Add support for patents; Add support for month ordering

src/pelican/plugins/pybtex/__init__.py

@@ -3,6 +3,7 @@
 # SPDX-License-Identifier: MIT
 """Manage your academic publications page with Pelican and pybtex (BibTeX)."""
 
+from . import style as _  # noqa: F401, monkey-patches to support extra entries
 from .injector import PybtexInjector
 
 _injector = PybtexInjector()

src/pelican/plugins/pybtex/style.py

@@ -0,0 +1,76 @@
+# SPDX-FileCopyrightText: Copyright © 2024 André Anjos <[email protected]>
+# SPDX-License-Identifier: MIT
+"""Monkey-patch standard style from pybtex to support some extra entry
+types.
+"""
+
+from pybtex.style.formatting import toplevel
+import pybtex.style.formatting.unsrt
+from pybtex.style.formatting.unsrt import date
+from pybtex.style.template import field, node, optional, sentence, tag, words
+
+
+def _monkeypatch_method(cls):
+    def decorator(func):
+        setattr(cls, func.__name__, func)
+        return func
+
+    return decorator
+
+
+@_monkeypatch_method(pybtex.style.formatting.unsrt.Style)
+def get_patent_template(self, e):
+    """Format patent bibtex entry.
+
+    Parameters
+    ----------
+    e
+        The entry to be formatted.
+
+    Returns
+    -------
+        The formatted entry object.
+    """
+    return toplevel[
+        sentence[self.format_names("author")],
+        self.format_title(e, "title"),
+        sentence(capfirst=False)[tag("em")[field("number")], date],
+        optional[self.format_url(e), optional[" (visited on ", field("urldate"), ")"]],
+    ]
+
+
+# format month by converting integers to month name
+_MONTH_NAMES = {
+    1: "January",
+    2: "February",
+    3: "March",
+    4: "April",
+    5: "May",
+    6: "June",
+    7: "July",
+    8: "August",
+    9: "September",
+    10: "October",
+    11: "November",
+    12: "December",
+}
+
+
+@node
+def _month_field(children, data):
+    assert not children
+    m = data["entry"].fields.get("month")
+    try:
+        m = int(m)
+        # normalize
+        m = 1 if m < 1 else m
+        m = len(_MONTH_NAMES) if m > len(_MONTH_NAMES) else m
+        # reset
+        data["entry"].fields["month"] = _MONTH_NAMES[m]
+    except (TypeError, ValueError):
+        pass
+    return optional[field("month")].format_data(data)
+
+
+# Ensures we always have the month correctly formatted
+pybtex.style.formatting.unsrt.date = words[_month_field(), field("year")]

src/pelican/plugins/pybtex/templates/publications.html

@@ -23,9 +23,9 @@ <h2>
 
     {% block content_pybtex %}
     <div id="pybtex">
-        {% for group in publications|groupby("year")|reverse %}
+        {% for group in publications|groupby(attribute="year")|reverse %}
         <h3 id="{{ group.grouper }}">{{ group.grouper }}</h3>
-            {% for item in group.list %}
+            {% for item in group.list|sort(attribute="month")|reverse %}
             <details id="pybtex-{{ item.key }}">
                 <summary>{{ item.html }}</summary>
                 {{ item.bibtex }}

src/pelican/plugins/pybtex/utils.py

@@ -126,12 +126,44 @@ def format_bibtex_pygments(
     )
 
 
+_MONTH_NUMBERS: dict[str, int] = {
+    "unk": 0,
+    "jan": 1,
+    "feb": 2,
+    "mar": 3,
+    "apr": 4,
+    "may": 5,
+    "jun": 6,
+    "jul": 7,
+    "aug": 8,
+    "sep": 9,
+    "oct": 10,
+    "nov": 11,
+    "dec": 12,
+}
+
+
+def _get_month_number(m: str) -> int:
+    """Get the month number or 0, if that is not known.
+
+    Parameters
+    ----------
+    m
+        The name of the month.
+
+    Returns
+    -------
+        An integer, representing the month number.
+    """
+    return _MONTH_NUMBERS[m.lower()[:3]]
+
+
 def generate_context(
     bibdata: typing.Sequence[pybtex.database.BibliographyData],
     style_name: str,
     extra_fields: typing.Sequence[str],
     html_formatter_options: dict[str, typing.Any],
-) -> list[dict[str, str]]:
+) -> list[dict[str, str | int]]:
     """Generate a list of dictionaries given a set of bibliography databases.
 
