mrwnslz
7095e176b7
HTML-Kommentare zählten als Text (1435 Blöcke in einem Testbuch), Leerraum wurde mit Pythons statt JavaScripts \s zusammengezogen, Fußnotenmarker bekamen Leerzeichen. Neu: tests/ (Blockliste, Anker, App-Start mit Textual-Pilot) und tools/parity/ – vergleicht Anzahl und Tags der Blöcke mit parseEpub aus dem Web-Reader in headless Chromium (6 Bücher, bis 25.798 Blöcke: gleich). Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
53 lines
2.2 KiB
Python
53 lines
2.2 KiB
Python
"""The block list must count and read exactly like the web reader (static/js/app/44-books.js,
|
||
40-epub.js sanitizeEpubHtml): anchors are block indexes shared between all clients. The
|
||
real-book comparison against the web reader's own code is tools/parity/."""
|
||
from diora_tui.blocks import anchor_is_further, format_anchor, load_flat_book, parse_anchor
|
||
|
||
|
||
def texts(book):
|
||
return [(b.tag, b.text) for b in book.blocks]
|
||
|
||
|
||
def test_block_selector_and_nesting(epub):
|
||
book = load_flat_book(epub([
|
||
"<h1>Titel</h1><p>Eins</p><blockquote><p>Zitat</p></blockquote><ul><li>a</li></ul>"
|
||
"<div>Blatt</div><div><span>kein Blatt</span></div><div><p>Behälter</p></div>"
|
||
]))
|
||
# a div counts only when it has no element children; blockquote and its p both count
|
||
assert texts(book) == [
|
||
("h1", "Titel"), ("p", "Eins"), ("blockquote", "Zitat"), ("p", "Zitat"),
|
||
("li", "a"), ("div", "Blatt"), ("p", "Behälter"),
|
||
]
|
||
|
||
|
||
def test_all_spine_documents_count_even_without_text(epub):
|
||
book = load_flat_book(epub(["<p>a</p>", "<p>b</p>"]))
|
||
assert [b.chapter_index for b in book.blocks] == [0, 1]
|
||
|
||
|
||
def test_comments_are_not_text(epub):
|
||
book = load_flat_book(epub(['<h1><!-- d="kap1" -->Titel</h1><p>x<!-- weg -->y</p>']))
|
||
assert texts(book) == [("h1", "Titel"), ("p", "xy")]
|
||
|
||
|
||
def test_whitespace_is_javascripts(epub):
|
||
# \s in JS: no-break space and BOM collapse like spaces; \x85 does not
|
||
book = load_flat_book(epub(["<p>a bc</p><p>\x85</p>"]))
|
||
assert texts(book)[0] == ("p", "a b c")
|
||
assert texts(book)[1][1] == "\x85"
|
||
|
||
|
||
def test_footnote_marker_adds_no_space(epub):
|
||
book = load_flat_book(epub(['<p>Satz.<sup><a href="#n1">1</a></sup>Weiter</p><p id="n1">Fußnote</p>']))
|
||
assert book.blocks[0].text == "Satz.1Weiter"
|
||
assert book.blocks[0].footnotes[0].marker == "1"
|
||
assert book.footnote_targets["n1"] == 1
|
||
|
||
|
||
def test_anchor_format_and_order():
|
||
assert format_anchor(12, 0.5) == "12:0.500000"
|
||
assert parse_anchor("12:0.500000") == (12, 0.5)
|
||
assert parse_anchor("kaputt") is None
|
||
assert anchor_is_further("5:0.1", "4:0.9")
|
||
assert anchor_is_further("5:0.5", "5:0.4")
|
||
assert not anchor_is_further("4:0.9", "5:0.1")
|