tastytea
/
remwharead
1
0
Fork 0
Code Issues 1 Pull Requests Releases 37 Activity

Remove HTML-encoded newlines in descriptions.
continuous-integration/drone/push Build is passing Details 

We didn't catch newlines encoded as HTML entities before.
This commit is contained in:
tastytea 2019-07-13 18:20:37 +02:00
parent ff708e9403
commit a83a2548c3
Signed by: tastytea
GPG Key ID: CFC39497F1B26E07
2 changed files with 14 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
CMakeLists.txt
View File

@ -1,6 +1,6 @@
cmake_minimum_required (VERSION 3.2)
project(remwharead
VERSION 0.4.2
VERSION 0.4.3
LANGUAGES CXX
)

19
src/uri.cpp
View File

@ -64,7 +64,7 @@ const html_extract URI::get()
return
{
extract_title(answer),
strip_html(extract_description(answer)),
extract_description(answer),
strip_html(answer)
};
}
@ -106,7 +106,7 @@ const string URI::extract_description(const string &html)
smatch match;
const regex re("description\"[^>]+content=\"([^\"]+)", icase);
regex_search(html, match, re);
return remove_newlines(match[1].str());
return remove_newlines(strip_html(match[1].str()));
}
return "";
@ -509,11 +509,18 @@ const string URI::archive()
const string URI::remove_newlines(string text)
{
size_t pos = 0;
while ((pos = text.find("\n", pos)) != std::string::npos)
size_t posn = 0;
while ((posn = text.find('\n', posn)) != std::string::npos)
{
text.replace(pos, 1, " ");
++pos;
text.replace(posn, 1, " ");
size_t posr = posn - 1;
if (text[posr] == '\r')
{
text.replace(posr, 1, " ");
}
++posn;
}
return text;
}