From 03821756189e0ef6be64f17f9b360aa97e158748 Mon Sep 17 00:00:00 2001 From: tastytea Date: Mon, 5 Aug 2019 22:01:08 +0200 Subject: [PATCH] 2019-08-05 --- docs/annotated.html | 14 +-- docs/classes.html | 20 ++-- docs/classremwharead_1_1Database.html | 6 +- docs/classremwharead_1_1URI-members.html | 7 +- docs/classremwharead_1_1URI.html | 95 ++++++++++--------- .../dir_c85d3e3c5052e9ad9ce18c6863244a25.html | 9 -- .../dir_d44c64559bbebec7f509842c48db8b23.html | 91 ++++++++++++++++++ docs/files.html | 23 ++--- docs/functions.html | 19 +--- docs/functions_func.html | 19 +--- docs/index.html | 3 +- docs/menudata.js | 1 - docs/remwharead_8hpp_source.html | 6 +- docs/search/all_0.js | 3 +- docs/search/all_1.js | 2 +- docs/search/all_2.js | 5 +- docs/search/all_3.js | 2 +- docs/search/all_4.js | 6 +- docs/search/all_5.js | 2 +- docs/search/all_6.js | 2 +- docs/search/all_7.js | 3 +- docs/search/all_8.js | 6 +- docs/search/all_9.js | 4 +- docs/search/all_a.js | 6 +- docs/search/all_b.js | 8 +- docs/search/classes_0.js | 2 +- docs/search/classes_1.js | 2 +- docs/search/classes_2.js | 2 +- docs/search/classes_3.js | 2 +- docs/search/functions_2.js | 1 - docs/search/functions_5.js | 2 +- docs/search/functions_6.js | 2 +- docs/search/functions_8.js | 2 - docs/search/searchdata.js | 6 +- docs/search_8hpp.html | 4 +- docs/search_8hpp_source.html | 4 +- docs/sqlite_8hpp_source.html | 10 +- ...structremwharead_1_1Database_1_1entry.html | 6 +- docs/structremwharead_1_1html__extract.html | 2 +- docs/time_8hpp.html | 4 +- docs/time_8hpp_source.html | 4 +- docs/types_8hpp.html | 4 +- docs/types_8hpp_source.html | 4 +- docs/uri_8hpp_source.html | 26 ++--- 44 files changed, 241 insertions(+), 210 deletions(-) create mode 100644 docs/dir_d44c64559bbebec7f509842c48db8b23.html diff --git a/docs/annotated.html b/docs/annotated.html index c5ab386..7b2fdbd 100644 --- a/docs/annotated.html +++ b/docs/annotated.html @@ -69,16 +69,10 @@ $(function() {
Here are the classes, structs, unions and interfaces with brief descriptions:
[detail level 123]
- - - - - - - - - - + + + +
 ▼Nremwharead
 ▼NExport
 CAsciiDocExport as AsciiDoc document
 CBookmarksExport as Netscape bookmark file
 CCSVExport as Comma Separated Values
 CExportBaseBase class for exports
 CSimpleExport as simple list
 ▼CDatabaseStore and retrieve files from/to SQLite
 CentryDescribes a database entry
 Chtml_extractA processed HTML page
 CURIDownload, archive and process an URI
 ▼CDatabaseStore and retrieve files from/to SQLite
 CentryDescribes a database entry
 Chtml_extractA processed HTML page
 CURIDownload, archive and process an URI
diff --git a/docs/classes.html b/docs/classes.html index a49e139..67efb9f 100644 --- a/docs/classes.html +++ b/docs/classes.html @@ -66,26 +66,18 @@ $(function() {
Class Index
-
a | b | c | d | e | h | s | u
+
d | e | h | u
- - - - - - +
  a  
-
  c  
+
  d  
  e  
-
  s  
+
  h  
+
  u  
AsciiDoc (remwharead::Export)   CSV (remwharead::Export)   Database::entry (remwharead)   Simple (remwharead::Export)   
  b  
-
  d  
-		ExportBase (remwharead::Export)   
  u  
-
  h  
-
Bookmarks (remwharead::Export)   Database (remwharead)   URI (remwharead)   
html_extract (remwharead)   
Database (remwharead)   Database::entry (remwharead)   html_extract (remwharead)   URI (remwharead)   
-
a | b | c | d | e | h | s | u
+
d | e | h | u
diff --git a/docs/classremwharead_1_1Database.html b/docs/classremwharead_1_1Database.html index d9413e0..52917e3 100644 --- a/docs/classremwharead_1_1Database.html +++ b/docs/classremwharead_1_1Database.html @@ -194,7 +194,7 @@ Public Member Functions

Retrieve a vector of Database::entry from the database.

-
116  {
117  try
118  {
119  const string query = "SELECT * FROM remwharead WHERE datetime "
120  "BETWEEN '" + timepoint_to_string(start, true)
121  + "' AND '" + timepoint_to_string(end, true)
122  + "' ORDER BY datetime DESC;";
123 
124  sqlite::query q(*_con, query);
125  sqlite::result_type res = q.get_result();
126  vector<entry> entries;
127 
128  while(res->next_row())
129  {
130  vector<string> tags;
131  const string strtags = res->get_string(3);
132  size_t pos = 0;
133  while (pos != std::string::npos)
134  {
135  const size_t newpos = strtags.find(',', pos);
136  tags.push_back(strtags.substr(pos, newpos - pos));
137  pos = newpos;
138  if (pos != std::string::npos)
139  {
140  ++pos;
141  }
142  }
143  entries.push_back
144  ({
145  res->get_string(0),
146  res->get_string(1),
147  string_to_timepoint(res->get_string(2), true),
148  tags,
149  res->get_string(4),
150  res->get_string(5),
151  res->get_string(6)
152  });
153  }
154 
155  return entries;
156  }
157  catch (std::exception &e)
158  {
159  cerr << "Error in " << __func__ << ": " << e.what() << endl;
160  }
161 
162  return {};
163  }
+
111  {
112  try
113  {
114  const string query = "SELECT * FROM remwharead WHERE datetime "
115  "BETWEEN '" + timepoint_to_string(start, true)
116  + "' AND '" + timepoint_to_string(end, true)
117  + "' ORDER BY datetime DESC;";
118 
119  sqlite::query q(*_con, query);
120  sqlite::result_type res = q.get_result();
121  vector<entry> entries;
122 
123  while(res->next_row())
124  {
125  vector<string> tags;
126  const string strtags = res->get_string(3);
127  size_t pos = 0;
128  while (pos != std::string::npos)
129  {
130  const size_t newpos = strtags.find(',', pos);
131  tags.push_back(strtags.substr(pos, newpos - pos));
132  pos = newpos;
133  if (pos != std::string::npos)
134  {
135  ++pos;
136  }
137  }
138  entries.push_back
139  ({
140  res->get_string(0),
141  res->get_string(1),
142  string_to_timepoint(res->get_string(2), true),
143  tags,
144  res->get_string(4),
145  res->get_string(5),
146  res->get_string(6)
147  });
148  }
149 
150  return entries;
151  }
152  catch (std::exception &e)
153  {
154  cerr << "Error in " << __func__ << ": " << e.what() << endl;
155  }
156 
157  return {};
158  }
@@ -214,11 +214,11 @@ Public Member Functions

Store a Database::entry in the database.

-
88  {
89  try
90  {
91  const string strdatetime = timepoint_to_string(data.datetime, true);
92  string strtags;
93  for (const string &tag : data.tags)
94  {
95  strtags += tag;
96  if (tag != *(data.tags.rbegin()))
97  {
98  strtags += ",";
99  }
100  }
101 
102  sqlite::execute ins(*_con, "INSERT INTO remwharead "
103  "VALUES(?, ?, ?, ?, ?, ?, ?);");
104  ins % data.uri % data.archive_uri % strdatetime % strtags
105  % data.title % data.description % data.fulltext;
106  ins();
107  }
108  catch (std::exception &e)
109  {
110  cerr << "Error in " << __func__ << ": " << e.what() << endl;
111  }
112  }
+
83  {
84  try
85  {
86  const string strdatetime = timepoint_to_string(data.datetime, true);
87  string strtags;
88  for (const string &tag : data.tags)
89  {
90  strtags += tag;
91  if (tag != *(data.tags.rbegin()))
92  {
93  strtags += ",";
94  }
95  }
96 
97  sqlite::execute ins(*_con, "INSERT INTO remwharead "
98  "VALUES(?, ?, ?, ?, ?, ?, ?);");
99  ins % data.uri % data.archive_uri % strdatetime % strtags
100  % data.title % data.description % data.fulltext;
101  ins();
102  }
103  catch (std::exception &e)
104  {
105  cerr << "Error in " << __func__ << ": " << e.what() << endl;
106  }
107  }
The documentation for this class was generated from the following files: diff --git a/docs/classremwharead_1_1URI-members.html b/docs/classremwharead_1_1URI-members.html index 5e46e04..14aaffa 100644 --- a/docs/classremwharead_1_1URI-members.html +++ b/docs/classremwharead_1_1URI-members.html @@ -78,12 +78,13 @@ $(function() { extract_description(const string &html)remwharead::URIprotected extract_title(const string &html)remwharead::URIprotected get()remwharead::URI - remove_html_tags(const string &html, const string &tag="")remwharead::URIprotected - remove_newlines(string text)remwharead::URIprotected - set_curlpp_options(curlpp::Easy &request)remwharead::URIprotected + make_request(const string &uri) constremwharead::URIprotected + remove_html_tags(const string &html, const string &tag="")remwharead::URIprotected + remove_newlines(string text)remwharead::URIprotected strip_html(const string &html)remwharead::URIprotected unescape_html(const string &html)remwharead::URIprotected URI(const string &uri)remwharead::URIexplicit + ~URI() (defined in remwharead::URI)remwharead::URI
diff --git a/docs/classremwharead_1_1URI.html b/docs/classremwharead_1_1URI.html index d06594e..83c26fc 100644 --- a/docs/classremwharead_1_1URI.html +++ b/docs/classremwharead_1_1URI.html @@ -95,9 +95,9 @@ Public Member Functions - - - + + + @@ -151,7 +151,7 @@ string 

Construct object and set URL.

-
44  :_uri(uri)
45  {
46  }
+
57  :_uri(uri)
58  {
59  Poco::Net::initializeSSL();
60 
61  try
62  {
63  HTTPClientSession::ProxyConfig proxy;
64  string proxy_env = Environment::get("http_proxy");
65  size_t pos;
66 
67  // Only keep text between // and /.
68  if ((pos = proxy_env.find("//")) != string::npos)
69  {
70  proxy_env = proxy_env.substr(pos + 2);
71  }
72  if ((pos = proxy_env.find('/')) != string::npos)
73  {
74  proxy_env = proxy_env.substr(0, pos);
75  }
76  if ((pos = proxy_env.find(':')) != string::npos)
77  {
78  proxy.host = proxy_env.substr(0, pos);
79  proxy.port = std::stoi(proxy_env.substr(pos + 1));
80  }
81  else
82  {
83  proxy.host = proxy_env;
84  }
85 
86  HTTPClientSession::setGlobalProxyConfig(proxy);
87  }
88  catch (const std::exception &)
89  {
90  // No proxy found, no problem.
91  }
92  }

Member Function Documentation

@@ -171,7 +171,7 @@ string 

Save URI in archive and return archive-URI.

-
476  {
477  if (_uri.substr(0, 4) != "http")
478  {
479  return "";
480  }
481 
482  try
483  {
484  std::ostringstream oss;
485  curlpp::Easy request;
486  set_curlpp_options(request);
487  request.setOpt<curlopts::Url>("https://web.archive.org/save/"
488  + _uri);
489  request.setOpt<curlopts::WriteStream>(&oss);
490  request.setOpt<curlopts::NoBody>(true); // Make HEAD request.
491  request.setOpt<curlpp::options::Header>(true); // Keep headers.
492  request.perform();
493 
494  smatch match;
495  const string answer = oss.str();
496  if (regex_search(answer, match, regex("Content-Location: (.+)\r")))
497  {
498  return "https://web.archive.org" + match[1].str();
499  }
500  else
501  {
502  cerr << "Error: Could not archive page. HTTP status: "
503  << curlpp::infos::ResponseCode::get(request) << endl;
504  }
505  }
506  catch (const std::exception &e)
507  {
508  cerr << "Error in " << __func__ << ": " << e.what() << endl;
509  }
510 
511  return "";
512  }
remwharead::URI::set_curlpp_options
void set_curlpp_options(curlpp::Easy &request)
Sets common curlpp options.
Definition: uri.cpp:83
+
569  {
570  if (_uri.substr(0, 4) != "http")
571  {
572  return "";
573  }
574 
575  try
576  {
577  const string answer = make_request("https://web.archive.org/save/"
578  + _uri);
579 
580  smatch match;
581  if (regex_search(answer, match, regex("Content-Location: (.+)\r")))
582  {
583  return "https://web.archive.org" + match[1].str();
584  }
585  else
586  {
587  cerr << "Error: Could not archive page.\n";
588  }
589  }
590  catch (const std::exception &e)
591  {
592  cerr << "Error in " << __func__ << ": " << e.what() << ".\n";
593  }
594 
595  return "";
596  }
remwharead::URI::make_request
const string make_request(const string &uri) const
Make a HTTP(S) request.
Definition: uri.cpp:129
@@ -200,8 +200,8 @@ string 

Extract the description from an HTML page.

-
105  {
106  const regex re_htmlfile("\\.(.?html?|xml|rss)$");
107  if (_uri.substr(0, 4) == "http" || regex_search(_uri, re_htmlfile))
108  {
109  smatch match;
110  const regex re("description\"[^>]+content=\"([^\"]+)", icase);
111  regex_search(html, match, re);
112  return remove_newlines(strip_html(match[1].str()));
113  }
114 
115  return "";
116  }
remwharead::URI::strip_html
const string strip_html(const string &html)
Removes HTML tags and superflous spaces from an HTML page.
Definition: uri.cpp:118
-
remwharead::URI::remove_newlines
const string remove_newlines(string text)
Replace newlines with spaces.
Definition: uri.cpp:514
+
198  {
199  const regex re_htmlfile("\\.(.?html?|xml|rss)$");
200  if (_uri.substr(0, 4) == "http" || regex_search(_uri, re_htmlfile))
201  {
202  smatch match;
203  const regex re("description\"[^>]+content=\"([^\"]+)", icase);
204  regex_search(html, match, re);
205  return remove_newlines(strip_html(match[1].str()));
206  }
207 
208  return "";
209  }
remwharead::URI::strip_html
const string strip_html(const string &html)
Removes HTML tags and superflous spaces from an HTML page.
Definition: uri.cpp:211
+
remwharead::URI::remove_newlines
const string remove_newlines(string text)
Replace newlines with spaces.
Definition: uri.cpp:598
@@ -230,8 +230,8 @@ string 

Extract the title from an HTML page.

-
92  {
93  const regex re_htmlfile("\\.(.?html?|xml|rss)$");
94  if (_uri.substr(0, 4) == "http" || regex_search(_uri, re_htmlfile))
95  {
96  smatch match;
97  regex_search(html, match, regex("<title>([^<]+)", icase));
98  return remove_newlines(unescape_html(match[1].str()));
99  }
100 
101  return "";
102  }
remwharead::URI::remove_newlines
const string remove_newlines(string text)
Replace newlines with spaces.
Definition: uri.cpp:514
-
remwharead::URI::unescape_html
const string unescape_html(const string &html)
Convert HTML entities to UTF-8.
Definition: uri.cpp:175
+
185  {
186  const regex re_htmlfile("\\.(.?html?|xml|rss)$");
187  if (_uri.substr(0, 4) == "http" || regex_search(_uri, re_htmlfile))
188  {
189  smatch match;
190  regex_search(html, match, regex("<title>([^<]+)", icase));
191  return remove_newlines(unescape_html(match[1].str()));
192  }
193 
194  return "";
195  }
remwharead::URI::remove_newlines
const string remove_newlines(string text)
Replace newlines with spaces.
Definition: uri.cpp:598
+
remwharead::URI::unescape_html
const string unescape_html(const string &html)
Convert HTML entities to UTF-8.
Definition: uri.cpp:268
@@ -251,10 +251,39 @@ string 

Download URI and extract title, description and full text.

-
49  {
50  try
51  {
52  std::ostringstream oss;
53  curlpp::Easy request;
54  set_curlpp_options(request);
55  request.setOpt<curlopts::Url>(_uri);
56  request.setOpt<curlopts::WriteStream>(&oss);
57  request.perform();
58 
59  const string answer = oss.str();
60  if (answer.empty())
61  {
62  cerr << "Error: Could not download page. Response code: "
63  << curlpp::infos::ResponseCode::get(request) << endl;
64  }
65  else
66  {
67  return
68  {
69  extract_title(answer),
70  extract_description(answer),
71  strip_html(answer)
72  };
73  }
74  }
75  catch (const std::exception &e)
76  {
77  cerr << "Error in " << __func__ << ": " << e.what() << endl;
78  }
79 
80  return { "", "", "" };
81  }
remwharead::URI::strip_html
const string strip_html(const string &html)
Removes HTML tags and superflous spaces from an HTML page.
Definition: uri.cpp:118
-
remwharead::URI::set_curlpp_options
void set_curlpp_options(curlpp::Easy &request)
Sets common curlpp options.
Definition: uri.cpp:83
-
remwharead::URI::extract_title
const string extract_title(const string &html)
Extract the title from an HTML page.
Definition: uri.cpp:91
-
remwharead::URI::extract_description
const string extract_description(const string &html)
Extract the description from an HTML page.
Definition: uri.cpp:104
+
100  {
101  try
102  {
103  std::ostringstream oss;
104 
105  const string answer = make_request(_uri);
106  if (answer.empty())
107  {
108  cerr << "Error: Could not download page.\n";
109  }
110  else
111  {
112  return
113  {
114  extract_title(answer),
115  extract_description(answer),
116  strip_html(answer)
117  };
118  }
119  }
120  catch (const std::exception &e)
121  {
122  // Prints something like "SSL Exception", nothing specific.
123  cerr << "Error in " << __func__ << ": " << e.what() << endl;
124  }
125 
126  return { "", "", "" };
127  }
remwharead::URI::strip_html
const string strip_html(const string &html)
Removes HTML tags and superflous spaces from an HTML page.
Definition: uri.cpp:211
+
remwharead::URI::extract_title
const string extract_title(const string &html)
Extract the title from an HTML page.
Definition: uri.cpp:184
+
remwharead::URI::extract_description
const string extract_description(const string &html)
Extract the description from an HTML page.
Definition: uri.cpp:197
+
remwharead::URI::make_request
const string make_request(const string &uri) const
Make a HTTP(S) request.
Definition: uri.cpp:129
+
+
+
+ +

◆ make_request()

+ +
+
+

Protected Member Functions

void set_curlpp_options (curlpp::Easy &request)
 Sets common curlpp options. More...
 
const string make_request (const string &uri) const
 Make a HTTP(S) request. More...
 
const string extract_title (const string &html)
 Extract the title from an HTML page. More...
 
_uri
_uri
_uri
_uri
_uri
+ + + + +
+ + + + + + + + +
const string remwharead::URI::make_request (const string & uri) const
+ 		+protected
+
+ +

Make a HTTP(S) request.

+
130  {
131  Poco::URI poco_uri(uri);
132  string path = poco_uri.getPathAndQuery();
133  if (path.empty())
134  {
135  path = "/";
136  }
137 
138  unique_ptr<HTTPClientSession> session;
139  if (poco_uri.getScheme() == "https")
140  {
141  session = make_unique<HTTPSClientSession>(poco_uri.getHost(),
142  poco_uri.getPort());
143  }
144  else if (poco_uri.getScheme() == "http")
145  {
146  session = make_unique<HTTPClientSession>(poco_uri.getHost(),
147  poco_uri.getPort());
148  }
149 
150  HTTPRequest request(HTTPRequest::HTTP_GET, path,
151  HTTPMessage::HTTP_1_1);
152  request.set("User-Agent", string("remwharead/") + global::version);
153 
154  HTTPResponse response;
155 
156  session->sendRequest(request);
157  istream &rs = session->receiveResponse(response);
158 
159  // Not using the constants because some are too new for Debian stretch.
160  switch (response.getStatus())
161  {
162  case 301: // HTTPResponse::HTTP_MOVED_PERMANENTLY
163  case 308: // HTTPResponse::HTTP_PERMANENT_REDIRECT
164  case 302: // HTTPResponse::HTTP_FOUND
165  case 303: // HTTPResponse::HTTP_SEE_OTHER
166  case 307: // HTTPResponse::HTTP_TEMPORARY_REDIRECT
167  {
168  return make_request(response.get("Location"));
169  }
170  case HTTPResponse::HTTP_OK:
171  {
172  string answer;
173  StreamCopier::copyToString(rs, answer);
174  return answer;
175  }
176  default:
177  {
178  cerr << response.getStatus() << " " << response.getReason() << endl;
179  return "";
180  }
181  }
182  }
remwharead::URI::make_request
const string make_request(const string &uri) const
Make a HTTP(S) request.
Definition: uri.cpp:129
@@ -300,7 +329,7 @@ string _uri -
138  {
139  // NOTE: I did this with regex_replace before, but libstdc++ segfaulted.
140  string out;
141  if (tag.empty())
142  {
143  size_t pos = 0;
144  while (pos != std::string::npos)
145  {
146  size_t startpos = html.find('<', pos);
147  size_t endpos = html.find('>', startpos);
148  out += html.substr(pos, startpos - pos);
149  pos = endpos;
150  if (pos != std::string::npos)
151  {
152  ++pos;
153  }
154  }
155  }
156  else
157  {
158  size_t pos = 0;
159  out = html;
160  while ((pos = out.find("<" + tag)) != std::string::npos)
161  {
162  size_t endpos = out.find("</" + tag, pos);
163  if (endpos == std::string::npos)
164  {
165  break;
166  }
167  endpos += 3 + tag.length(); // tag + </ + >
168  out.replace(pos, endpos - pos, "");
169  }
170  }
171 
172  return out;
173  }
+
231  {
232  // NOTE: I did this with regex_replace before, but libstdc++ segfaulted.
233  string out;
234  if (tag.empty())
235  {
236  size_t pos = 0;
237  while (pos != std::string::npos)
238  {
239  size_t startpos = html.find('<', pos);
240  size_t endpos = html.find('>', startpos);
241  out += html.substr(pos, startpos - pos);
242  pos = endpos;
243  if (pos != std::string::npos)
244  {
245  ++pos;
246  }
247  }
248  }
249  else
250  {
251  size_t pos = 0;
252  out = html;
253  while ((pos = out.find("<" + tag)) != std::string::npos)
254  {
255  size_t endpos = out.find("</" + tag, pos);
256  if (endpos == std::string::npos)
257  {
258  break;
259  }
260  endpos += 3 + tag.length(); // tag + </ + >
261  out.replace(pos, endpos - pos, "");
262  }
263  }
264 
265  return out;
266  }
@@ -328,35 +357,7 @@ string _uri

Replace newlines with spaces.

-
515  {
516  size_t posn = 0;
517  while ((posn = text.find('\n', posn)) != std::string::npos)
518  {
519  text.replace(posn, 1, " ");
520 
521  size_t posr = posn - 1;
522  if (text[posr] == '\r')
523  {
524  text.replace(posr, 1, " ");
525  }
526  ++posn;
527  }
528 
529  return text;
530  }
-
- - -

◆ set_curlpp_options()

- -
-
- - - - - -
- - - - - - - - -
void remwharead::URI::set_curlpp_options (curlpp::Easy & request)
- 		-protected
-
- -

Sets common curlpp options.

-
84  {
85  request.setOpt<curlopts::UserAgent>(string("remwharead/")
86  + global::version);
87  request.setOpt<curlopts::HttpHeader>({ "Connection: close" });
88  request.setOpt<curlopts::FollowLocation>(true);
89  }
+
599  {
600  size_t posn = 0;
601  while ((posn = text.find('\n', posn)) != std::string::npos)
602  {
603  text.replace(posn, 1, " ");
604 
605  size_t posr = posn - 1;
606  if (text[posr] == '\r')
607  {
608  text.replace(posr, 1, " ");
609  }
610  ++posn;
611  }
612 
613  return text;
614  }
@@ -384,8 +385,8 @@ string _uri

Removes HTML tags and superflous spaces from an HTML page.

-
119  {
120  string out;
121 
122  out = remove_html_tags(html, "script"); // Remove JavaScript.
123  out = remove_html_tags(out, "style"); // Remove CSS.
124  out = remove_html_tags(out); // Remove tags.
125 
126  size_t pos = 0;
127  while ((pos = out.find("\r", pos)) != std::string::npos) // Remove CR.
128  {
129  out.replace(pos, 1, "");
130  }
131 
132  out = regex_replace(out, regex("\\s+\n"), "\n"); // Remove space at eol.
133  out = regex_replace(out, regex("\n{2,}"), "\n"); // Reduce newlines.
134 
135  return unescape_html(out);
136  }
remwharead::URI::remove_html_tags
const string remove_html_tags(const string &html, const string &tag="")
Remove HTML tags.
Definition: uri.cpp:137
-
remwharead::URI::unescape_html
const string unescape_html(const string &html)
Convert HTML entities to UTF-8.
Definition: uri.cpp:175
+
212  {
213  string out;
214 
215  out = remove_html_tags(html, "script"); // Remove JavaScript.
216  out = remove_html_tags(out, "style"); // Remove CSS.
217  out = remove_html_tags(out); // Remove tags.
218 
219  size_t pos = 0;
220  while ((pos = out.find("\r", pos)) != std::string::npos) // Remove CR.
221  {
222  out.replace(pos, 1, "");
223  }
224 
225  out = regex_replace(out, regex("\\s+\n"), "\n"); // Remove space at eol.
226  out = regex_replace(out, regex("\n{2,}"), "\n"); // Reduce newlines.
227 
228  return unescape_html(out);
229  }
remwharead::URI::remove_html_tags
const string remove_html_tags(const string &html, const string &tag="")
Remove HTML tags.
Definition: uri.cpp:230
+
remwharead::URI::unescape_html
const string unescape_html(const string &html)
Convert HTML entities to UTF-8.
Definition: uri.cpp:268
@@ -414,11 +415,11 @@ string _uri

Convert HTML entities to UTF-8.

