pub-analyzer 0.2.0__py3-none-any.whl → 0.3.0__py3-none-any.whl

pub_analyzer/css/body.tcss

@@ -14,38 +14,51 @@ SideBar {
 
     background: $bg-secondary-color;
     color: $text-primary-color;
-    transition: width 250ms in_out_cubic;
-}
 
-.-dark-mode SideBar {
-    background: $bg-secondary-color-darken;
-    color: $text-primary-color-darken;
-}
+    Button {
+        text-align: start;
+    }
 
-SideBar.-hidden {
-    width: 0;
-}
+    #sidebar-title {
+        width: 100%;
+        content-align: left middle;
+        text-style: bold;
+        border-bottom: heavy $text-primary-color;
+    }
 
-SideBar .sidebar-options-column {
-    margin: 1;
-    padding: 1 1;
-}
+    .sidebar-options-column {
+        margin: 1;
+        padding: 1 1;
+    }
 
-SideBar #sidebar-title {
-    width: 100%;
-    content-align: left middle;
-    text-style: bold;
-    border-bottom: heavy $text-primary-color;
-}
+    .sidebar-buttons-column {
+        height: 1fr;
+
+        .sidebar-option {
+            content-align: left middle;
+            margin: 1 0;
+            width: 100%;
+        }
+    }
 
-.-dark-mode SideBar #sidebar-title {
-    border-bottom: heavy $text-primary-color-darken;
+    #module-version-label {
+        color: $text-primary-color 25%;
+        text-align: center;
+        width: 100%;
+    }
 }
 
-SideBar .sidebar-option {
-    content-align: left middle;
-    margin: 1 0;
-    width: 100%;
+.-dark-mode SideBar {
+    background: $bg-secondary-color-darken;
+    color: $text-primary-color-darken;
+
+    #sidebar-title {
+        border-bottom: heavy $text-primary-color-darken;
+    }
+
+    #module-version-label {
+        color: $text-primary-color-darken 25%;
+    }
 }
 
 /* Main Content CSS */
@@ -55,20 +68,20 @@ MainContent {
 
     padding: 2 1 0 1;
     height: 100%;
+
+    .title {
+        content-align: left middle;
+        text-style: bold;
+        border-bottom: heavy $text-primary-color;
+        width: 100%
+    }
 }
 
 .-dark-mode MainContent {
     background: $bg-main-color-darken;
     color: $text-primary-color-darken;
-}
-
-MainContent .title {
-    content-align: left middle;
-    text-style: bold;
-    border-bottom: heavy $text-primary-color;
-    width: 100%
-}
 
-.-dark-mode MainContent .title {
-    border-bottom: heavy $text-primary-color-darken;
+    .title {
+        border-bottom: heavy $text-primary-color-darken;
+    }
 }

pub_analyzer/css/buttons.tcss

@@ -3,10 +3,6 @@ $primary-color: #b91c1c;
 $primary-color-accent: #991b1b;
 $primary-color-highlight: #dc2626;
 
-Button {
-    text-align: start;
-}
-
 /* Primary variant */
 Button.-primary {
     background: $primary-color;

pub_analyzer/css/main.tcss

@@ -39,6 +39,6 @@ LoadingIndicator {
     color: $primary-color-accent;
 }
 
-LoadingIndicator.-overlay {
+LoadingIndicator.-textual-loading-indicator {
     background: transparent;
 }

