chore: add CI and modernize test deps

Author: philippb

.github/workflows/ci.yml

@@ -0,0 +1,33 @@
+name: CI
+
+on:
+  push:
+  pull_request:
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version-file: .python-version
+
+      - name: Configure git for private deps
+        run: |
+          git config --global url."https://x-access-token:${{ secrets.GITHUB_TOKEN }}@github.com/".insteadOf "https://github.com/"
+
+      - name: Install dependencies
+        run: |
+          python -m pip install -U pip
+          python -m pip install -r requirements-dev.txt
+
+      - name: Lint
+        run: |
+          flake8 validator tests
+
+      - name: Test
+        run: |
+          pytest -q

.python-version

@@ -1 +1 @@
-3.11
+3.12.12

.travis.yml

@@ -1,4 +1,4 @@
 -r requirements.txt
-flake8==3.6.0
-nose
-coverage
+flake8==7.1.1
+pytest>=8
+coverage==7.6.1

requirements-dev.txt

@@ -1,4 +1,5 @@
-beautifulsoup4==4.4.1
+beautifulsoup4==4.14.3
+sdiff @ git+https://github.com/KeepSafe/[email protected]#egg=sdiff
 Markdown
 html2text==2014.12.29
 lxml==6.0.2

requirements.txt

@@ -1,5 +1,7 @@
 from unittest import TestCase
 
+import pytest
+
 from validator import parsers
 
 from tests.utils import read
@@ -10,3 +12,18 @@ def test_xml_parsing(self):
         content = read('tests/fixtures/bugs/parser_bug.xml')
         parser = parsers.XmlParser()
         parser.parse(content)
+
+
+def test_xml_parser_empty_returns_empty():
+    parser = parsers.XmlParser()
+
+    assert parser.parse('   ') == ''
+
+
+def test_chain_parser_wraps_errors():
+    parser = parsers.ChainParser([parsers.XmlParser()])
+
+    with pytest.raises(parsers.ParserError) as exc:
+        parser.parse('<root><broken></root>')
+
+    assert 'error in content' in str(exc.value)

tests/test_parser.py

@@ -0,0 +1,31 @@
+from validator.errors import ContentData, MdDiff, UrlDiff
+from validator.reports import HtmlReporter
+
+
+def test_html_reporter_handles_url_diff(tmp_path):
+    reporter = HtmlReporter(output_directory=str(tmp_path))
+    error = UrlDiff('http://example.com', files=['errors/source.md'], status_code=404)
+
+    reporter.report([error])
+
+    report_path = tmp_path / 'errors' / 'source.html'
+    assert report_path.exists()
+    assert 'http://example.com returned with code 404' in report_path.read_text()
+
+
+def test_html_reporter_writes_markdown_diff(tmp_path):
+    reporter = HtmlReporter(output_directory=str(tmp_path))
+    base = ContentData('base.md', 'Base', '<del>Base</del>', '<p>Base</p>')
+    other = ContentData('other.md', 'Other', '<ins>Other</ins>', '<p>Other</p>')
+    error = MdDiff(base, other, ['Missing content'])
+
+    reporter.report([error])
+
+    report_path = tmp_path / 'other.html'
+    assert report_path.exists()
+    content = report_path.read_text()
+    assert 'Missing content' in content
+    assert '<del>' in content
+    assert '<ins>' in content
+    assert 'Base' in content
+    assert 'Other' in content

tests/test_reports.py

@@ -1,3 +1,5 @@
+from pathlib import Path
+
 from bs4 import BeautifulSoup
 import shutil
 import markdown
@@ -94,13 +96,17 @@ def _add_content(self, soup, tag_id, content):
     # TODO remove isinstance
     def report(self, errors):
         shutil.rmtree(self.output_directory, ignore_errors=True)
+        if self.output_directory:
+            Path(self.output_directory).mkdir(parents=True, exist_ok=True)
         for error in errors:
             # TODO save to different files for links and diff
             # TODO use mustache for templates
             report_soup = BeautifulSoup(self.report_template, 'lxml')
+            source_path = None
             if isinstance(error, UrlDiff):
                 messages = [f'<span>{error.url} returned with code {error.status_code}</span>']
                 self._add_content(report_soup, 'urls', '\n'.join(messages))
+                source_path = error.files[0] if error.files else 'url_errors'
             if isinstance(error, MdDiff):
                 error_msgs = '<br />'.join(map(lambda i: str(i), error.error_msgs))
                 base = markdown.markdown(error.base.parsed)
@@ -110,7 +116,9 @@ def report(self, errors):
                 report_soup = self._add_content(report_soup, 'left_diff', BeautifulSoup(error.base.diff, 'lxml').body)
                 report_soup = self._add_content(report_soup, 'right_diff', BeautifulSoup(error.other.diff, 'lxml').body)
                 report_soup = self._add_content(report_soup, 'error_msgs', BeautifulSoup(error_msgs, 'lxml').body)
-            save_report(self.output_directory, error.other.original, report_soup.prettify())
+                source_path = error.other.original
+            if source_path is not None:
+                save_report(self.output_directory, source_path, report_soup.prettify())
 
 
 class ConsoleReporter: