            required = envdict.get("required", False)
+            if type(required) != bool:
+                raise ConfigurationError("environment: 'required' must be a bool")
+            path = envdict.get("path")
+            if path is None:
+                raise ConfigurationError("environment: 'path' is missing")
+
+            value = os.environ.get(name)
+            if value is None:
+                if required:
+                    raise ConfigurationError(f"required environment variable '{name}' not set")
+            else:
+                value = convert_string_to_value(value)
+                self.app_config.update_single_config_from_path_and_value(path, value)
+
+    def handle_aws_secrets_manager(self, context):
+        """For each aws secret defined, get the key/values, and set the specified config parameter"""
+        self.validate_correct_type_of_configuration_attribute("aws_secrets_manager__region", (type(None), str))
+        self.validate_correct_type_of_configuration_attribute("aws_secrets_manager__secrets", list)
+
+        if not self.aws_secrets_manager__secrets:
+            return
+
+        self.validate_correct_type_of_configuration_attribute("aws_secrets_manager__region", str)
+
+        for secret in self.aws_secrets_manager__secrets:
+            secret_name = secret.get("name")
+            if secret_name is None:
+                raise ConfigurationError("aws_secrets_manager: 'name' is missing")
+            if not isinstance(secret_name, str):
+                raise ConfigurationError("aws_secrets_manager: 'name' must be a string")
+
+            try:
+                secret_dict = get_secret_key(self.aws_secrets_manager__region, secret_name)
+            except SecretKeyRetrievalError as e:
+                raise ConfigurationError(f"Unable to retrieve secret {secret_name}: {str(e)}")
+
+            values = secret.get("values")
+            if values is None:
+                raise ConfigurationError("aws_secrets_manager: 'values' is missing")
+            if not isinstance(values, list):
+                raise ConfigurationError("aws_secrets_manager: 'values' must be a list")
+
+            for value in values:
+                key = value.get("key")
+                if key is None:
+                    raise ConfigurationError(f"missing 'key' in secret values: {secret_name}")
+                path = value.get("path")
+                if path is None:
+                    raise ConfigurationError(f"missing 'path' in secret values: {secret_name}")
+                required = value.get("required", False)
+                if type(required) != bool:
+                    raise ConfigurationError(f"wrong type for 'required' in secret values: {secret_name}")
+
+                secret_value = secret_dict.get(key)
+                if secret_value is None:
+                    if required:
+                        raise ConfigurationError(f"required secret '{secret_name}:{key}' not set")
+                else:
+                    secret_value = convert_string_to_value(secret_value)
+                    self.app_config.update_single_config_from_path_and_value(path, secret_value)

backend/server/common/config/server_config.py

@@ -0,0 +1,183 @@
+import os
+import sys
+import warnings
+from os.path import basename
+from urllib.parse import urlparse
+
+from backend.server.auth.auth import AuthTypeFactory
+from backend.server.common.config.base_config import BaseConfig
+from backend.server.common.config import DEFAULT_SERVER_PORT, BIG_FILE_SIZE_THRESHOLD
+from backend.common.utils.data_locator import discover_s3_region_name
+from backend.common.errors import ConfigurationError, DatasetAccessError
+from backend.common.utils.utils import is_port_available, find_available_port, custom_format_warning
+from backend.server.data_common.matrix_loader import MatrixDataLoader
+
+
+class ServerConfig(BaseConfig):
+    """Manages the config attribute associated with the server."""
+
+    def __init__(self, app_config, default_config):
+        super().__init__(app_config, default_config)
+
+        try:
+            self.app__verbose = default_config["app"]["verbose"]
+            self.app__debug = default_config["app"]["debug"]
+            self.app__host = default_config["app"]["host"]
+            self.app__port = default_config["app"]["port"]
+            self.app__open_browser = default_config["app"]["open_browser"]
+            self.app__force_https = default_config["app"]["force_https"]
+            self.app__flask_secret_key = default_config["app"]["flask_secret_key"]
+
+            self.authentication__type = default_config["authentication"]["type"]
+            self.authentication__insecure_test_environment = default_config["authentication"][
+                "insecure_test_environment"
+            ]
+
+            self.single_dataset__datapath = default_config["single_dataset"]["datapath"]
+            self.single_dataset__obs_names = default_config["single_dataset"]["obs_names"]
+            self.single_dataset__var_names = default_config["single_dataset"]["var_names"]
+            self.single_dataset__about = default_config["single_dataset"]["about"]
+            self.single_dataset__title = default_config["single_dataset"]["title"]
+
+            self.data_locator__s3__region_name = default_config["data_locator"]["s3"]["region_name"]
+
+            self.adaptor__anndata_adaptor__backed = default_config["adaptor"]["anndata_adaptor"]["backed"]
+
+            self.limits__diffexp_cellcount_max = default_config["limits"]["diffexp_cellcount_max"]
+            self.limits__column_request_max = default_config["limits"]["column_request_max"]
+
+        except KeyError as e:
+            raise ConfigurationError(f"Unexpected config: {str(e)}")
+
+        self.data_adaptor = None
+
+        # The authentication object
+        self.auth = None
+
+    def complete_config(self, context):
+        self.handle_app(context)
+        self.handle_data_source()
+        self.handle_authentication()
+        self.handle_data_locator()
+        self.handle_adaptor()  # may depend on data_locator
+        self.handle_single_dataset(context)  # may depend on adaptor
+        self.handle_limits()
+
+        self.check_config()
+
+    def handle_app(self, context):
+        self.validate_correct_type_of_configuration_attribute("app__verbose", bool)
+        self.validate_correct_type_of_configuration_attribute("app__debug", bool)
+        self.validate_correct_type_of_configuration_attribute("app__host", str)
+        self.validate_correct_type_of_configuration_attribute("app__port", (type(None), int))
+        self.validate_correct_type_of_configuration_attribute("app__open_browser", bool)
+        self.validate_correct_type_of_configuration_attribute("app__force_https", bool)
+        self.validate_correct_type_of_configuration_attribute("app__flask_secret_key", str)
+
+        if self.app__port:
+            try:
+                if not is_port_available(self.app__host, self.app__port):
+                    raise ConfigurationError(
+                        f"The port selected {self.app__port} is in use, please configure an open port."
+                    )
+            except OverflowError:
+                raise ConfigurationError(f"Invalid port: {self.app__port}")
+        else:
+            try:
+                default_server_port = int(os.environ.get("CXG_SERVER_PORT", DEFAULT_SERVER_PORT))
+            except ValueError:
+                raise ConfigurationError(
+                    "Invalid port from environment variable CXG_SERVER_PORT: " + os.environ.get("CXG_SERVER_PORT")
+                )
+            try:
+                self.app__port = find_available_port(self.app__host, default_server_port)
+            except OverflowError:
+                raise ConfigurationError(f"Invalid port: {default_server_port}")
+
+        if self.app__debug:
+            context["messagefn"]("in debug mode, setting verbose=True and open_browser=False")
+            self.app__verbose = True
+            self.app__open_browser = False
+        else:
+            warnings.formatwarning = custom_format_warning
+
+        if not self.app__verbose:
+            sys.tracebacklimit = 0
+
+    def handle_authentication(self):
+        self.validate_correct_type_of_configuration_attribute("authentication__type", (type(None), str))
+        self.validate_correct_type_of_configuration_attribute("authentication__insecure_test_environment", bool)
+
+        if self.authentication__type == "test" and not self.authentication__insecure_test_environment:
+            raise ConfigurationError("Test auth can only be used in an insecure test environment")
+
+        self.auth = AuthTypeFactory.create(self.authentication__type, self)
+        if self.auth is None:
+            raise ConfigurationError(f"Unknown authentication type: {self.authentication__type}")
+
+    def handle_data_locator(self):
+        self.validate_correct_type_of_configuration_attribute("data_locator__s3__region_name", (type(None), bool, str))
+        if self.data_locator__s3__region_name is True:
+            path = self.single_dataset__datapath
+
+            if path.startswith("s3://"):
+                region_name = discover_s3_region_name(path)
+                if region_name is None:
+                    raise ConfigurationError(f"Unable to discover s3 region name from {path}")
+            else:
+                region_name = None
+            self.data_locator__s3__region_name = region_name
+
+    def handle_data_source(self):
+        self.validate_correct_type_of_configuration_attribute("single_dataset__datapath", str)
+
+    def handle_single_dataset(self, context):
+        self.validate_correct_type_of_configuration_attribute("single_dataset__datapath", (str, type(None)))
+        self.validate_correct_type_of_configuration_attribute("single_dataset__title", (str, type(None)))
+        self.validate_correct_type_of_configuration_attribute("single_dataset__about", (str, type(None)))
+        self.validate_correct_type_of_configuration_attribute("single_dataset__obs_names", (str, type(None)))
+        self.validate_correct_type_of_configuration_attribute("single_dataset__var_names", (str, type(None)))
+
+        # preload this data set
+        matrix_data_loader = MatrixDataLoader(self.single_dataset__datapath, app_config=self.app_config)
+        try:
+            matrix_data_loader.pre_load_validation()
+        except DatasetAccessError as e:
+            raise ConfigurationError(str(e))
+
+        file_size = matrix_data_loader.file_size()
+        file_basename = basename(self.single_dataset__datapath)
+        if file_size > BIG_FILE_SIZE_THRESHOLD:
+            context["messagefn"](f"Loading data from {file_basename}, this may take a while...")
