Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

More work on kepubify

Browse Source
This commit is contained in:
Kovid Goyal 2025-02-20 10:17:27 +05:30
parent 1dc92ac423
commit 4faf5fb9e5
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
2 changed files with 41 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
src/calibre/ebooks/oeb/polish/kepubify.py
View File

@ -14,6 +14,8 @@
import re
from lxml import etree
from calibre.ebooks.oeb.base import XHTML, XPath
from calibre.ebooks.oeb.parse_utils import barename, merge_multiple_html_heads_and_bodies
from calibre.ebooks.oeb.polish.tts import lang_for_elem
@ -32,6 +34,10 @@ BLOCK_TAGS = frozenset((
))
def outer_html(node):
return etree.tostring(node, encoding='unicode', with_tail=False)
def add_style(root, css='div#book-inner { margin-top: 0; margin-bottom: 0; }', cls=KOBO_STYLE_HACKS) -> bool:
def add(parent):
@ -98,7 +104,7 @@ def add_kobo_spans(inner, root_lang):
segnum += 1
return parent.makeelement(span_tag_name, attrib={'class': 'koboSpan', 'id': f'kobo.{paranum}.{segnum}'})
def wrap_text_in_spans(text: str, parent, at: int, lang: str) -> str | None:
def wrap_text_in_spans(text: str, parent: etree.ElementBase, after_child: etree.ElementBase, lang: str) -> str | None:
nonlocal increment_next_para, paranum, segnum
if increment_next_para:
paranum += 1
@ -108,6 +114,7 @@ def add_kobo_spans(inner, root_lang):
ws = None
if num := len(text) - len(stripped):
ws = text[:num]
at = 0 if after_child is None else parent.index(after_child) + 1
if at:
parent[at-1].tail = ws
else:
@ -116,6 +123,7 @@ def add_kobo_spans(inner, root_lang):
s = kobo_span(parent)
s.text = stripped[pos:pos+sz]
parent.insert(at, s)
at += 1
while stack:
node, parent, tagname, node_lang = p()
@ -124,23 +132,23 @@ def add_kobo_spans(inner, root_lang):
continue
if not increment_next_para and tagname in BLOCK_TAGS:
increment_next_para = True
if node.text:
wrap_text_in_spans(node.text, node, 0, node_lang)
for i, child in enumerate(reversed(node)):
i = len(node) - 1 - i
for child in reversed(node):
if child.tail:
a((child.tail, node, i + 1, node_lang))
if isinstance(child.tag, 'str'):
a((child.tail, node, child, node_lang))
if isinstance(child.tag, str):
child_name = barename(child.tag).lower()
if child_name == 'img':
increment_next_para = False
paranum += 1
segnum = 0
idx = node.index(child)
w = kobo_span(node)
w.append(child)
node[i] = w
node[idx] = w
elif child_name not in SKIPPED_TAGS:
a((child, None, child_name, lang_for_elem(child, node_lang)))
if node.text:
wrap_text_in_spans(node.text, node, None, node_lang)
def add_kobo_markup_to_html(root, metadata_lang):

21
src/calibre/ebooks/oeb/polish/tests/kepubify.py
View File

@ -11,9 +11,30 @@ from calibre.ebooks.oeb.polish.tests.base import BaseTest
class KepubifyTests(BaseTest):
def test_kepubify_html(self):
prefix = '''<?xml version='1.0' encoding='utf-8'?>
<html xmlns="http://www.w3.org/1999/xhtml"><head><style type="text/css" class="kobostylehacks">\
div#book-inner { margin-top: 0; margin-bottom: 0; }</style></head><body><div id="book-columns"><div id="book-inner">'''
suffix = '</div></div></body></html>'
for src, expected in {
# basics
'<p>Simple sentences. In a single paragraph.'
'<p>A sentence <i>with <b>nested</b>, tailed</i> formatting. Another.':
'<p><span class="koboSpan" id="kobo.1.1">Simple sentences. </span><span class="koboSpan" id="kobo.1.2">In a single paragraph.</span></p>'
'<p><span class="koboSpan" id="kobo.2.1">A sentence </span><i><span class="koboSpan" id="kobo.2.2">with </span>'
'<b><span class="koboSpan" id="kobo.2.3">nested</span></b><span class="koboSpan" id="kobo.2.4">, tailed</span></i> '
'<span class="koboSpan" id="kobo.2.5">formatting. </span>'
'<span class="koboSpan" id="kobo.2.6">Another.</span></p>',
# img tags
# comments
# nested block tags
}.items():
with self.subTest(src=src):
root = parse(src)
kepubify_html(root)
actual = serialize(root, 'text/html').decode('utf-8')
actual = actual[len(prefix):-len(suffix)]
self.assertEqual(expected, actual)