pub_analyzer/css/summary.tcss

@@ -0,0 +1,75 @@
+/* COLORS */
+$bg-main-color: white;
+$bg-secondary-color: #e5e7eb;
+$bg-secondary-color-accent: #d1d5db;
+$text-primary-color: black;
+
+$bg-main-color-darken: #1e293b;
+$bg-secondary-color-darken: #0f172a;
+$text-primary-color-darken: black;
+
+SummaryWidget {
+    height: 1fr;
+    margin: 1 2;
+
+    /* Titles */
+    .block-title {
+        text-align: center;
+        width: 100%;
+        border-bottom: solid $text-primary-color;
+    }
+
+    /* Block Container */
+    .block-container {
+        padding: 1;
+        height: auto;
+    }
+
+    /* Cards */
+    .cards-container {
+        height: auto;
+        margin: 1 0 0 0 ;
+
+        layout: grid;
+        grid-size: 3 1;
+        grid-rows: 14;
+        grid-columns: 1fr;
+        grid-gutter: 1 2;
+    }
+
+    /* Info Container */
+    .info-container {
+        height: auto;
+
+        Label {
+            text-align: center;
+            width: 1fr;
+        }
+    }
+
+    /* Table */
+    .table-container {
+        height: auto;
+        margin: 1 0 0 0;
+    }
+
+    /* Filter Container */
+    .filter-collapsible {
+        margin-top: 1;
+
+        DateRangeFilter {
+            margin-top: 1;
+        }
+    }
+
+    /* Buttons */
+    .button-container {
+        align: center middle;
+        height: 5;
+    }
+}
+
+.-dark-mode SummaryWidget {
+    color: $text-primary-color-darken;
+    background: $bg-secondary-color;
+}

pub_analyzer/internal/identifier.py

@@ -2,6 +2,7 @@
 
 from pub_analyzer.models.author import Author, AuthorOpenAlexKey, AuthorResult, DehydratedAuthor
 from pub_analyzer.models.institution import DehydratedInstitution, Institution, InstitutionOpenAlexKey, InstitutionResult
+from pub_analyzer.models.source import DehydratedSource, Source
 from pub_analyzer.models.work import Work
 
 
@@ -78,3 +79,28 @@ def get_work_id(work: Work) -> str:
         return work.id.path.rpartition("/")[2]
     else:
         return ""
+
+
+def get_source_id(source: DehydratedSource | Source) -> str:
+    """Extract OpenAlex ID from Source Model.
+
+    Args:
+        source: Source model instance.
+
+    Returns:
+        Source OpenAlex ID.
+
+    Example:
+        ```python
+        from pub_analyzer.internal.identifier import get_source_id
+        from pub_analyzer.models.source import Source
+
+        source = Source(id="https://openalex.org/S000000000", **kwargs)
+        print(get_source_id(source))
+        # 'S000000000'
+        ```
+    """
+    if source.id.path:
+        return source.id.path.rpartition("/")[2]
+    else:
+        return ""

pub_analyzer/internal/report.py

@@ -13,14 +13,15 @@ from pub_analyzer.models.institution import DehydratedInstitution, Institution,
 from pub_analyzer.models.report import (
     AuthorReport,
     CitationReport,
-    CitationResume,
+    CitationSummary,
     CitationType,
     InstitutionReport,
-    OpenAccessResume,
-    SourcesResume,
+    OpenAccessSummary,
+    SourcesSummary,
     WorkReport,
     WorkTypeCounter,
 )
+from pub_analyzer.models.source import DehydratedSource, Source
 from pub_analyzer.models.work import Authorship, Work
 
 FromDate = NewType("FromDate", datetime.datetime)
@@ -171,6 +172,25 @@ async def _get_works(client: httpx.AsyncClient, url: str) -> list[Work]:
     return TypeAdapter(list[Work]).validate_python(works_data)
 
 
+async def _get_source(client: httpx.AsyncClient, url: str) -> Source:
+    """Get source given a URL.
+
+    Args:
+        client: HTTPX asynchronous client to be used to make the requests.
+        url: URL of works with all filters.
+
+    Returns:
+        Source Model.
+
+    Raises:
+        httpx.HTTPStatusError: One response from OpenAlex API had an error HTTP status of 4xx or 5xx.
+    """
+    response = await client.get(url=url)
+    response.raise_for_status()
+
+    return Source(**response.json())
+
+
 async def make_author_report(
     author: Author,
     extra_profiles: list[Author | AuthorResult | DehydratedAuthor] | None = None,
@@ -216,10 +236,10 @@ async def make_author_report(
 
         # Report fields.
         works: list[WorkReport] = []
-        report_citation_resume = CitationResume()
-        open_access_resume = OpenAccessResume()
+        report_citation_summary = CitationSummary()
+        open_access_summary = OpenAccessSummary()
         works_type_counter: list[WorkTypeCounter] = []
-        sources_resume = SourcesResume(sources=[])
+        dehydrated_sources: list[DehydratedSource] = []
 
         # Getting all works that have cited the author.
         for author_work in author_works:
@@ -230,7 +250,7 @@ async def make_author_report(
             )
 
             # Adding the type of OpenAccess in the counter.
-            open_access_resume.add_oa_type(author_work.open_access.oa_status)
+            open_access_summary.add_oa_type(author_work.open_access.oa_status)
 
             # Adding the work type to works type counter.
             work_type = next((work_type for work_type in works_type_counter if work_type.type_name == author_work.type), None)
@@ -241,31 +261,42 @@ async def make_author_report(
 
             # Add Sources to global list.
             for location in author_work.locations:
-                if location.source and not any(source.display_name == location.source.display_name for source in sources_resume.sources):
-                    sources_resume.sources.append(location.source)
+                if location.source and not any(source.id == location.source.id for source in dehydrated_sources):
+                    dehydrated_sources.append(location.source)
 
             cited_by_works = await _get_works(client, cited_by_api_url)
             cited_by: list[CitationReport] = []
-            work_citation_resume = CitationResume()
+            work_citation_summary = CitationSummary()
             for cited_by_work in cited_by_works:
                 cited_authors = _get_authors_list(authorships=cited_by_work.authorships)
                 citation_type = _get_citation_type(work_authors, cited_authors)
 
                 # Adding the type of cites in the counters.
-                report_citation_resume.add_cite_type(citation_type)
-                work_citation_resume.add_cite_type(citation_type)
+                report_citation_summary.add_cite_type(citation_type)
+                work_citation_summary.add_cite_type(citation_type)
 
                 cited_by.append(CitationReport(work=cited_by_work, citation_type=citation_type))
 
-            works.append(WorkReport(work=author_work, cited_by=cited_by, citation_resume=work_citation_resume))
+            works.append(WorkReport(work=author_work, cited_by=cited_by, citation_summary=work_citation_summary))
+
+        # Get sources full info.
+        sources: list[Source] = []
+        for dehydrated_source in dehydrated_sources:
+            source_id = identifier.get_source_id(dehydrated_source)
+            source_url = f"https://api.openalex.org/sources/{source_id}"
+            sources.append(await _get_source(client, source_url))
+
+        # Sort sources by h_index
+        sources_sorted = sorted(sources, key=lambda source: source.summary_stats.two_yr_mean_citedness, reverse=True)
+        sources_summary = SourcesSummary(sources=sources_sorted)
 
     return AuthorReport(
         author=author,
         works=works,
-        citation_resume=report_citation_resume,
-        open_access_resume=open_access_resume,
-        works_type_resume=works_type_counter,
-        sources_resume=sources_resume,
+        citation_summary=report_citation_summary,
+        open_access_summary=open_access_summary,
+        works_type_summary=works_type_counter,
+        sources_summary=sources_summary,
     )
 
 
@@ -312,10 +343,10 @@ async def make_institution_report(
 
         # Report fields.
         works: list[WorkReport] = []
-        report_citation_resume = CitationResume()
-        open_access_resume = OpenAccessResume()
+        report_citation_summary = CitationSummary()
+        open_access_summary = OpenAccessSummary()
         works_type_counter: list[WorkTypeCounter] = []
-        sources_resume = SourcesResume(sources=[])
+        dehydrated_sources: list[DehydratedSource] = []
 
         # Getting all works that have cited a work.
         for institution_work in institution_works:
@@ -326,7 +357,7 @@ async def make_institution_report(
             )
 
             # Adding the type of OpenAccess in the counter.
-            open_access_resume.add_oa_type(institution_work.open_access.oa_status)
+            open_access_summary.add_oa_type(institution_work.open_access.oa_status)
 
             # Adding the work type to works type counter.
             work_type = next((work_type for work_type in works_type_counter if work_type.type_name == institution_work.type), None)
@@ -337,29 +368,40 @@ async def make_institution_report(
 