+        else:
+            context["messagefn"](f"Loading data from {file_basename}.")
+
+        if self.single_dataset__about:
+
+            def url_check(url):
+                try:
+                    result = urlparse(url)
+                    if all([result.scheme, result.netloc]):
+                        return True
+                    else:
+                        return False
+                except ValueError:
+                    return False
+
+            if not url_check(self.single_dataset__about):
+                raise ConfigurationError(
+                    "Must provide an absolute URL for --about. (Example format: http://example.com)"
+                )
+
+    def handle_adaptor(self):
+        self.validate_correct_type_of_configuration_attribute("adaptor__anndata_adaptor__backed", bool)
+
+    def handle_limits(self):
+        self.validate_correct_type_of_configuration_attribute("limits__diffexp_cellcount_max", (type(None), int))
+        self.validate_correct_type_of_configuration_attribute("limits__column_request_max", (type(None), int))
+
+    def exceeds_limit(self, limit_name, value):
+        limit_value = getattr(self, "limits__" + limit_name, None)
+        if limit_value is None:  # disabled
+            return False
+        return value > limit_value

backend/server/common/corpora.py

@@ -0,0 +1,78 @@
+"""
+Corpora schema conventions support.  Helper functions for reading.
+
+https://github.com/chanzuckerberg/corpora-data-portal/blob/main/backend/schema/corpora_schema.md
+
+https://github.com/chanzuckerberg/corpora-data-portal/blob/main/backend/schema/corpora_schema_h5ad_implementation.md
+"""
+import collections
+import json
+
+from backend.server.cli.upgrade import validate_version_str
+from backend.server.common.utils.corpora_constants import CorporaConstants
+
+
+def corpora_get_versions_from_anndata(adata):
+    """
+    Given an AnnData object, return:
+        * None - if not a Corpora object
+        * [ corpora_schema_version, corpora_encoding_version ] - if a Corpora object
+
+    Implements the identification protocol defined in the specification.
+    """
+
+    # per Corpora AnnData spec, this is a corpora file if the following is true
+    if "version" not in adata.uns_keys():
+        return None
+    version = adata.uns["version"]
+    if not isinstance(version, collections.abc.Mapping) or "corpora_schema_version" not in version:
+        return None
+
+    corpora_schema_version = version.get("corpora_schema_version")
+    corpora_encoding_version = version.get("corpora_encoding_version")
+
+    # TODO: spec says these must be SEMVER values, so check.
+    if validate_version_str(corpora_schema_version) and validate_version_str(corpora_encoding_version):
+        return [corpora_schema_version, corpora_encoding_version]
+
+
+def corpora_is_version_supported(corpora_schema_version, corpora_encoding_version):
+    return (
+        corpora_schema_version
+        and corpora_encoding_version
+        and corpora_schema_version.startswith("1.")
+        and corpora_encoding_version.startswith("0.1.")
