mirror of
https://github.com/vinta/awesome-python.git
synced 2026-03-23 13:56:43 +08:00
refactor: extract parsing logic from build.py into readme_parser module
slugify, parse_readme, count_entries, extract_preview, render_content_html, and related helpers are moved to a dedicated readme_parser module. build.py now imports from readme_parser rather than defining these inline. Tests for the removed functions are dropped from test_build.py since they now live with the module they test. Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
Vinta Chen
@@ -7,21 +7,15 @@ import sys
|
||||
import textwrap
|
||||
from pathlib import Path
|
||||
|
||||
import pytest
|
||||
|
||||
sys.path.insert(0, os.path.join(os.path.dirname(__file__), ".."))
|
||||
from build import (
|
||||
build,
|
||||
count_entries,
|
||||
extract_github_repo,
|
||||
extract_preview,
|
||||
group_categories,
|
||||
load_stars,
|
||||
parse_readme,
|
||||
render_content_html,
|
||||
slugify,
|
||||
sort_entries,
|
||||
)
|
||||
from readme_parser import slugify
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# slugify
|
||||
@@ -51,244 +45,6 @@ class TestSlugify:
|
||||
assert slugify(" Date and Time ") == "date-and-time"
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# count_entries
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
class TestCountEntries:
|
||||
def test_counts_dash_entries(self):
|
||||
assert count_entries("- [a](url) - Desc.\n- [b](url) - Desc.") == 2
|
||||
|
||||
def test_counts_star_entries(self):
|
||||
assert count_entries("* [a](url) - Desc.") == 1
|
||||
|
||||
def test_ignores_non_entries(self):
|
||||
assert count_entries("Some text\n- [a](url) - Desc.\nMore text") == 1
|
||||
|
||||
def test_counts_indented_entries(self):
|
||||
assert count_entries(" - [a](url) - Desc.") == 1
|
||||
|
||||
def test_empty_content(self):
|
||||
assert count_entries("") == 0
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# extract_preview
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
class TestExtractPreview:
|
||||
def test_basic(self):
|
||||
content = "* [alpha](url) - A.\n* [beta](url) - B.\n* [gamma](url) - C."
|
||||
assert extract_preview(content) == "alpha, beta, gamma"
|
||||
|
||||
def test_max_four(self):
|
||||
content = "\n".join(f"* [lib{i}](url) - Desc." for i in range(10))
|
||||
assert extract_preview(content) == "lib0, lib1, lib2, lib3"
|
||||
|
||||
def test_empty(self):
|
||||
assert extract_preview("") == ""
|
||||
|
||||
def test_skips_subcategory_labels(self):
|
||||
content = "* Synchronous\n* [django](url) - Framework.\n* [flask](url) - Micro."
|
||||
assert extract_preview(content) == "django, flask"
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# render_content_html
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
class TestRenderContentHtml:
|
||||
def test_basic_entry(self):
|
||||
content = "* [django](https://example.com) - A web framework."
|
||||
html = render_content_html(content)
|
||||
assert 'href="https://example.com"' in html
|
||||
assert "django" in html
|
||||
assert "A web framework." in html
|
||||
assert 'class="entry"' in html
|
||||
|
||||
def test_subcategory_label(self):
|
||||
content = "* Synchronous\n* [django](https://x.com) - Framework."
|
||||
html = render_content_html(content)
|
||||
assert 'class="subcat"' in html
|
||||
assert "Synchronous" in html
|
||||
|
||||
def test_sub_entry(self):
|
||||
content = "* [django](https://x.com) - Framework.\n * [awesome-django](https://y.com)"
|
||||
html = render_content_html(content)
|
||||
assert 'class="entry-sub"' in html
|
||||
assert "awesome-django" in html
|
||||
|
||||
def test_link_only_entry(self):
|
||||
content = "* [tool](https://x.com)"
|
||||
html = render_content_html(content)
|
||||
assert 'href="https://x.com"' in html
|
||||
assert "tool" in html
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# parse_readme
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
MINIMAL_README = textwrap.dedent("""\
|
||||
# Awesome Python
|
||||
|
||||
Some intro text.
|
||||
|
||||
---
|
||||
|
||||
## Alpha
|
||||
|
||||
_Libraries for alpha stuff._
|
||||
|
||||
- [lib-a](https://example.com/a) - Does A.
|
||||
- [lib-b](https://example.com/b) - Does B.
|
||||
|
||||
## Beta
|
||||
|
||||
_Tools for beta._
|
||||
|
||||
- [lib-c](https://example.com/c) - Does C.
|
||||
|
||||
# Resources
|
||||
|
||||
Where to discover resources.
|
||||
|
||||
## Newsletters
|
||||
|
||||
- [News One](https://example.com/n1)
|
||||
- [News Two](https://example.com/n2)
|
||||
|
||||
## Podcasts
|
||||
|
||||
- [Pod One](https://example.com/p1)
|
||||
|
||||
# Contributing
|
||||
|
||||
Please contribute!