             # Add Sources to global list.
             for location in institution_work.locations:
-                if location.source and not any(source.display_name == location.source.display_name for source in sources_resume.sources):
-                    sources_resume.sources.append(location.source)
+                if location.source and not any(source.id == location.source.id for source in dehydrated_sources):
+                    dehydrated_sources.append(location.source)
 
             cited_by_works = await _get_works(client, cited_by_api_url)
             cited_by: list[CitationReport] = []
-            work_citation_resume = CitationResume()
+            work_citation_summary = CitationSummary()
             for cited_by_work in cited_by_works:
                 cited_authors = _get_authors_list(authorships=cited_by_work.authorships)
                 citation_type = _get_citation_type(work_authors, cited_authors)
 
                 # Adding the type of cites in the counters.
-                report_citation_resume.add_cite_type(citation_type)
-                work_citation_resume.add_cite_type(citation_type)
+                report_citation_summary.add_cite_type(citation_type)
+                work_citation_summary.add_cite_type(citation_type)
 
                 cited_by.append(CitationReport(work=cited_by_work, citation_type=citation_type))
 
-            works.append(WorkReport(work=institution_work, cited_by=cited_by, citation_resume=work_citation_resume))
+            works.append(WorkReport(work=institution_work, cited_by=cited_by, citation_summary=work_citation_summary))
+
+        # Get sources full info.
+        sources: list[Source] = []
+        for dehydrated_source in dehydrated_sources:
+            source_id = identifier.get_source_id(dehydrated_source)
+            source_url = f"https://api.openalex.org/sources/{source_id}"
+            sources.append(await _get_source(client, source_url))
+
+        # Sort sources by h_index
+        sources_sorted = sorted(sources, key=lambda source: source.summary_stats.two_yr_mean_citedness, reverse=True)
+        sources_summary = SourcesSummary(sources=sources_sorted)
 
     return InstitutionReport(
         institution=institution,
         works=works,
-        citation_resume=report_citation_resume,
-        open_access_resume=open_access_resume,
-        works_type_resume=works_type_counter,
-        sources_resume=sources_resume,
+        citation_summary=report_citation_summary,
+        open_access_summary=open_access_summary,
+        works_type_summary=works_type_counter,
+        sources_summary=sources_summary,
     )

pub_analyzer/internal/templates/author/{author_resume.typ → author_summary.typ}

@@ -1,4 +1,4 @@
-// Author Resume
+// Author Summary
 = Author.
 
 // Cards
@@ -22,8 +22,9 @@
         [#align(center)[#text(size: 12pt)[Last institution:]]],
 
         // Card content
-        {% if report.author.last_known_institution %}
-        [#align(left)[#text(size: 10pt)[- *Name:* {{ report.author.last_known_institution.display_name }}]]],
+        {% if report.author.last_known_institutions%}
+        {% set last_known_institution = report.author.last_known_institutions[0] %}
+        [#align(left)[#text(size: 10pt)[- *Name:* {{ last_known_institution.display_name }}]]],
         [#align(left)[#text(size: 10pt)[- *Country:* MX]]],
         [#align(left)[#text(size: 10pt)[- *Type:* education]]],
         {% endif %}

pub_analyzer/internal/templates/author/report.typ

@@ -39,12 +39,13 @@
   columns: (1fr),
   row-gutter: 11pt,
   [#align(center, text(size: 17pt, weight: "bold")[{{ report.author.display_name }}])],
-  {% if report.author.last_known_institution %}
-  [#align(center, text(size: 15pt, weight: "thin")[{{ report.author.last_known_institution.display_name }}])],
+  {% if report.author.last_known_institutions %}
+  {% set last_known_institution = report.author.last_known_institutions[0] %}
+  [#align(center, text(size: 15pt, weight: "thin")[{{ last_known_institution.display_name }}])],
   {% endif %}
 )
 
-{% include 'author_resume.typ' %}
+{% include 'author_summary.typ' %}
 
 {% include 'works.typ' %}
 

pub_analyzer/internal/templates/author/sources.typ

@@ -2,19 +2,21 @@
 = Sources.
 