+    )
+
+
+def corpora_get_props_from_anndata(adata):
+    """
+    Get Corpora dataset properties from an AnnData
+    """
+    versions = corpora_get_versions_from_anndata(adata)
+    if versions is None:
+        return None
+    [corpora_schema_version, corpora_encoding_version] = versions
+    version_is_supported = corpora_is_version_supported(corpora_schema_version, corpora_encoding_version)
+    if not version_is_supported:
+        raise ValueError("Unsupported Corpora schema version")
+
+    corpora_props = {}
+    for key in CorporaConstants.REQUIRED_SIMPLE_METADATA_FIELDS:
+        if key not in adata.uns:
+            raise KeyError(f"missing Corpora schema field {key}")
+        corpora_props[key] = adata.uns[key]
+
+    for key in CorporaConstants.OPTIONAL_JSON_ENCODED_METADATA_FIELD:
+        if key not in adata.uns:
+            continue
+        try:
+            corpora_props[key] = json.loads(adata.uns[key])
+        except json.JSONDecodeError:
+            raise json.JSONDecodeError(f"Corpora schema field {key} is expected to be a valid JSON string")
+
+    for key in CorporaConstants.OPTIONAL_SIMPLE_METADATA_FIELDS:
+        if key in adata.uns:
+            corpora_props[key] = adata.uns[key]
+
+    return corpora_props

backend/server/common/health.py

@@ -0,0 +1,33 @@
+from http import HTTPStatus
+from flask import make_response, jsonify
+
+from backend.server import __version__ as cellxgene_version
+from backend.common.utils.data_locator import DataLocator
+
+
+def _is_accessible(path, config):
+    if path is None:
+        return True
+
+    try:
+        dl = DataLocator(path, region_name=config.data_locator__s3__region_name)
+        return dl.exists()
+    except RuntimeError:
+        return False
+
+
+def health_check(config):
+    """
+    simple health check - return HTTP response.
+    See https://tools.ietf.org/id/draft-inadarei-api-health-check-01.html
+    """
+    health = {"status": None, "version": "1", "releaseID": cellxgene_version}
+
+    server_config = config.server_config
+    check = _is_accessible(server_config.single_dataset__datapath, server_config)
+
+    health["status"] = "pass" if check else "fail"
+    code = HTTPStatus.OK if health["status"] == "pass" else HTTPStatus.BAD_REQUEST
+    response = make_response(jsonify(health), code)
+    response.headers["Content-Type"] = "application/health+json"
+    return response

backend/server/common/rest.py

@@ -0,0 +1,413 @@
+import copy
+import logging
+import sys
+from http import HTTPStatus
+import zlib
+
+from flask import make_response, jsonify, current_app, abort
+from werkzeug.urls import url_unquote
+
+from backend.server.common.config.client_config import get_client_config, get_client_userinfo
+from backend.common.constants import Axis, DiffExpMode, JSON_NaN_to_num_warning_msg
+from backend.common.errors import (
+    FilterError,
+    JSONEncodingValueError,
+    PrepareError,
+    DisabledFeatureError,
+    ExceedsLimitError,
+    DatasetAccessError,
+    ColorFormatException,
+    AnnotationsError,
+    ObsoleteRequest,
+    UnsupportedSummaryMethod,
+)
+
+import json
+
+from backend.common.fbs.matrix import decode_matrix_fbs
+
+
+def abort_and_log(code, logmsg, loglevel=logging.DEBUG, include_exc_info=False):
+    """
+    Log the message, then abort with HTTP code. If include_exc_info is true,
+    also include current exception via sys.exc_info().
+    """
+    if include_exc_info:
+        exc_info = sys.exc_info()
+    else:
+        exc_info = False
+    current_app.logger.log(loglevel, logmsg, exc_info=exc_info)
+    # Do NOT send log message to HTTP response.
+    return abort(code)
+
+
+def _query_parameter_to_filter(args):
+    """
+    Convert an annotation value filter, if present in the query args,
+    into the standard dict filter format used by internal code.
+
+    Query param filters look like:  <axis>:name=value, where value
+    may be one of:
+        - a range, min,max, where either may be an open range by using an asterisk, eg, 10,*
+        - a value
+    Eg,
+        ...?tissue=lung&obs:tissue=heart&obs:num_reads=1000,*
+    """
+    filters = {
+        "obs": {},
+        "var": {},
+    }
+
+    # args has already been url-unquoted once.  We assume double escaping
+    # on name and value.
