bvandeusen
976107bbe8
THE empty-body root cause. Patreon deprecated the flat `content` HTML field — it returns null on the feed AND the detail endpoint, for every post type (confirmed against the live API: all 135 StickySpoodge posts, text_only/ image_file/poll alike). The real body now lives in `content_json_string` (a ProseMirror/TipTap doc), returned only under the DEFAULT post fieldset — a sparse fields[post]=content request omits it. Not credential, not post_type: a request shape gone stale. - NEW utils/prosemirror.py: ProseMirror doc -> HTML (paragraphs, marks bold/italic/underline/strike/code/link, hardBreak, inline images, lists, headings; unknown nodes degrade to children). post_body_html(attrs) = the one resolver: legacy content HTML else convert content_json_string. - patreon_client: add content_json_string to the feed _FIELDS_POST; rewrite fetch_post_detail_content to use the DEFAULT fieldset (no sparse fields[post]) and resolve via post_body_html (replaces the wrong sparse req + full-fetch fallback). - patreon_downloader._write_sidecar_data: resolve body via post_body_html (feed content_json_string) before the detail-fetch; memoize resolved HTML. - tests: prosemirror converter unit tests; client legacy + content_json_string paths; contract pins content_json_string. Inline <img> nodes carry the CDN filehash → bodies now feed Phase-2 localization. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
109 lines
3.6 KiB
Python
109 lines
3.6 KiB
Python
"""Unit tests for the Patreon ProseMirror→HTML body converter (#842).
|
|
|
|
Patreon moved the post body from the flat `content` HTML field (now null) to
|
|
`content_json_string` (a ProseMirror doc). PURE module → no DB, fast lane.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import json
|
|
|
|
from backend.app.utils.prosemirror import post_body_html, prosemirror_to_html
|
|
|
|
|
|
def _doc(*nodes) -> str:
|
|
return json.dumps({"type": "doc", "content": list(nodes)})
|
|
|
|
|
|
def test_paragraph_text_and_hardbreak():
|
|
doc = _doc({
|
|
"type": "paragraph",
|
|
"content": [
|
|
{"type": "text", "text": "Hi there"},
|
|
{"type": "hardBreak"},
|
|
{"type": "text", "text": "line two"},
|
|
],
|
|
})
|
|
assert prosemirror_to_html(doc) == "<p>Hi there<br>line two</p>"
|
|
|
|
|
|
def test_marks_bold_italic_link():
|
|
doc = _doc({
|
|
"type": "paragraph",
|
|
"content": [
|
|
{"type": "text", "marks": [{"type": "bold"}], "text": "B"},
|
|
{"type": "text", "marks": [{"type": "italic"}], "text": "I"},
|
|
{
|
|
"type": "text",
|
|
"marks": [{"type": "link", "attrs": {"href": "https://x.test/a"}}],
|
|
"text": "L",
|
|
},
|
|
],
|
|
})
|
|
assert prosemirror_to_html(doc) == (
|
|
'<p><strong>B</strong><em>I</em><a href="https://x.test/a">L</a></p>'
|
|
)
|
|
|
|
|
|
def test_image_node_emits_img_with_cdn_src():
|
|
doc = _doc({
|
|
"type": "image",
|
|
"attrs": {"src": "https://cdn.test/p/post/1/abc/1.gif?token-hash=z", "alt": None},
|
|
})
|
|
out = prosemirror_to_html(doc)
|
|
assert out == '<img src="https://cdn.test/p/post/1/abc/1.gif?token-hash=z" alt="">'
|
|
|
|
|
|
def test_lists_and_heading():
|
|
doc = _doc(
|
|
{"type": "heading", "attrs": {"level": 2},
|
|
"content": [{"type": "text", "text": "Status"}]},
|
|
{"type": "bulletList", "content": [
|
|
{"type": "listItem", "content": [
|
|
{"type": "paragraph", "content": [{"type": "text", "text": "one"}]}]},
|
|
]},
|
|
)
|
|
assert prosemirror_to_html(doc) == (
|
|
"<h2>Status</h2><ul><li><p>one</p></li></ul>"
|
|
)
|
|
|
|
|
|
def test_text_is_html_escaped():
|
|
doc = _doc({"type": "paragraph",
|
|
"content": [{"type": "text", "text": "a < b & c > d"}]})
|
|
assert prosemirror_to_html(doc) == "<p>a < b & c > d</p>"
|
|
|
|
|
|
def test_unknown_node_renders_children_not_dropped():
|
|
doc = _doc({"type": "weirdBlock", "content": [
|
|
{"type": "paragraph", "content": [{"type": "text", "text": "keep me"}]}]})
|
|
assert prosemirror_to_html(doc) == "<p>keep me</p>"
|
|
|
|
|
|
def test_empty_and_unparseable_return_none():
|
|
assert prosemirror_to_html(None) is None
|
|
assert prosemirror_to_html("") is None
|
|
assert prosemirror_to_html(" ") is None
|
|
assert prosemirror_to_html("{not json") is None
|
|
assert prosemirror_to_html(json.dumps({"type": "doc", "content": []})) is None
|
|
|
|
|
|
def test_post_body_html_prefers_legacy_content():
|
|
attrs = {"content": "<p>legacy</p>",
|
|
"content_json_string": _doc({"type": "paragraph",
|
|
"content": [{"type": "text", "text": "new"}]})}
|
|
assert post_body_html(attrs) == "<p>legacy</p>"
|
|
|
|
|
|
def test_post_body_html_falls_back_to_json_string():
|
|
attrs = {"content": None,
|
|
"content_json_string": _doc({"type": "paragraph",
|
|
"content": [{"type": "text", "text": "new"}]})}
|
|
assert post_body_html(attrs) == "<p>new</p>"
|
|
|
|
|
|
def test_post_body_html_none_when_both_empty():
|
|
assert post_body_html({"content": None, "content_json_string": None}) is None
|
|
assert post_body_html({}) is None
|
|
assert post_body_html(None) is None
|