 #table(
-  columns: (auto, 3fr, 2fr, auto, auto, auto),
+  columns: (auto, 3fr, 2fr, auto, auto, auto, auto, auto),
   inset: 8pt,
   align: horizon,
   // Headers
-  [], [*Name*], [*Publisher or institution*], [*Type*], [*ISSN-L*], [*Is Open Access*],
+  [], [*Name*], [*Publisher or institution*], [*Type*], [*ISSN-L*], [*Impact factor*], [*h-index*], [*Is OA*],
 
   // Content
-  {% for source in report.sources_resume.sources %}
-  [{{ loop.index }}],
-  [#underline([#link("{{ source.id }}")[#"{{ source.display_name }}"]])],
+  {% for source in report.sources_summary.sources %}
+  [#underline[3.{{ loop.index }}. #label("source_{{ source.id.path.rpartition("/")[2] }}")]],
+  [#underline([#link("{{ source.homepage_url }}")[#"{{ source.display_name }}"]])],
   [{{ source.host_organization_name or "-" }}],
   [{{source.type }}],
   [{{ source.issn_l or "-" }}],
+  [{{ source.summary_stats.two_yr_mean_citedness|round(3) }}],
+  [{{ source.summary_stats.h_index }}],
   [{% if source.is_oa %}#text(rgb("909d63"))[True]{% else %}#text(rgb("bc5653"))[False]{% endif %}],
   {% endfor %}
 )

pub_analyzer/internal/templates/author/works.typ

@@ -9,14 +9,14 @@
   [
     #align(center)[_Citation metrics_]
     #parbreak()
-    - *Count:* {{ report.citation_resume.type_a_count + report.citation_resume.type_b_count }}
-    - *Type A:* {{ report.citation_resume.type_a_count }}
-    - *Type B:* {{ report.citation_resume.type_b_count }}
+    - *Count:* {{ report.citation_summary.type_a_count + report.citation_summary.type_b_count }}
+    - *Type A:* {{ report.citation_summary.type_a_count }}
+    - *Type B:* {{ report.citation_summary.type_b_count }}
   ],
   [
     #align(center)[_Work Type_]
     #parbreak()
-    {% for work_type in report.works_type_resume %}
+    {% for work_type in report.works_type_summary %}
     - *{{ work_type.type_name }}:* {{ work_type.count }}
     {% endfor %}
   ],
@@ -27,13 +27,13 @@
       columns: (1fr, 1fr),
       column-gutter: 15pt,
       [
-        - *gold:* {{report.open_access_resume.gold}}
-        - *green:* {{report.open_access_resume.green}}
-        - *hybrid:* {{report.open_access_resume.hybrid}}
+        - *gold:* {{report.open_access_summary.gold}}
+        - *green:* {{report.open_access_summary.green}}
+        - *hybrid:* {{report.open_access_summary.hybrid}}
       ],
       [
-        - *bronze:* {{report.open_access_resume.bronze}}
-        - *closed:* {{report.open_access_resume.closed}}
+        - *bronze:* {{report.open_access_summary.bronze}}
+        - *closed:* {{report.open_access_summary.closed}}
       ],
     )
   ],
@@ -56,9 +56,9 @@
   [{{ work.work.type }}],
   [{% if work.work.ids.doi %}#underline([#link("{{ work.work.ids.doi }}")[DOI]]){% else %}-{% endif %}],
   [{{ work.work.publication_date }}],
-  [{{ work.citation_resume.type_a_count + work.citation_resume.type_b_count }}],
-  [{{ work.citation_resume.type_a_count }}],
-  [{{ work.citation_resume.type_b_count }}],
+  [{{ work.citation_summary.type_a_count + work.citation_summary.type_b_count }}],
+  [{{ work.citation_summary.type_a_count }}],
+  [{{ work.citation_summary.type_b_count }}],
   [{{ work.work.open_access.oa_status.value }}],
   {% endfor %}
 )

pub_analyzer/internal/templates/author/works_extended.typ

@@ -39,9 +39,9 @@
   [
     #align(center)[_Citation_]
     #parbreak()
-    - *Count:* {{ work.citation_resume.type_a_count + work.citation_resume.type_b_count }}
-    - *Type A:* {{ work.citation_resume.type_a_count }}
-    - *Type B:* {{ work.citation_resume.type_b_count }}
+    - *Count:* {{ work.citation_summary.type_a_count + work.citation_summary.type_b_count }}
+    - *Type A:* {{ work.citation_summary.type_a_count }}
+    - *Type B:* {{ work.citation_summary.type_b_count }}
   ],
 )
 