+    try:
+        for key, value in args.items(multi=True):
+            axis, name = key.split(":")
+            if axis not in ("obs", "var"):
+                raise FilterError("unknown filter axis")
+            name = url_unquote(name)
+            current = filters[axis].setdefault(name, {"name": name})
+
+            val_split = value.split(",")
+            if len(val_split) == 1:
+                if "min" in current or "max" in current:
+                    raise FilterError("do not mix range and value filters")
+                value = url_unquote(value)
+                values = current.setdefault("values", [])
+                values.append(value)
+
+            elif len(val_split) == 2:
+                if len(current) > 1:
+                    raise FilterError("duplicate range specification")
+                min = url_unquote(val_split[0])
+                max = url_unquote(val_split[1])
+                if min != "*":
+                    current["min"] = float(min)
+                if max != "*":
+                    current["max"] = float(max)
+                if len(current) < 2:
+                    raise FilterError("must specify at least min or max in range filter")
+
+            else:
+                raise FilterError("badly formated filter value")
+
+    except ValueError as e:
+        raise FilterError(str(e))
+
+    result = {}
+    for axis in ("obs", "var"):
+        axis_filter = filters[axis]
+        if len(axis_filter) > 0:
+            result[axis] = {"annotation_value": [val for val in axis_filter.values()]}
+
+    return result
+
+
+def schema_get_helper(data_adaptor):
+    """helper function to gather the schema from the data source and annotations"""
+    schema = data_adaptor.get_schema()
+    schema = copy.deepcopy(schema)
+
+    # add label obs annotations as needed
+    annotations = data_adaptor.dataset_config.user_annotations
+    if annotations.user_annotations_enabled():
+        label_schema = annotations.get_schema(data_adaptor)
+        schema["annotations"]["obs"]["columns"].extend(label_schema)
+
+    return schema
+
+
+def schema_get(data_adaptor):
+    schema = schema_get_helper(data_adaptor)
+    return make_response(jsonify({"schema": schema}), HTTPStatus.OK)
+
+
+def config_get(app_config, data_adaptor):
+    config = get_client_config(app_config, data_adaptor)
+    return make_response(jsonify(config), HTTPStatus.OK)
+
+
+def userinfo_get(app_config, data_adaptor):
+    config = get_client_userinfo(app_config, data_adaptor)
+    return make_response(jsonify(config), HTTPStatus.OK)
+
+
+def annotations_obs_get(request, data_adaptor):
+    fields = request.args.getlist("annotation-name", None)
+    num_columns_requested = len(data_adaptor.get_obs_keys()) if len(fields) == 0 else len(fields)
+    if data_adaptor.server_config.exceeds_limit("column_request_max", num_columns_requested):
+        return abort(HTTPStatus.BAD_REQUEST)
+    preferred_mimetype = request.accept_mimetypes.best_match(["application/octet-stream"])
+    if preferred_mimetype != "application/octet-stream":
+        return abort(HTTPStatus.NOT_ACCEPTABLE)
+
+    try:
+        labels = None
+        annotations = data_adaptor.dataset_config.user_annotations
+        if annotations.user_annotations_enabled():
+            labels = annotations.read_labels(data_adaptor)
+        fbs = data_adaptor.annotation_to_fbs_matrix(Axis.OBS, fields, labels)
+        return make_response(fbs, HTTPStatus.OK, {"Content-Type": "application/octet-stream"})
+    except KeyError as e:
+        return abort_and_log(HTTPStatus.BAD_REQUEST, str(e), include_exc_info=True)
+
+
+def annotations_put_fbs_helper(data_adaptor, fbs):
+    """helper function to write annotations from fbs"""
+    annotations = data_adaptor.dataset_config.user_annotations
+    if not annotations.user_annotations_enabled():
+        raise DisabledFeatureError("Writable annotations are not enabled")
