pub-analyzer 0.4.2__tar.gz → 0.5.0__tar.gz

{pub_analyzer-0.4.2 → pub_analyzer-0.5.0}/PKG-INFO

@@ -1,8 +1,7 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.3
 Name: pub-analyzer
-Version: 0.4.2
+Version: 0.5.0
 Summary: A text user interface, written in python, which automates the generation of scientific production reports using OpenAlex
-Home-page: https://github.com/alejandrgaspar/pub-analyzer
 License: MIT
 Author: Alejandro Gaspar
 Author-email: alejandro@gaspar.land
@@ -23,12 +22,12 @@ Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Programming Language :: Python :: 3.13
 Classifier: Typing :: Typed
-Requires-Dist: httpx (==0.27.2)
-Requires-Dist: jinja2 (==3.1.4)
-Requires-Dist: pydantic (==2.9.2)
-Requires-Dist: textual (==0.70.0)
-Requires-Dist: typst (==0.11.1)
+Requires-Dist: httpx (==0.28.1)
+Requires-Dist: pydantic (==2.11.7)
+Requires-Dist: textual (==0.85.2)
+Requires-Dist: typst (==0.13.2)
 Project-URL: Documentation, https://pub-analyzer.com/
+Project-URL: Homepage, https://github.com/alejandrgaspar/pub-analyzer
 Project-URL: Repository, https://github.com/alejandrgaspar/pub-analyzer
 Description-Content-Type: text/markdown
 

pub_analyzer-0.5.0/pub_analyzer/css/editor.tcss

@@ -0,0 +1,60 @@
+/* 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;
+$text-primary-color-darken: black;
+
+$primary-color: #b91c1c;
+$primary-color-accent: #991b1b;
+$primary-color-highlight: #dc2626;
+
+TextEditor {
+    #dialog {
+        margin: 0 10;
+        min-height: 10vh;
+        max-height: 60vh;
+    }
+
+    #text-editor-container {
+        height: 1fr;
+    }
+
+    TextArea{
+        height: auto;
+        padding: 1 3;
+
+        background: $bg-main-color;
+        border: none;
+
+        .text-area--cursor {
+            background: $primary-color;
+        }
+        .text-area--cursor-gutter {
+            color: $bg-main-color;
+            background: $primary-color-accent;
+        }
+        .text-area--cursor-line {
+            background: $bg-main-color;
+        }
+        .text-area--matching-bracket {
+            background: $primary-color-highlight 30%;
+        }
+
+    }
+
+    #actions-buttons {
+        height: 3;
+        margin-top: 1;
+        margin-bottom: 2;
+
+        align: center middle;
+
+        Button {
+            margin: 0 5;
+        }
+    }
+}

{pub_analyzer-0.4.2 → pub_analyzer-0.5.0}/pub_analyzer/css/report.tcss

@@ -67,29 +67,29 @@ LoadReportWidget .button-container {
 }
 
 /* Export Report Pane */
-ExportReportPane #export-form {
+#export-form {
     height: auto;
 }
 
-ExportReportPane .export-form-input-container {
+.export-form-input-container {
     height: auto;
     margin-bottom: 2;
 }
 
-ExportReportPane .export-form-label {
+.export-form-label {
     width: 25vw;
     border-bottom: solid $text-primary-color;
 }
 
-ExportReportPane .file-selector-container {
+.file-selector-container {
     height: 3;
 }
 
-ExportReportPane .export-form-input {
+.export-form-input {
     width: 50vw;
 }
 
-ExportReportPane .export-form-buttons {
+.export-form-buttons {
     align: center middle;
     height: 3;
 }
@@ -113,6 +113,15 @@ WorkModal #dialog .abstract {
     padding: 1 2;
 }
 
+WorkModal TabPane EditWidget {
+    height: 3;
+    margin-top: 1;
+
+    Horizontal {
+        align: center middle;
+    }
+}
+
 WorkModal #dialog #tables-container {
     margin: 1 0;
 }

pub_analyzer-0.5.0/pub_analyzer/internal/render.py

@@ -0,0 +1,41 @@
+"""Render reports."""
+
+import pathlib
+import time
+from importlib.metadata import version
+
+import typst
+from textual import log
+
+from pub_analyzer.models.report import AuthorReport, InstitutionReport
+
+
+def render_report(report: AuthorReport | InstitutionReport, file_path: pathlib.Path | None) -> bytes | None:
+    """Render report to PDF.
+
+    Args:
+        report: Report Model.
+        file_path: Path to save the compiled file.
+
+    Returns:
+        PDF bytes or None if output file path is defined.
+
+    Raises:
+        SyntaxError: If typst compiler syntax error.
+    """
+    if isinstance(report, AuthorReport):
+        templates_path = pathlib.Path(__file__).parent.resolve().joinpath("templates")
+        typst_file = templates_path / "author_report.typ"
+    if isinstance(report, InstitutionReport):
+        raise NotImplementedError
+
+    sys_inputs = {"report": report.model_dump_json(by_alias=True), "version": version("pub-analyzer")}
+
+    start_time = time.time()
+    if file_path:
+        result = typst.compile(input=typst_file, output=file_path, sys_inputs=sys_inputs)
+    else:
+        result = typst.compile(input=typst_file, sys_inputs=sys_inputs)
+
+    log.info(f"Typst compile time: {round((time.time() - start_time), 2)} seconds.")
+    return result

{pub_analyzer-0.4.2 → pub_analyzer-0.5.0}/pub_analyzer/internal/report.py

@@ -6,6 +6,7 @@ from typing import Any, NewType
 
 import httpx
 from pydantic import TypeAdapter
+from textual import log
 
 from pub_analyzer.internal import identifier
 from pub_analyzer.models.author import Author, AuthorOpenAlexKey, AuthorResult, DehydratedAuthor
@@ -138,7 +139,14 @@ def _get_valid_works(works: list[dict[str, Any]]) -> list[dict[str, Any]]:
         In response, we have chosen to exclude such works at this stage, thus avoiding
         the need to handle exceptions within the Model validators.
     """
-    return [_add_work_abstract(work) for work in works if work["title"] is not None]
+    valid_works = []
+    for work in works:
+        if work["title"] is not None:
+            valid_works.append(_add_work_abstract(work))
+        else:
+            log.warning(f"Discarded work: {work['id']}")
+
+    return valid_works
 
 
 async def _get_works(client: httpx.AsyncClient, url: str) -> list[Work]:
@@ -156,7 +164,7 @@ async def _get_works(client: httpx.AsyncClient, url: str) -> list[Work]:
     Raises:
         httpx.HTTPStatusError: One response from OpenAlex API had an error HTTP status of 4xx or 5xx.
     """
-    response = await client.get(url=url)
+    response = await client.get(url=url, follow_redirects=True)
     response.raise_for_status()
 
     json_response = response.json()
@@ -166,7 +174,7 @@ async def _get_works(client: httpx.AsyncClient, url: str) -> list[Work]:
     works_data = list(_get_valid_works(json_response["results"]))
 
     for page_number in range(1, page_count):
-        page_result = (await client.get(url + f"&page={page_number + 1}")).json()
+        page_result = (await client.get(url + f"&page={page_number + 1}", follow_redirects=True)).json()
         works_data.extend(_get_valid_works(page_result["results"]))
 
     return TypeAdapter(list[Work]).validate_python(works_data)
@@ -185,10 +193,17 @@ async def _get_source(client: httpx.AsyncClient, url: str) -> Source:
     Raises:
         httpx.HTTPStatusError: One response from OpenAlex API had an error HTTP status of 4xx or 5xx.
     """
-    response = await client.get(url=url)
+    response = await client.get(url=url, follow_redirects=True)
     response.raise_for_status()
 
-    return Source(**response.json())
+    json_response = response.json()
+    hp_url = json_response["homepage_url"]
+    if isinstance(hp_url, str):
+        if not hp_url.startswith(("http", "https")):
+            json_response["homepage_url"] = None
+            log.warning(f"Discarted source homepage url: {url}")
+
+    return Source(**json_response)
 
 
 async def make_author_report(
@@ -242,8 +257,11 @@ async def make_author_report(
         dehydrated_sources: list[DehydratedSource] = []
 
         # Getting all works that have cited the author.
-        for author_work in author_works:
+        author_works_count = len(author_works)
+        for idx_work, author_work in enumerate(author_works, 1):
             work_id = identifier.get_work_id(author_work)
+            log.info(f"[{work_id}] Work [{idx_work}/{author_works_count}]")
+
             work_authors = _get_authors_list(authorships=author_work.authorships)
             cited_by_api_url = (
                 f"https://api.openalex.org/works?filter=cites:{work_id}{cited_from_filter}{cited_to_filter}&sort=publication_date"
@@ -281,9 +299,12 @@ async def make_author_report(
 
         # Get sources full info.
         sources: list[Source] = []
-        for dehydrated_source in dehydrated_sources:
+        sources_count = len(dehydrated_sources)
+        for idx, dehydrated_source in enumerate(dehydrated_sources, 1):
             source_id = identifier.get_source_id(dehydrated_source)
             source_url = f"https://api.openalex.org/sources/{source_id}"
+
+            log.info(f"Getting Sources... [{idx}/{sources_count}]")
             sources.append(await _get_source(client, source_url))
 
         # Sort sources by h_index
@@ -349,8 +370,11 @@ async def make_institution_report(
         dehydrated_sources: list[DehydratedSource] = []
 
         # Getting all works that have cited a work.
-        for institution_work in institution_works:
+        institution_works_count = len(institution_works)
+        for idx_work, institution_work in enumerate(institution_works, 1):
             work_id = identifier.get_work_id(institution_work)
+            log.info(f"[{work_id}] Work [{idx_work}/{institution_works_count}]")
+
             work_authors = _get_authors_list(authorships=institution_work.authorships)
             cited_by_api_url = (
                 f"https://api.openalex.org/works?filter=cites:{work_id}{cited_from_filter}{cited_to_filter}&sort=publication_date"
@@ -388,9 +412,12 @@ async def make_institution_report(
 
         # Get sources full info.
         sources: list[Source] = []
-        for dehydrated_source in dehydrated_sources:
+        sources_count = len(dehydrated_sources)
+        for idx, dehydrated_source in enumerate(dehydrated_sources, 1):
             source_id = identifier.get_source_id(dehydrated_source)
             source_url = f"https://api.openalex.org/sources/{source_id}"
+
+            log.debug(f"[{work_id}] Getting Sources... [{idx}/{sources_count}]")
             sources.append(await _get_source(client, source_url))
 
         # Sort sources by h_index