Merge remote-tracking branch 'upstream/bugfix/pubmed-citations' into bugfix/pubmed-citations

chreman · chreman · commit a695eb2ed4c2 · 2025-03-24T23:39:08.000+01:00
diff --git a/server/workers/common/common/utils.py b/server/workers/common/common/utils.py
@@ -128,30 +128,49 @@ def push_metadata_to_queue(
     redis_store: redis.Redis,
     params: Dict[str, Union[str, List[str]]],
     metadata: pd.DataFrame,
-    source: Literal["crossref", "altmetric"]
+    source_list: List[str]
 ) -> str:
     """
     Sending metadata for processing into Redis queue and returning the request_id.
 
     :param redis_store: Object of the Redis store.
     :param params: Request params.
     :param metadata: DataFrame with default metadata.
-    :param source: define from which service additional metadata will be received.
+    :param source_list: define from which service additional metadata will be received (available values: "crossref", "altmetric").
     :return: request_id for the receiving of the request result.
     """
+    # Checks that valid values are specified in the source array
+    check_metadata_enrichment_source(source_list)
 
+    # Creates a new unique request identifier that will then be used to retrieve the result
     request_id = str(uuid.uuid4())
-    params["metrics_sources"] = [source]
+
+    # Specifies from which sources to obtain information
+    params["metrics_sources"] = source_list
+
+    # Payload object creation
     task_data = json.dumps({
         "id": request_id,
         "params": params,
         "metadata": metadata.to_json(orient="records"),
     })
 
+    # Pushing request to Redis and returning request id
     redis_store.rpush("metrics", task_data)
     return request_id
 
 
+def check_metadata_enrichment_source(source_list: List[str]) -> None:
+    """
+    Checks that valid values are specified in the source array.
+
+    :param source_list: List of sources from where metadata will be enriched.
+    :return: None.
+    """
+    if not all(source in ("crossref", "altmetric") for source in source_list):
+        raise ValueError("Source list must contain only 'crossref' or 'altmetric'")
+
+
 def fetch_enriched_metadata(redis_store: redis.Redis, request_id: str, timeout: int = 600) -> pd.DataFrame:
     """
     Getting enriched metadata from Redis.
@@ -161,23 +180,29 @@ def fetch_enriched_metadata(redis_store: redis.Redis, request_id: str, timeout:
     :param timeout: Results waiting time (default - 600 seconds).
     :return: Enriched DataFrame with metadata.
     """
+    # Getting result of metadata enrichment from Redis
     result = get_key(redis_store, request_id, timeout)
     return pd.DataFrame(result["input_data"])
 
 
-def get_metadata_columns_for_integration(integration: Literal["pubmed", "orcid"]):
+def get_metadata_columns_for_source(source_list: List[str]) -> List[str]:
     """
-    Returning required metadata columns for different integrations.
+    Returning required metadata columns for different sources.
 
-    :param integration: integration service.
+    :param source_list: List of sources from where metadata received.
     :return: array with required metadata columns.
     """
+    # Checks that valid values are specified in the source array
+    check_metadata_enrichment_source(source_list)
+
+    # Define required metadata columns for different sources and return them
+    result = []
 
-    if integration == 'pubmed':
-        return ["citation_count"]
-    elif integration == 'orcid':
-        return [
-            "citation_count",
+    if "crossref" in source_list:
+        result.extend(["citation_count"])
+
+    if "altmetric" in source_list:
+        result.extend([
             "cited_by_wikipedia_count",
             "cited_by_msm_count",
             "cited_by_policies_count",
@@ -190,21 +215,24 @@ def get_metadata_columns_for_integration(integration: Literal["pubmed", "orcid"]
             "cited_by_qna_count",
             "cited_by_tweeters_count",
             "cited_by_videos_count"
-        ]
+        ])
 
-    return []
+    return result
 
 
-def ensure_required_columns(metadata: pd.DataFrame, integration: Literal["pubmed", "orcid"]) -> pd.DataFrame:
+def ensure_required_columns(metadata: pd.DataFrame, source_list: List[str]) -> pd.DataFrame:
     """
     Checks that all necessary columns are available or adding them with NaN value.
 
     :param metadata: DataFrame with metadata.
-    :param integration: integration service.
+    :param source_list: List of sources from where metadata received.
     :return: Updated DataFrame.
     """
+    # Checks that valid values are specified in the source array
+    check_metadata_enrichment_source(source_list)
 
-    columns = get_metadata_columns_for_integration(integration)
+    # Gets metadata columns that must be received from source(-s)
+    columns = get_metadata_columns_for_source(source_list)
     for column in columns:
         if column not in metadata.columns:
             metadata[column] = np.NaN
@@ -216,26 +244,27 @@ def enrich_metadata(
     redis: redis.Redis,
     params: Dict[str, Union[str, List[str]]],
     metadata: pd.DataFrame,
-    source: Literal["crossref", "altmetric"],
-    integration: Literal["pubmed", "orcid"]
+    source_list: List[str],
 ) -> pd.DataFrame:
     """
     Enriching metadata - adding information about citations from Redis.
 
     :param redis: store object of Redis.
     :param params: params of the request.
     :param metadata: DataFrame with default metadata.
-    :param source: define from which service additional metadata will be received.
+    :param source: define from which service additional metadata will be received (available values: "crossref", "altmetric").
     :return: Enriched DataFrame with metadata.
     """
+    # Checks that valid values are specified in the source array
+    check_metadata_enrichment_source(source_list)
 
     # Creates a request to metrics for metadata enrichment
     # and returns request_id for receiving the result later
-    request_id = push_metadata_to_queue(redis, params, metadata, source)
+    request_id = push_metadata_to_queue(redis, params, metadata, source_list)
 
     # Getting the result after metadata enrichment at metrics
     enriched_metadata = fetch_enriched_metadata(redis, request_id)
 
     # Checks that all necessary columns are available or adding them with NaN value
-    enriched_metadata = ensure_required_columns(enriched_metadata, integration)
+    enriched_metadata = ensure_required_columns(enriched_metadata, source_list)
     return enriched_metadata
diff --git a/server/workers/orcid/src/orcid_service.py b/server/workers/orcid/src/orcid_service.py
@@ -388,9 +388,10 @@ def _retrieve_author_info_and_metadata(self, orcid: Orcid) -> Tuple[AuthorInfo,
 
     def _process_metadata(self, metadata: pd.DataFrame, author_info: AuthorInfo, params: Dict[str, str]) -> pd.DataFrame:
         metadata["authors"] = metadata["authors"].replace("", author_info.author_name)
-        source_for_metadata_enrichment = "crossref"
-        integration = 'orcid'
-        metadata = enrich_metadata(self.redis_store, params, metadata, source_for_metadata_enrichment, integration)
+
+        source_for_metadata_enrichment = ["crossref", "altmetric"]
+        metadata = enrich_metadata(self.redis_store, params, metadata, source_for_metadata_enrichment)
+
         self.logger.debug(f'metadata shape after base enrichment: {metadata.shape}')
         author_info = self.enrich_author_info(author_info, metadata, params)
         self.logger.debug(f'metadata shape after enrichment: {metadata.shape}')
diff --git a/server/workers/pubmed/src/pubmed.py b/server/workers/pubmed/src/pubmed.py
@@ -41,10 +41,9 @@ def execute_search(self, params):
                 return raw_metadata
 
             metadata = pd.DataFrame(raw_metadata)
-            source_for_metadata_enrichment = "crossref"
-            integration = 'pubmed'
 
-            metadata = enrich_metadata(self.redis_store, params, metadata, source_for_metadata_enrichment, integration)
+            source_for_metadata_enrichment = ["crossref"]
+            metadata = enrich_metadata(self.redis_store, params, metadata, source_for_metadata_enrichment)
 
             text = pd.DataFrame(raw_text)
 
diff --git a/vis/js/templates/Paper.tsx b/vis/js/templates/Paper.tsx
@@ -15,8 +15,8 @@ const orderPriorityMap = {
   cited_by_accounts_count: "social",
   references: "references",
   readers: "readers",
-  tweets: "tweets"
-}
+  tweets: "tweets",
+};
 
 class Paper extends React.Component {
   constructor(props) {
@@ -108,18 +108,35 @@ class Paper extends React.Component {
   }
 
   render() {
-    const { data, zoom, selected, hovered, maxSize, enlargeFactor, onClick, onMouseOver, onMouseOut } = this.props;
+    const {
+      data,
+      zoom,
+      selected,
+      hovered,
+      maxSize,
+      enlargeFactor,
+      onClick,
+      onMouseOver,
+      onMouseOut,
+    } = this.props;
 
     const {
       title,
       authors_string: authors,
       authors_list: authors_list,
       year,
       area,
-      published_in: publisher
+      published_in: publisher,
     } = data;
 
-    const { x, y, width: baseWidth, height: baseHeight, path: basePath, dogEar: baseDogEar } = this.state;
+    const {
+      x,
+      y,
+      width: baseWidth,
+      height: baseHeight,
+      path: basePath,
+      dogEar: baseDogEar,
+    } = this.state;
 
     const {
       showSocialMedia,
@@ -135,14 +152,7 @@ class Paper extends React.Component {
       tweetsLabel,
     } = this.props;
 