|
||||
""")
|
||||
|
||||
|
||||
class TestParseReadme:
|
||||
def test_category_count(self):
|
||||
cats, resources = parse_readme(MINIMAL_README)
|
||||
assert len(cats) == 2
|
||||
|
||||
def test_resource_count(self):
|
||||
cats, resources = parse_readme(MINIMAL_README)
|
||||
assert len(resources) == 2
|
||||
|
||||
def test_category_names(self):
|
||||
cats, _ = parse_readme(MINIMAL_README)
|
||||
assert cats[0]["name"] == "Alpha"
|
||||
assert cats[1]["name"] == "Beta"
|
||||
|
||||
def test_category_slugs(self):
|
||||
cats, _ = parse_readme(MINIMAL_README)
|
||||
assert cats[0]["slug"] == "alpha"
|
||||
assert cats[1]["slug"] == "beta"
|
||||
|
||||
def test_category_description(self):
|
||||
cats, _ = parse_readme(MINIMAL_README)
|
||||
assert cats[0]["description"] == "Libraries for alpha stuff."
|
||||
assert cats[1]["description"] == "Tools for beta."
|
||||
|
||||
def test_category_content_has_entries(self):
|
||||
cats, _ = parse_readme(MINIMAL_README)
|
||||
assert "lib-a" in cats[0]["content"]
|
||||
assert "lib-b" in cats[0]["content"]
|
||||
|
||||
def test_resources_names(self):
|
||||
_, resources = parse_readme(MINIMAL_README)
|
||||
assert resources[0]["name"] == "Newsletters"
|
||||
assert resources[1]["name"] == "Podcasts"
|
||||
|
||||
def test_resources_content(self):
|
||||
_, resources = parse_readme(MINIMAL_README)
|
||||
assert "News One" in resources[0]["content"]
|
||||
assert "Pod One" in resources[1]["content"]
|
||||
|
||||
def test_contributing_skipped(self):
|
||||
cats, resources = parse_readme(MINIMAL_README)
|
||||
all_names = [c["name"] for c in cats] + [r["name"] for r in resources]
|
||||
assert "Contributing" not in all_names
|
||||
|
||||
def test_no_separator(self):
|
||||
cats, resources = parse_readme("# Just a heading\n\nSome text.\n")
|
||||
assert cats == []
|
||||
assert resources == []
|
||||
|
||||
def test_no_description(self):
|
||||
readme = textwrap.dedent("""\
|
||||
# Title
|
||||
|
||||
---
|
||||
|
||||
## NullDesc
|
||||
|
||||
- [item](https://x.com) - Thing.
|
||||
|
||||
# Resources
|
||||
|
||||
## Tips
|
||||
|
||||
- [tip](https://x.com)
|
||||
|
||||
# Contributing
|
||||
|
||||
Done.
|
||||
""")
|
||||
cats, resources = parse_readme(readme)
|
||||
assert cats[0]["description"] == ""
|
||||
assert "item" in cats[0]["content"]
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# parse_readme on real README
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
class TestParseRealReadme:
|
||||
@pytest.fixture(autouse=True)
|
||||
def load_readme(self):
|
||||
readme_path = os.path.join(os.path.dirname(__file__), "..", "..", "README.md")
|
||||
with open(readme_path, encoding="utf-8") as f:
|
||||
self.readme_text = f.read()
|
||||
self.cats, self.resources = parse_readme(self.readme_text)
|
||||
|
||||
def test_at_least_83_categories(self):
|
||||
assert len(self.cats) >= 83
|
||||
|
||||
def test_resources_has_newsletters_and_podcasts(self):
|
||||
names = [r["name"] for r in self.resources]
|
||||
assert "Newsletters" in names
|
||||
assert "Podcasts" in names
|
||||
|
||||
def test_contributing_not_in_results(self):
|
||||
all_names = [c["name"] for c in self.cats] + [
|
||||
r["name"] for r in self.resources
|
||||
]
|
||||
assert "Contributing" not in all_names
|
||||
|
||||
def test_first_category_is_admin_panels(self):
|
||||
assert self.cats[0]["name"] == "Admin Panels"
|
||||
assert self.cats[0]["slug"] == "admin-panels"
|
||||
|
||||
def test_last_category_is_wsgi_servers(self):
|
||||
assert self.cats[-1]["name"] == "WSGI Servers"
|
||||
assert self.cats[-1]["slug"] == "wsgi-servers"
|
||||
|
||||
def test_restful_api_slug(self):
|
||||
slugs = [c["slug"] for c in self.cats]
|
||||
assert "restful-api" in slugs
|
||||
|
||||
def test_descriptions_extracted(self):
|
||||
admin = self.cats[0]
|
||||
assert admin["description"] == "Libraries for administrative interfaces."
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# group_categories
|
||||
# ---------------------------------------------------------------------------
|
||||
@@ -318,26 +74,6 @@ class TestGroupCategories:
|
||||
assert "Resources" in group_names
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# render_markdown (kept for compatibility)
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
class TestRenderMarkdown:
|
||||
def test_renders_link_list(self):
|
||||
from build import render_markdown
|
||||
|
||||
html = render_markdown("- [lib](https://example.com) - Does stuff.")
|
||||
assert "<li>" in html
|
||||
assert '<a href="https://example.com">lib</a>' in html
|
||||
|
||||
def test_renders_plain_text(self):
|
||||
from build import render_markdown
|
||||
|
||||
html = render_markdown("Hello world")
|
||||
assert "<p>Hello world</p>" in html
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# build (integration)
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
Reference in New Issue
Block a user