+
+    new_label_df = decode_matrix_fbs(fbs)
+    if not new_label_df.empty:
+        new_label_df = data_adaptor.check_new_labels(new_label_df)
+    annotations.write_labels(new_label_df, data_adaptor)
+
+
+def inflate(data):
+    return zlib.decompress(data)
+
+
+def annotations_obs_put(request, data_adaptor):
+    annotations = data_adaptor.dataset_config.user_annotations
+    if not annotations.user_annotations_enabled():
+        return abort(HTTPStatus.NOT_IMPLEMENTED)
+
+    anno_collection = request.args.get("annotation-collection-name", default=None)
+    fbs = inflate(request.get_data())
+
+    if anno_collection is not None:
+        if not annotations.is_safe_collection_name(anno_collection):
+            return abort(HTTPStatus.BAD_REQUEST, "Bad annotation collection name")
+        annotations.set_collection(anno_collection)
+
+    try:
+        annotations_put_fbs_helper(data_adaptor, fbs)
+        res = json.dumps({"status": "OK"})
+        return make_response(res, HTTPStatus.OK, {"Content-Type": "application/json"})
+    except (ValueError, DisabledFeatureError, KeyError) as e:
+        return abort_and_log(HTTPStatus.BAD_REQUEST, str(e), include_exc_info=True)
+
+
+def annotations_var_get(request, data_adaptor):
+    fields = request.args.getlist("annotation-name", None)
+    num_columns_requested = len(data_adaptor.get_var_keys()) if len(fields) == 0 else len(fields)
+    if data_adaptor.server_config.exceeds_limit("column_request_max", num_columns_requested):
+        return abort(HTTPStatus.BAD_REQUEST)
+    preferred_mimetype = request.accept_mimetypes.best_match(["application/octet-stream"])
+    if preferred_mimetype != "application/octet-stream":
+        return abort(HTTPStatus.NOT_ACCEPTABLE)
+
+    try:
+        labels = None
+        return make_response(
+            data_adaptor.annotation_to_fbs_matrix(Axis.VAR, fields, labels),
+            HTTPStatus.OK,
+            {"Content-Type": "application/octet-stream"},
+        )
+    except KeyError as e:
+        return abort_and_log(HTTPStatus.BAD_REQUEST, str(e), include_exc_info=True)
+
+
+def data_var_put(request, data_adaptor):
+    preferred_mimetype = request.accept_mimetypes.best_match(["application/octet-stream"])
+    if preferred_mimetype != "application/octet-stream":
+        return abort(HTTPStatus.NOT_ACCEPTABLE)
+
+    filter_json = request.get_json()
+    filter = filter_json["filter"] if filter_json else None
+    try:
+        return make_response(
+            data_adaptor.data_frame_to_fbs_matrix(filter, axis=Axis.VAR),
+            HTTPStatus.OK,
+            {"Content-Type": "application/octet-stream"},
+        )
+    except (FilterError, ValueError, ExceedsLimitError) as e:
+        return abort_and_log(HTTPStatus.BAD_REQUEST, str(e), include_exc_info=True)
+
+
+def data_var_get(request, data_adaptor):
+    preferred_mimetype = request.accept_mimetypes.best_match(["application/octet-stream"])
+    if preferred_mimetype != "application/octet-stream":
+        return abort(HTTPStatus.NOT_ACCEPTABLE)
+
+    try:
+        filter = _query_parameter_to_filter(request.args)
+        return make_response(
+            data_adaptor.data_frame_to_fbs_matrix(filter, axis=Axis.VAR),
+            HTTPStatus.OK,
+            {"Content-Type": "application/octet-stream"},
+        )
+    except (FilterError, ValueError, ExceedsLimitError) as e:
+        return abort_and_log(HTTPStatus.BAD_REQUEST, str(e), include_exc_info=True)
+
+
+def colors_get(data_adaptor):
+    if not data_adaptor.dataset_config.presentation__custom_colors:
+        return make_response(jsonify({}), HTTPStatus.OK)
+    try:
+        return make_response(jsonify(data_adaptor.get_colors()), HTTPStatus.OK)
+    except ColorFormatException as e:
+        return abort_and_log(HTTPStatus.NOT_FOUND, str(e), include_exc_info=True)
+
+
+def diffexp_obs_post(request, data_adaptor):