-    const {
-      // num_readers: 
-      readers,
-      tweets,
-      citations,
-      social,
-      references,
-    } = data;
+    const { readers, tweets, citations, social, references } = data;
 
     let { width: realWidth, height: realHeight } =
       this.getCoordinatesAndDimensions();
@@ -226,11 +236,10 @@ class Paper extends React.Component {
         value: citations,
         label: citationsLabel,
       },
-      // consider to refactor and retrieve correct data from the backend side instead of doing this hack with citations for pubmed
       {
         id: "citations pubmed",
         show: showPubmedCitations,
-        value: readers,
+        value: citations,
         label: citationsLabel,
       },
       {
@@ -257,15 +266,14 @@ class Paper extends React.Component {
         value: tweets,
         label: tweetsLabel,
       },
-    ].filter(stat => stat.show)
+    ].filter((stat) => stat.show);
 
     let sortedStats = stats;
 
     if (this.props.scaleValue) {
       const { scaleValue } = this.props;
 
-
-      const tagPreference = orderPriorityMap[scaleValue]
+      const tagPreference = orderPriorityMap[scaleValue];
 
       sortedStats = tagPreference
         ? [...stats].sort((a, b) => {
@@ -354,20 +362,35 @@ class Paper extends React.Component {
                   )}
                 </p>
               </div>
-              {(hovered ? sortedStats : sortedStats.slice(0, 1)).map(({ value, label, id }) => (
-                <div key={id} className="stat" style={{
-                  textWrap: 'nowrap'
-                }}>
-                  <p id="stat" className={sizeModifierClass}>
-                    <span style={{
-                      textWrap: 'nowrap'
-                    }} className="num-stat">{value || value === 0 ? value : "n/a"} </span>
-                    <span style={{
-                      textWrap: 'nowrap'
-                    }}>{label}</span>
-                  </p>
-                </div>
-              ))}
+              {(hovered ? sortedStats : sortedStats.slice(0, 1)).map(
+                ({ value, label, id }) => (
+                  <div
+                    key={id}
+                    className="stat"
+                    style={{
+                      textWrap: "nowrap",
+                    }}
+                  >
+                    <p id="stat" className={sizeModifierClass}>
+                      <span
+                        style={{
+                          textWrap: "nowrap",
+                        }}
+                        className="num-stat"
+                      >
+                        {value || value === 0 ? value : "n/a"}{" "}
+                      </span>
+                      <span
+                        style={{
+                          textWrap: "nowrap",
+                        }}
+                      >
+                        {label}
+                      </span>
+                    </p>
+                  </div>
+                )
+              )}
             </div>
           </div>
         </foreignObject>
@@ -506,8 +529,9 @@ const DOGEAR_WIDTH = 0.15;
 const DOGEAR_HEIGHT = 0.15;
 
 const getDogEar = ({ x, y, width: w, height: h }) => {
-  return `M ${x + (1 - DOGEAR_WIDTH) * w} ${y} v ${DOGEAR_HEIGHT * h} h ${DOGEAR_WIDTH * w
-    }`;
+  return `M ${x + (1 - DOGEAR_WIDTH) * w} ${y} v ${DOGEAR_HEIGHT * h} h ${
+    DOGEAR_WIDTH * w
+  }`;
 };
 
 const getRoundedPath = ({ x, y, width, height }) => {
@@ -527,8 +551,9 @@ const getRoundedPath = ({ x, y, width, height }) => {
 };
 
 const getSquarePath = ({ x, y, width: w, height: h }) => {
-  return `M ${x} ${y} h ${(1 - DOGEAR_WIDTH) * w} l ${DOGEAR_HEIGHT * w} ${DOGEAR_WIDTH * h
-    } v ${(1 - DOGEAR_HEIGHT) * h} h ${-w} v ${-h}`;
+  return `M ${x} ${y} h ${(1 - DOGEAR_WIDTH) * w} l ${DOGEAR_HEIGHT * w} ${
+    DOGEAR_WIDTH * h
+  } v ${(1 - DOGEAR_HEIGHT) * h} h ${-w} v ${-h}`;
 };
 
 const getEnlargeFactor = (offsetWidth, scrollHeight) => {
@@ -551,7 +576,7 @@ const getEnlargeFactor = (offsetWidth, scrollHeight) => {
 
 const getMetadataHeight = (realHeight, numOfLabels, isZoomed) => {
   let readersHeight = 0;
-  
+
   if (numOfLabels && isZoomed) {
     readersHeight += numOfLabels * 12 + 10;
   }
