averello/koreader-mirror
1
0
Fork 0
mirror of https://github.com/koreader/koreader.git synced 2025-12-13 20:36:53 +01:00
Code Issues Packages Projects Releases Wiki Activity

htmlToPlainText(): Format paragraphs with indentation (#7027)

Browse Source 
Cf. <https://www.mobileread.com/forums/showthread.php?p=4072308#post4072308>.
This commit is contained in:
Frans de Jonge
2020-12-24 15:38:18 +01:00
committed by GitHub
parent ad08ce9849
commit dafaf966e4
1 changed files with 3 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
frontend/util.lua
View File

@@ -1002,7 +1002,7 @@ This may fail on complex HTML (with styles, scripts, comments), but should be fi
function util.htmlToPlainText(text)
-- Replace <br> and <p> with \n
text = text:gsub("%s*<%s*br%s*/?>%s*", "\n") -- <br> and <br/>
text = text:gsub("%s*<%s*p%s*>%s*", "\n") -- <p>
text = text:gsub("%s*<%s*p%s*>%s*", "\n&nbsp;&nbsp;&nbsp;&nbsp;") -- <p>
text = text:gsub("%s*</%s*p%s*>%s*", "\n") -- </p>
text = text:gsub("%s*<%s*p%s*/>%s*", "\n") -- standalone <p/>
-- Remove all HTML tags
@@ -1012,6 +1012,8 @@ function util.htmlToPlainText(text)
-- Trim spaces and new lines at start and end
text = text:gsub("^[\n%s]*", "")
text = text:gsub("[\n%s]*$", "")
-- Trim non-breaking spaces from the start
text = text:gsub("^\xC2\xA0\xC2\xA0\xC2\xA0\xC2\xA0", "")
return text
end