@@ -83,7 +83,7 @@
   // Content
   {% for location in work.work.locations %}
   {% if location.source %}
-  [{{ loop.index }}],
+  [#underline([#link(label("source_{{ location.source.id.path.rpartition("/")[2] }}"))[{{ loop.index }}]])],
   [#underline([#link("{{ location.landing_page_url }}")[#"{{ location.source.display_name }}"]])],
   [{{ location.source.host_organization_name or "-" }}],
   [{{ location.source.type }}],

pub_analyzer/main.py

@@ -18,16 +18,17 @@ from pub_analyzer.widgets.sidebar import SideBar
 class PubAnalyzerApp(App[DOMNode]):
     """Pub Analyzer App entrypoint."""
 
+    TITLE = "Pub Analyzer"
+
     CSS_PATH: ClassVar[CSSPathType | None] = [
-        "css/author.tcss",
         "css/body.tcss",
         "css/buttons.tcss",
         "css/checkbox.tcss",
         "css/collapsible.tcss",
         "css/datatable.tcss",
-        "css/institution.tcss",
         "css/main.tcss",
         "css/report.tcss",
+        "css/summary.tcss",
         "css/search.tcss",
         "css/tabs.tcss",
         "css/tree.tcss",

pub_analyzer/models/author.py

@@ -2,7 +2,7 @@
 
 from typing import TypeAlias
 
-from pydantic import BaseModel, ConfigDict, Field, HttpUrl, field_validator
+from pydantic import BaseModel, Field, HttpUrl
 
 from pub_analyzer.models.institution import DehydratedInstitution
 
@@ -16,19 +16,11 @@ AuthorOpenAlexKey: TypeAlias = str
 class AuthorIDs(BaseModel):
     """IDs from an Author."""
 
-    openalex: str
-    orcid: str | None = ""
-    scopus: str | None = ""
-    twitter: str | None = ""
-    wikipedia: str | None = ""
-
-    # Allowing a value to be assigned during validation.
-    model_config = ConfigDict(validate_assignment=True)
-
-    @field_validator("scopus", "twitter", "wikipedia")
-    def set_default(cls, value: str) -> str:
-        """Define a default text."""
-        return value or ""
+    openalex: AuthorOpenAlexID
+    orcid: HttpUrl | None = None
+    scopus: HttpUrl | None = None
+    twitter: HttpUrl | None = None
+    wikipedia: HttpUrl | None = None
 
 
 class AuthorYearCount(BaseModel):
@@ -60,7 +52,7 @@ class Author(BaseModel):
     works_count: int
     cited_by_count: int
 
-    last_known_institution: DehydratedInstitution | None
+    last_known_institutions: list[DehydratedInstitution]
     counts_by_year: list[AuthorYearCount]
 
     summary_stats: AuthorSummaryStats
@@ -81,16 +73,8 @@ class AuthorResult(BaseModel):
 
     id: AuthorOpenAlexID
     display_name: str
-    hint: str | None = ""
+    hint: str | None = None
     cited_by_count: int
     works_count: int
     entity_type: str
-    external_id: str | None = ""
-
-    # Allowing a value to be assigned during validation.
-    model_config = ConfigDict(validate_assignment=True)
-
-    @field_validator("hint", "external_id")
-    def set_default(cls, value: str) -> str:
-        """Define a default text."""
-        return value or ""
+    external_id: str | None = None

pub_analyzer/models/concept.py

@@ -0,0 +1,19 @@
+"""Concept model from OpenAlex API Schema definition."""
+
+from pydantic import BaseModel, HttpUrl
+
+
+class DehydratedConcept(BaseModel):
+    """Stripped-down Concept Model."""
+
+    id: HttpUrl
+    """The OpenAlex ID for this concept."""
+    display_name: str
+    """The English-language label of the concept."""
+
+    wikidata: HttpUrl
+    """The Wikidata ID for this concept. All OpenAlex concepts are also Wikidata concepts."""
+    level: int
+    """The level in the concept. Lower-level concepts are more general, and higher-level concepts are more specific."""
+    score: float
+    """The strength of the connection between the work and this concept (higher is stronger)."""