tastytea
/
mastorss
1
0
Fork 0
Code Issues Pull Requests Releases 12 Wiki Activity

replaced own unescape_html() with the one from mastodon-cpp

This commit is contained in:
tastytea 2018-05-09 06:36:48 +02:00
parent a184b9f231
commit 03d3e0e179
Signed by: tastytea
GPG Key ID: 59346E0EA35C67E5
3 changed files with 3 additions and 43 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 3.7)
project (mastorss
VERSION 0.5.15
VERSION 0.5.16
LANGUAGES CXX
)

2
README.md
View File

@ -14,7 +14,7 @@ The documentation is far from complete, sorry.
* [cmake](https://cmake.org/) (tested: 3.9.6)
* [boost](http://www.boost.org/) (tested: 1.63.0)
* [curlpp](http://www.curlpp.org/) (tested: 0.8.1)
* [mastodon-cpp](https://github.com/tastytea/mastodon-cpp) (at least: 0.8.6)
* [mastodon-cpp](https://github.com/tastytea/mastodon-cpp) (at least: 0.12.0)
* [jsoncpp](https://github.com/open-source-parsers/jsoncpp) (tested: 1.8.4)
## Get sourcecode

42
src/parse.cpp
View File

@ -33,46 +33,6 @@ using std::cerr;
using std::string;
namespace pt = boost::property_tree;
// Translate { to chars, translate some named entities to chars
void unescape_html(string &str)
{
string html = str;
str = "";
// Used to convert int to utf-8 char
std::wstring_convert<std::codecvt_utf8<char32_t>, char32_t> u8c;
std::regex re_entity("&#(x)?(\\d{1,8});");
std::smatch match;
while (std::regex_search(html, match, re_entity))
{
char32_t codepoint = 0;
// 'x' in front of the number means it's hexadecimal, else decimal.
if (match[1].length() == 1)
{
codepoint = std::stoi(match[2].str(), nullptr, 16);
}
else
{
codepoint = std::stoi(match[2].str(), nullptr, 10);
}
str += match.prefix().str() + u8c.to_bytes(codepoint);
html = match.suffix().str();
}
str += html;
std::regex relt("&lt;");
std::regex regt("&gt;");
std::regex reamp("&amp;");
std::regex requot("&quot;");
std::regex reapos("&apos;");
str = std::regex_replace(str, relt, "<");
str = std::regex_replace(str, regt, ">");
str = std::regex_replace(str, reamp, "&");
str = std::regex_replace(str, requot, "\"");
str = std::regex_replace(str, reapos, "\'");
}
std::vector<string> parse_website(const string &xml)
{
Json::Value list;
@ -157,7 +117,7 @@ std::vector<string> parse_website(const string &xml)
continue;
}
unescape_html(str);
Mastodon::API::unescape_html(str);
// Try to turn the HTML into human-readable text
std::regex reparagraph("<p>");