+    if not data_adaptor.dataset_config.diffexp__enable:
+        return abort(HTTPStatus.NOT_IMPLEMENTED)
+
+    args = request.get_json()
+    try:
+        # TODO: implement varfilter mode
+        mode = DiffExpMode(args["mode"])
+
+        if mode == DiffExpMode.VAR_FILTER or "varFilter" in args:
+            return abort_and_log(HTTPStatus.NOT_IMPLEMENTED, "varFilter not enabled")
+
+        set1_filter = args.get("set1", {"filter": {}})["filter"]
+        set2_filter = args.get("set2", {"filter": {}})["filter"]
+        count = args.get("count", None)
+
+        if set1_filter is None or set2_filter is None or count is None:
+            return abort_and_log(HTTPStatus.BAD_REQUEST, "missing required parameter")
+        if Axis.VAR in set1_filter or Axis.VAR in set2_filter:
+            return abort_and_log(HTTPStatus.BAD_REQUEST, "var axis filter not enabled")
+
+    except (KeyError, TypeError) as e:
+        return abort_and_log(HTTPStatus.BAD_REQUEST, str(e), include_exc_info=True)
+
+    try:
+        diffexp = data_adaptor.diffexp_topN(set1_filter, set2_filter, count)
+        return make_response(diffexp, HTTPStatus.OK, {"Content-Type": "application/json"})
+    except (ValueError, DisabledFeatureError, FilterError, ExceedsLimitError) as e:
+        return abort_and_log(HTTPStatus.BAD_REQUEST, str(e), include_exc_info=True)
+    except JSONEncodingValueError:
+        # JSON encoding failure, usually due to bad data. Just let it ripple up
+        # to default exception handler.
+        current_app.logger.warning(JSON_NaN_to_num_warning_msg)
+        raise
+
+
+def layout_obs_get(request, data_adaptor):
+    fields = request.args.getlist("layout-name", None)
+    num_columns_requested = len(data_adaptor.get_embedding_names()) if len(fields) == 0 else len(fields)
+    if data_adaptor.server_config.exceeds_limit("column_request_max", num_columns_requested):
+        return abort(HTTPStatus.BAD_REQUEST)
+
+    preferred_mimetype = request.accept_mimetypes.best_match(["application/octet-stream"])
+    if preferred_mimetype != "application/octet-stream":
+        return abort(HTTPStatus.NOT_ACCEPTABLE)
+
+    try:
+        return make_response(
+            data_adaptor.layout_to_fbs_matrix(fields), HTTPStatus.OK, {"Content-Type": "application/octet-stream"}
+        )
+    except (KeyError, DatasetAccessError) as e:
+        return abort_and_log(HTTPStatus.BAD_REQUEST, str(e), include_exc_info=True)
+    except PrepareError:
+        return abort_and_log(
+            HTTPStatus.NOT_IMPLEMENTED,
+            f"No embedding available {request.path}",
+            loglevel=logging.ERROR,
+            include_exc_info=True,
+        )
+
+
+def layout_obs_put(request, data_adaptor):
+    if not data_adaptor.dataset_config.embeddings__enable_reembedding:
+        return abort(HTTPStatus.NOT_IMPLEMENTED)
+
+    args = request.get_json()
+    filter = args["filter"] if args else None
+    if not filter:
+        return abort_and_log(HTTPStatus.BAD_REQUEST, "obs filter is required")
+    method = args["method"] if args else "umap"
+
+    try:
+        schema = data_adaptor.compute_embedding(method, filter)
+        return make_response(jsonify(schema), HTTPStatus.OK, {"Content-Type": "application/json"})
+    except NotImplementedError as e:
+        return abort_and_log(HTTPStatus.NOT_IMPLEMENTED, str(e))
+    except (ValueError, DisabledFeatureError, FilterError) as e:
+        return abort_and_log(HTTPStatus.BAD_REQUEST, str(e), include_exc_info=True)
+
+
+def genesets_get(request, data_adaptor):
+    preferred_mimetype = request.accept_mimetypes.best_match(["application/json", "text/csv"])
+    if preferred_mimetype not in ("application/json", "text/csv"):
+        return abort(HTTPStatus.NOT_ACCEPTABLE)
+
+    try:
+        annotations = data_adaptor.dataset_config.user_annotations
+        (genesets, tid) = annotations.read_gene_sets(data_adaptor)