     Parameters
@@ -153,11 +185,13 @@ def generate_context(
         order) from the input databases. Each entry in the list contains at least the
         following keys:
 
-            * ``key``: The BibTeX database key
-            * ``year``: The year of the entry
-            * ``html``: An HTML-formatted version of the entry
+            * ``label``: The attribute label by the formatting style (str)
+            * ``key``: The BibTeX database key (str)
+            * ``year``: The year of the entry (int)
+            * ``month``: A string-fied version of the month number (int)
+            * ``html``: An HTML-formatted version of the entry (str)
             * ``bibtex``: An HTML-ready (pygments-highlighted) BibTeX-formatted version of
-              the entry
+              the entry (str)
 
         More keys as defined by ``extra_fiedls`` may also be present in case they are
         found in the original database entry.  These fields are copied verbatim to this
@@ -189,7 +223,7 @@ def generate_context(
     ]
 
     backend = pybtex.backends.html.Backend()
-    retval: list[dict[str, str]] = []
+    retval: list[dict[str, str | int]] = []
     for entry, formatted_entry in zip(all_entries, formatted_entries):
         # make entry text, and then pass it through pygments for highlighting
         assert entry.fields is not None
@@ -198,7 +232,8 @@ def generate_context(
             {
                 "label": typing.cast(str, formatted_entry.label),
                 "key": formatted_entry.key,
-                "year": entry.fields.get("year"),
+                "year": int(entry.fields.get("year", 0)),
+                "month": _get_month_number(entry.fields.get("month", "unk")),
                 "html": formatted_entry.text.render(backend),
                 "bibtex": format_bibtex_pygments(entry, html_formatter_options),
             }

tests/data/biblio-patent/content/article.bib

@@ -0,0 +1,13 @@
+%% SPDX-FileCopyrightText: Copyright © 2024 André Anjos <andre.dos.anjos-at-gmail.com>
+%% SPDX-License-Identifier: MIT
+
+@patent{pat,
+    author = "A. G. Bell",
+    title = "Improvement in telegraphy",
+    nationality = "United States",
+    number = "174465",
+    day = "7",
+    month = Mar,
+    year = "1876",
+    url = "https://www.google.com/patents/US174465",
+}

tests/data/biblio-patent/content/article.rst

@@ -0,0 +1,16 @@
+.. SPDX-FileCopyrightText: Copyright © 2024 André Anjos <[email protected]>
+.. SPDX-License-Identifier: MIT
+
+This is an article
+##################
+
+:date: 2010-10-03 10:20
+:modified: 2010-10-04 18:40
+:tags: test, article
+:category: bibliography
+:slug: article
+:authors: André Anjos
+:summary: Short version for index and feeds
+:pybtex_sources: article.bib
+
+This will be turned into a citation [@@pat].

tests/data/biblio-patent/pelicanconf.py

@@ -0,0 +1,3 @@
+# SPDX-FileCopyrightText: Copyright © 2024 André Anjos <[email protected]>
+# SPDX-License-Identifier: MIT
+PATH = "content"

tests/data/month-ordering/content/publications.bib

@@ -0,0 +1,29 @@
+%% SPDX-FileCopyrightText: Copyright © 2024 André Anjos <andre.dos.anjos-at-gmail.com>
+%% SPDX-License-Identifier: MIT
+
+@misc{no-month,
+    title = "Misc title 1",
+    author = "Author Last",
+    year = 2015,
+}
+
+@misc{month-short,
+    title = "Misc with short month name",
+    author = "Author Last",
+    year = 2015,
+    month = jan,
+}
+
+@misc{month-long,
+    title = "Misc with short month name",
+    author = "Author Last",
+    year = 2015,
+    month = "June",
+}
+
+@misc{month-number,
+    title = "Misc with numbered month",
+    author = "Author Last",
+    year = 2015,
+    month = 3,
+}

tests/data/month-ordering/pelicanconf.py

@@ -0,0 +1,4 @@
+# SPDX-FileCopyrightText: Copyright © 2024 André Anjos <[email protected]>
+# SPDX-License-Identifier: MIT
+PATH = "content"
+PYBTEX_SOURCES = ["publications.bib"]

tests/test_pybtex.py

@@ -148,6 +148,53 @@ def test_publications_simple(
     )
 
 
+@pytest.mark.parametrize("subdir", ["month-ordering"])
+def test_publications_month_ordering(
+    setup_pelican: tuple[list[logging.LogRecord], pathlib.Path],
+):
+    records, pelican_output = setup_pelican
+
+    publications_html = pelican_output / "publications.html"
+    assert publications_html.exists()
+
+    with publications_html.open() as f:
+        soup = BeautifulSoup(f, "html.parser")
+
+    div = soup.find_all("div", id="pybtex")
+    assert len(div) == 1
+
+    publication_keys = [
+        "month-long",
+        "month-number",
+        "month-short",
+        "no-month",
+    ]
+    details = div[0].find_all("details")
+    assert len(details) == len(publication_keys)
+
+    for k, detail in enumerate(details):
+        # should correspond to one of the expected entries
+        assert detail.attrs["id"][len("pybtex-") :] == publication_keys[k]
+
+        # it should contain the bibtex entry
+        pre = detail.find_all("pre")
+        assert len(pre) == 1
+
+        # check pygments filtered the BibTeX entry
+        assert "highlight" in pre[0].parent.attrs["class"]
+
+        # the bibtex entry should start with @
+        assert detail.pre.text.startswith("@")
+
+    _assert_log_no_errors(records)
+    _assert_log_contains(
+        records,
+        message="plugin detected 4 entries spread across 1 source file",
+        level=logging.INFO,
+        count=1,
+    )
+
+
 @pytest.mark.parametrize("subdir", ["urls"])
 def test_publications_urls(setup_pelican: tuple[list[logging.LogRecord], pathlib.Path]):
     records, pelican_output = setup_pelican
@@ -277,6 +324,57 @@ def test_biblio_at_article(setup_pelican: tuple[list[logging.LogRecord], pathlib
     )
 
 
+@pytest.mark.parametrize("subdir", ["biblio-patent"])
+def test_biblio_patent(setup_pelican: tuple[list[logging.LogRecord], pathlib.Path]):
+    records, pelican_output = setup_pelican
+
+    article_html = pelican_output / "article.html"
+    assert article_html.exists()
+
+    publications_html = pelican_output / "publications.html"
+    assert not publications_html.exists()
+
+    with article_html.open() as f:
+        soup = BeautifulSoup(f, "html.parser")
+
+    publication_keys = [
+        "pat",
+    ]
+
+    para = soup.find_all("p")
+
+    text_to_be_checked = ((publication_keys[0], "1", para[0]),)
+
+    for key, label, paragraph in text_to_be_checked:
+        a = paragraph.find_all("a")
+        text_label = f"[{label}]"
+        assert len(a) == 1
+        assert text_label in a[0].attrs["title"]
+        assert a[0].attrs["href"].startswith("#")  # internal
+        assert a[0].attrs["href"].endswith(key)
+        assert a[0].text == text_label
+
+    num_headers = 2
+    h2 = soup.find_all("h2")
+    assert len(h2) == num_headers
+
+    assert h2[1].text.strip() == "Bibliography"
+
+    div = soup.find_all("div", id="pybtex")
+    assert len(div) == 1
+
+    details = div[0].find_all("details")
+    assert len(details) == len(publication_keys)
+
+    # prefixed by "pybtex-"
+    assert details[0].attrs["id"].endswith(publication_keys[0])
+
+    _assert_log_no_errors(records)
+    _assert_log_contains(
+        records, message="plugin detected no entries", level=logging.INFO, count=1
+    )
+
+
 @pytest.mark.parametrize("subdir", ["biblio-alpha"])
 def test_biblio_alpha(setup_pelican: tuple[list[logging.LogRecord], pathlib.Path]):
     records, pelican_output = setup_pelican