Skip to content

Resolve entities #888

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
wants to merge 6 commits into
base: master
Choose a base branch
from
Draft

Resolve entities #888

Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
776d0a5
TextUtil::resolveEntities: preallocate
stokito Aug 2, 2025
1e3e9c9
TextUtil::resolveEntities: don't increment i++
stokito Aug 2, 2025
d6394a7
TextUtil::resolveEntities: invert if
stokito Aug 2, 2025
5ec9217
TextUtil::resolveEntities: ignore unescaped HTML entities
stokito Aug 2, 2025
29ee37c
TextUtil::resolveEntities: use qsizetype to avoid narrowinf type
stokito Aug 2, 2025
6916c80
TextUtil use raw string literal
stokito Aug 2, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
67 changes: 35 additions & 32 deletions src/textutil.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -191,33 +191,37 @@ QString TextUtil::rich2plain(const QString &in, bool collapseSpaces)
QString TextUtil::resolveEntities(const QStringView &in)
{
QString out;
out.reserve(in.length());

for (int i = 0; i < int(in.length()); ++i) {
if (in[i] == '&') {
// find a semicolon
++i;
int n = in.indexOf(';', i);
if (n == -1)
break;
auto type = in.mid(i, (n - i));

i = n; // should be n+1, but we'll let the loop increment do it

if (type == QLatin1String { "amp" })
out += '&';
else if (type == QLatin1String { "lt" })
out += '<';
else if (type == QLatin1String { "gt" })
out += '>';
else if (type == QLatin1String { "quot" })
out += '\"';
else if (type == QLatin1String { "apos" })
out += '\'';
else if (type == QLatin1String { "nbsp" })
out += char(0xa0);
} else {
for (qsizetype i = 0; i < int(in.length()); i++) {
if (in[i] != '&') {
out += in[i];
continue;
}
// find a semicolon
qsizetype n = in.indexOf(';', i+1);
if (n == -1) {
out += in[i];
continue;
}
auto type = in.mid(i+1, (n - (i+1)));
if (type == QLatin1String { "amp" })
out += '&';
else if (type == QLatin1String { "lt" })
out += '<';
else if (type == QLatin1String { "gt" })
out += '>';
else if (type == QLatin1String { "quot" })
out += '\"';
else if (type == QLatin1String { "apos" })
out += '\'';
else if (type == QLatin1String { "nbsp" })
out += char(0xa0);
else {
out += in[i];
continue;
}
i = n; // should be n+1, but we'll let the loop increment do it
}

return out;
Expand Down Expand Up @@ -452,7 +456,7 @@ QString TextUtil::linkify(const QString &in)
#else
auto linkColor = ColorOpt::instance()->color("options.ui.look.colors.messages.link");
// we have visited link as well but it's no applicable to QTextEdit or we have to track visited manually
linked = QString("<a href=\"%1\" style=\"color:%2\">").arg(href, linkColor.name());
linked = QString(R"(<a href="%1" style="color:%2">)").arg(href, linkColor.name());
#endif
linked += (escape(link) + "</a>" + escape(pre.mid(cutoff)));
out.replace(x1, len, linked);
Expand Down Expand Up @@ -592,17 +596,16 @@ QString TextUtil::img2title(const QString &in)

QString TextUtil::legacyFormat(const QString &in)
{

// enable *bold* stuff
// //old code
// out=out.replace(QRegularExpression("(^[^<>\\s]*|\\s[^<>\\s]*)\\*(\\S+)\\*([^<>\\s]*\\s|[^<>\\s]*$)"),"\\1<b>*\\2*</b>\\3");
// out=out.replace(QRegularExpression("(^[^<>\\s\\/]*|\\s[^<>\\s\\/]*)\\/([^\\/\\s]+)\\/([^<>\\s\\/]*\\s|[^<>\\s\\/]*$)"),"\\1<i>/\\2/</i>\\3");
// out=out.replace(QRegularExpression("(^[^<>\\s]*|\\s[^<>\\s]*)_(\\S+)_([^<>\\s]*\\s|[^<>\\s]*$)"),"\\1<u>_\\2_</u>\\3");
// out=out.replace(QRegularExpression(R"((^[^<>\s]*|\s[^<>\s]*)\*(\S+)\*([^<>\s]*\s|[^<>\s]*$))"), "\\1<b>*\\2*</b>\\3");
// out=out.replace(QRegularExpression(R"((^[^<>\s\/]*|\s[^<>\s\/]*)\/([^\/\s]+)\/([^<>\s\/]*\s|[^<>\s\/]*$))"), "\\1<i>/\\2/</i>\\3");
// out=out.replace(QRegularExpression(R"((^[^<>\s]*|\s[^<>\s]*)_(\S+)_([^<>\s]*\s|[^<>\s]*$))"), "\\1<u>_\\2_</u>\\3");

QString out = in;
out = out.replace(QRegularExpression("(^|\\s|>)_(\\S+)_(?=<|\\s|$)"), "\\1<u>_\\2_</u>"); // underline inside _text_
out = out.replace(QRegularExpression("(^|\\s|>)\\*(\\S+)\\*(?=<|\\s|$)"), "\\1<b>*\\2*</b>"); // bold *text*
out = out.replace(QRegularExpression("(^|\\s|>)\\/(\\S+)\\/(?=<|\\s|$)"), "\\1<i>/\\2/</i>"); // italic /text/
out = out.replace(QRegularExpression(R"((^|\s|>)_(\S+)_(?=<|\s|$))"), "\\1<u>_\\2_</u>"); // underline inside _text_
out = out.replace(QRegularExpression(R"((^|\s|>)\*(\S+)\*(?=<|\s|$))"), "\\1<b>*\\2*</b>"); // bold *text*
out = out.replace(QRegularExpression(R"((^|\s|>)\/(\S+)\/(?=<|\s|$))"), "\\1<i>/\\2/</i>"); // italic /text/

return out;
}
Expand Down