+
+        if preferred_mimetype == "text/csv":
+            return make_response(
+                annotations.gene_sets_to_csv(genesets),
+                HTTPStatus.OK,
+                {
+                    "Content-Type": "text/csv",
+                    "Content-Disposition": "attachment; filename=genesets.csv",
+                },
+            )
+        else:
+            return make_response(
+                jsonify({"genesets": annotations.gene_sets_to_response(genesets), "tid": tid}), HTTPStatus.OK
+            )
+    except (ValueError, KeyError, AnnotationsError) as e:
+        return abort_and_log(HTTPStatus.BAD_REQUEST, str(e))
+
+
+def genesets_put(request, data_adaptor):
+    annotations = data_adaptor.dataset_config.user_annotations
+    if not annotations.gene_sets_save_enabled():
+        return abort(HTTPStatus.NOT_IMPLEMENTED)
+
+    anno_collection = request.args.get("annotation-collection-name", default=None)
+    if anno_collection is not None:
+        if not annotations.is_safe_collection_name(anno_collection):
+            return abort(HTTPStatus.BAD_REQUEST, "Bad annotation collection name")
+        annotations.set_collection(anno_collection)
+
+    args = request.get_json()
+    try:
+        genesets = args.get("genesets", None)
+        tid = args.get("tid", None)
+        if genesets is None:
+            abort(HTTPStatus.BAD_REQUEST)
+
+        annotations.write_gene_sets(genesets, tid, data_adaptor)
+        return make_response(jsonify({"status": "OK"}), HTTPStatus.OK)
+    except (ValueError, DisabledFeatureError, KeyError) as e:
+        return abort_and_log(HTTPStatus.BAD_REQUEST, str(e), include_exc_info=True)
+    except (ObsoleteRequest, TypeError) as e:
+        return abort(HTTPStatus.NOT_FOUND, description=str(e))
+
+
+def geneset_summary_get(request, data_adaptor):
+    preferred_mimetype = request.accept_mimetypes.best_match(["application/octet-stream"])
+    if preferred_mimetype != "application/octet-stream":
+        return abort(HTTPStatus.NOT_ACCEPTABLE)
+
+    geneset_name = request.args.get("geneset_name", default=None)
+    summary_method = request.args.get("method", default="mean")
+    request_tid = request.args.get("tid", default=None)
+
+    try:
+        annotations = data_adaptor.dataset_config.user_annotations
+        (genesets, tid) = annotations.read_gene_sets(data_adaptor)
+
+        if request_tid is not None and int(request_tid) != tid:
+            return abort(HTTPStatus.NOT_FOUND, "Obsolete TID")
+        if geneset_name is None or geneset_name not in genesets:
+            return abort(HTTPStatus.BAD_REQUEST, "Gene set name not found.")
+        genes = [g["gene_symbol"] for g in genesets.get(geneset_name)["genes"]]
+
+        return make_response(
+            data_adaptor.get_gene_set_summary(geneset_name, genes, summary_method),
+            HTTPStatus.OK,
+            {"Content-Type": "application/octet-stream"},
+        )
+    except (ValueError) as e:
+        return abort(HTTPStatus.NOT_FOUND, description=str(e))
+    except (UnsupportedSummaryMethod) as e:
+        return abort(HTTPStatus.BAD_REQUEST, description=str(e))

backend/server/common/utils/corpora_constants.py

@@ -0,0 +1,22 @@
+class CorporaConstants(object):
+    REQUIRED_SIMPLE_METADATA_FIELDS = [
+        "version",
+        "title",
+        "layer_descriptions",
+        "organism",
+        "organism_ontology_term_id",
+    ]
+
+    # The Corpora specification requires some values encoded as JSON due to the inability of AnnData to store complex
+    # types.
+    OPTIONAL_JSON_ENCODED_METADATA_FIELD = ["contributors", "project_links"]
+
+    OPTIONAL_SIMPLE_METADATA_FIELDS = [
+        "preprint_doi",
+        "publication_doi",
+        "default_embedding",
+        "default_field",
+        "tags",
+        "project_name",
+        "project_description",
+    ]