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

E-book viewer: Fix searching not ignoring ruby text. Fixes #2065249 [Ruby text interferes with in-book search](https://bugs.launchpad.net/calibre/+bug/2065249)

Browse Source
This commit is contained in:
Kovid Goyal 2024-05-20 20:25:55 +05:30
parent 98a09d9bdf
commit 33a8d70a93
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
1 changed files with 14 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

28
src/pyj/read_book/resources.pyj
View File

@ -408,26 +408,24 @@ def text_from_serialized_html(data, get_anchor_offset_map):
serialized_data = JSON.parse(data) serialized_data = JSON.parse(data)
tag_map = serialized_data.tag_map tag_map = serialized_data.tag_map
ans = v'[]' ans = v'[]'
no_visit = {'script': True, 'style': True, 'title': True, 'head': True}
ignore_text = {'img': True, 'math': True, 'rt': true, 'rp': True, 'rtc': True}
if tag_map: if tag_map:
stack = v'[serialized_data.tree[2]]' stack = v'[[serialized_data.tree[2], False]]'
else: else:
stack = v'[]' stack = v'[]'
for child in serialized_data.tree.c: for child in serialized_data.tree.c:
if child.n is 'body': if child.n is 'body':
stack.push(child) stack.push(v'[child, False]')
ignore_text = {'script':True, 'style':True, 'title': True}
anchor_offset_map = {} anchor_offset_map = {}
text_pos = 0 text_pos = 0
while stack.length: while stack.length:
node = stack.pop() node, text_ignored_in_parent = stack.pop()
if jstype(node) is 'string': if jstype(node) is 'string':
ans.push(node) ans.push(node)
text_pos += node.length text_pos += node.length
continue continue
if tag_map: src = tag_map[node[0]] if tag_map else node
src = tag_map[node[0]]
else:
src = node
if get_anchor_offset_map and src.a: if get_anchor_offset_map and src.a:
for v'var i = 0; i < src.a.length; i++': for v'var i = 0; i < src.a.length; i++':
x = src.a[i] x = src.a[i]
@ -435,19 +433,21 @@ def text_from_serialized_html(data, get_anchor_offset_map):
aid = x[1] aid = x[1]
if jstype(anchor_offset_map[aid]) is not 'number': if jstype(anchor_offset_map[aid]) is not 'number':
anchor_offset_map[aid] = text_pos anchor_offset_map[aid] = text_pos
if no_visit[src.n]:
if src.n and not ignore_text[src.n] and src.x: continue
ignore_text_in_node_and_children = v'!!ignore_text[src.n]'
if not ignore_text_in_node_and_children and src.x:
ans.push(src.x) ans.push(src.x)
text_pos += src.x.length text_pos += src.x.length
if src.l: if not text_ignored_in_parent and src.l:
stack.push(src.l) stack.push(v'[src.l, ignore_text_in_node_and_children]')
if tag_map: if tag_map:
for v'var i = node.length - 1; i >= 1; i--': for v'var i = node.length - 1; i >= 1; i--':
stack.push(node[i]) stack.push(v'[node[i], ignore_text_in_node_and_children]')
else: else:
if src.c: if src.c:
for v'var i = src.c.length; i-- > 0;': for v'var i = src.c.length; i-- > 0;':
stack.push(v'src.c[i]') stack.push(v'[src.c[i], ignore_text_in_node_and_children]')
ans = ans.join('') ans = ans.join('')
if get_anchor_offset_map: if get_anchor_offset_map:
return ans, anchor_offset_map return ans, anchor_offset_map