Merge pull request #60 from GateNLP/release/1.1.0

Release 1.1.0

.github/workflows/lint.yml

@@ -20,7 +20,7 @@ jobs:
     steps:
       - uses: actions/checkout@v4
       - name: Install Poetry
-        run: pipx install poetry==1.8.3
+        run: pipx install poetry==2.0.1
       - name: Setup Python 3.8
         uses: actions/setup-python@v5
         with:

.github/workflows/publish.yml

@@ -14,7 +14,7 @@ jobs:
     steps:
       - uses: actions/checkout@v4
       - name: Install Poetry
-        run: pipx install poetry==1.8.3
+        run: pipx install poetry==2.0.1
       - name: Set up Python 3.8
         uses: actions/setup-python@v5
         with:

.github/workflows/test.yml

@@ -20,12 +20,12 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        python-version: ["3.8", "3.9", "3.10", "3.11", "3.12"]
+        python-version: ["3.8", "3.9", "3.10", "3.11", "3.12", "3.13"]
 
     steps:
       - uses: actions/checkout@v4
       - name: Install Poetry
-        run: pipx install poetry==1.8.3
+        run: pipx install poetry==2.0.1
       - name: Setup Python ${{ matrix.python-version }}
         uses: actions/setup-python@v5
         with:

.github/workflows/test_integration.yml

@@ -16,7 +16,7 @@ jobs:
     steps:
       - uses: actions/checkout@v4
       - name: Install Poetry
-        run: pipx install poetry==1.8.3
+        run: pipx install poetry==2.0.1
       - name: Setup Python ${{ matrix.python-version }}
         uses: actions/setup-python@v5
         with:

.readthedocs.yaml

@@ -19,7 +19,7 @@ build:
     post_create_environment:
       # Install poetry
       # https://python-poetry.org/docs/#installing-manually
-      - pip install poetry
+      - pip install poetry==2.0.1
     post_install:
       # Install dependencies with 'docs' dependency group
       # https://python-poetry.org/docs/managing-dependencies/#dependency-groups

docs/changelog.rst

@@ -1,6 +1,15 @@
 Changelog
 =========
 
+v1.1.0 (2025-01-20)
+-------------------
+
+**New Features**
+
+* Added support for :ref:`alternate localised pages <sitemap-extra-localisation>` with ``hreflang``.
+* If an HTTP error is encountered, the contents of the error page is logged at ``INFO`` level.
+* Added optional configurable wait time to HTTP request client.
+
 v1.0.0 (2025-01-13)
 -------------------
 

docs/reference/formats.rst

@@ -132,6 +132,8 @@ The Google News extension provides additional information to describe the news s
 
 If the page contains Google News data, it is stored as a :class:`~usp.objects.page.SitemapNewsStory` object in :attr:`SitemapPage.news_story <usp.objects.page.SitemapPage.news_story>`.
 
+.. _google-image-ext:
+
 Google Image
 """"""""""""
 
@@ -150,6 +152,27 @@ If the page contains Google Image data, it is stored as a list of :class:`~usp.o
 
 .. _xml date:
 
+Additional Features
+^^^^^^^^^^^^^^^^^^^
+
+Beyond the Sitemap specification, USP also supports some non-standard features used by large sitemap consumers (e.g. Google).
+
+.. _sitemap-extra-localisation:
+
+Alternate Localised Pages
+"""""""""""""""""""""""""
+
+- `Google documentation <https://developers.google.com/search/docs/specialty/international/localized-versions#sitemap>`__
+
+.. dropdown:: Example
+    :class-container: flush
+
+    .. literalinclude:: formats_examples/hreflang.xml
+        :emphasize-lines: 3,7-10,15-18
+        :language: xml
+
+Alternate localised pages specified with the ``<link>`` tag will be stored as a list in :attr:`SitemapPage.alternates <usp.objects.page.SitemapPage.alternates>`. Language codes are not validated.
+
 Date Time Parsing
 ^^^^^^^^^^^^^^^^^
 

docs/reference/formats_examples/hreflang.xml

@@ -0,0 +1,20 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9/"
+    xmlns:xhtml="http://www.w3.org/1999/xhtml">
+    <url>
+        <loc>https://example.org/en/page</loc>
+        <lastmod>2024-01-01</lastmod>
+        <xhtml:link
+            rel="alternate"
+            hreflang="fr-FR"
+            href="https://example.org/fr/page"/>
+    </url>
+    <url>
+        <loc>https://example.org/fr/page</loc>
+        <lastmod>2024-01-02</lastmod>
+        <xhtml:link
+            rel="alternate"
+            hreflang="en-GB"
+            href="https://example.org/en/page"/>
+    </url>
+</urlset>