-
176  {
177  string buffer = html;
178  string output;
179 
180  // Used to convert int to utf-8 char.
181  std::wstring_convert<std::codecvt_utf8<char32_t>, char32_t> u8c;
182  regex re_entity("&#(x)?([[:alnum:]]{1,8});");
183  smatch match;
184 
185  while (regex_search(buffer, match, re_entity))
186  {
187  char32_t codepoint = 0;
188  // 'x' in front of the number means it's hexadecimal, else decimal.
189  if (match[1].length() == 1)
190  {
191  codepoint = std::stoi(match[2].str(), nullptr, 16);
192  }
193  else
194  {
195  codepoint = std::stoi(match[2].str(), nullptr, 10);
196  }
197  output += match.prefix().str() + u8c.to_bytes(codepoint);
198  buffer = match.suffix().str();
199  }
200  output += buffer;
201 
202  // Source: https://en.wikipedia.org/wiki/List_of_XML_and_HTML_character_
203  // entity_references#Character_entity_references_in_HTML
204  const array<const std::pair<const string, const char32_t>, 258> names =
205  {{
206  { "exclamation", 0x0021 },
207  { "quot", 0x0022 },
208  { "percent", 0x0025 },
209  { "amp", 0x0026 },
210  { "apos", 0x0027 },
211  { "add", 0x002B },
212  { "lt", 0x003C },
213  { "equal", 0x003D },
214  { "gt", 0x003E },
215  { "nbsp", 0x00A0 },
216  { "iexcl", 0x00A1 },
217  { "cent", 0x00A2 },
218  { "pound", 0x00A3 },
219  { "curren", 0x00A4 },
220  { "yen", 0x00A5 },
221  { "brvbar", 0x00A6 },
222  { "sect", 0x00A7 },
223  { "uml", 0x00A8 },
224  { "copy", 0x00A9 },
225  { "ordf", 0x00AA },
226  { "laquo", 0x00AB },
227  { "not", 0x00AC },
228  { "shy", 0x00AD },
229  { "reg", 0x00AE },
230  { "macr", 0x00AF },
231  { "deg", 0x00B0 },
232  { "plusmn", 0x00B1 },
233  { "sup2", 0x00B2 },
234  { "sup3", 0x00B3 },
235  { "acute", 0x00B4 },
236  { "micro", 0x00B5 },
237  { "para", 0x00B6 },
238  { "middot", 0x00B7 },
239  { "cedil", 0x00B8 },
240  { "sup1", 0x00B9 },
241  { "ordm", 0x00BA },
242  { "raquo", 0x00BB },
243  { "frac14", 0x00BC },
244  { "frac12", 0x00BD },
245  { "frac34", 0x00BE },
246  { "iquest", 0x00BF },
247  { "Agrave", 0x00C0 },
248  { "Aacute", 0x00C1 },
249  { "Acirc", 0x00C2 },
250  { "Atilde", 0x00C3 },
251  { "Auml", 0x00C4 },
252  { "Aring", 0x00C5 },
253  { "AElig", 0x00C6 },
254  { "Ccedil", 0x00C7 },
255  { "Egrave", 0x00C8 },
256  { "Eacute", 0x00C9 },
257  { "Ecirc", 0x00CA },
258  { "Euml", 0x00CB },
259  { "Igrave", 0x00CC },
260  { "Iacute", 0x00CD },
261  { "Icirc", 0x00CE },
262  { "Iuml", 0x00CF },
263  { "ETH", 0x00D0 },
264  { "Ntilde", 0x00D1 },
265  { "Ograve", 0x00D2 },
266  { "Oacute", 0x00D3 },
267  { "Ocirc", 0x00D4 },
268  { "Otilde", 0x00D5 },
269  { "Ouml", 0x00D6 },
270  { "times", 0x00D7 },
271  { "Oslash", 0x00D8 },
272  { "Ugrave", 0x00D9 },
273  { "Uacute", 0x00DA },
274  { "Ucirc", 0x00DB },
275  { "Uuml", 0x00DC },
276  { "Yacute", 0x00DD },
277  { "THORN", 0x00DE },
278  { "szlig", 0x00DF },
279  { "agrave", 0x00E0 },
280  { "aacute", 0x00E1 },
281  { "acirc", 0x00E2 },
282  { "atilde", 0x00E3 },
283  { "auml", 0x00E4 },
284  { "aring", 0x00E5 },
285  { "aelig", 0x00E6 },
286  { "ccedil", 0x00E7 },
287  { "egrave", 0x00E8 },
288  { "eacute", 0x00E9 },
289  { "ecirc", 0x00EA },
290  { "euml", 0x00EB },
291  { "igrave", 0x00EC },
292  { "iacute", 0x00ED },
293  { "icirc", 0x00EE },
294  { "iuml", 0x00EF },
295  { "eth", 0x00F0 },
296  { "ntilde", 0x00F1 },
297  { "ograve", 0x00F2 },
298  { "oacute", 0x00F3 },
299  { "ocirc", 0x00F4 },
300  { "otilde", 0x00F5 },
301  { "ouml", 0x00F6 },
302  { "divide", 0x00F7 },
303  { "oslash", 0x00F8 },
304  { "ugrave", 0x00F9 },
305  { "uacute", 0x00FA },
306  { "ucirc", 0x00FB },
307  { "uuml", 0x00FC },
308  { "yacute", 0x00FD },
309  { "thorn", 0x00FE },
310  { "yuml", 0x00FF },
311  { "OElig", 0x0152 },
312  { "oelig", 0x0153 },
313  { "Scaron", 0x0160 },
314  { "scaron", 0x0161 },
315  { "Yuml", 0x0178 },
316  { "fnof", 0x0192 },
317  { "circ", 0x02C6 },
318  { "tilde", 0x02DC },
319  { "Alpha", 0x0391 },
320  { "Beta", 0x0392 },
321  { "Gamma", 0x0393 },
322  { "Delta", 0x0394 },
323  { "Epsilon", 0x0395 },
324  { "Zeta", 0x0396 },
325  { "Eta", 0x0397 },
326  { "Theta", 0x0398 },
327  { "Iota", 0x0399 },
328  { "Kappa", 0x039A },
329  { "Lambda", 0x039B },
330  { "Mu", 0x039C },
331  { "Nu", 0x039D },
332  { "Xi", 0x039E },
333  { "Omicron", 0x039F },
334  { "Pi", 0x03A0 },
335  { "Rho", 0x03A1 },
336  { "Sigma", 0x03A3 },
337  { "Tau", 0x03A4 },
338  { "Upsilon", 0x03A5 },
339  { "Phi", 0x03A6 },
340  { "Chi", 0x03A7 },
341  { "Psi", 0x03A8 },
342  { "Omega", 0x03A9 },
343  { "alpha", 0x03B1 },
344  { "beta", 0x03B2 },
345  { "gamma", 0x03B3 },
346  { "delta", 0x03B4 },
347  { "epsilon", 0x03B5 },
348  { "zeta", 0x03B6 },
349  { "eta", 0x03B7 },
350  { "theta", 0x03B8 },
351  { "iota", 0x03B9 },
352  { "kappa", 0x03BA },
353  { "lambda", 0x03BB },
354  { "mu", 0x03BC },
355  { "nu", 0x03BD },
356  { "xi", 0x03BE },
357  { "omicron", 0x03BF },
358  { "pi", 0x03C0 },
359  { "rho", 0x03C1 },
360  { "sigmaf", 0x03C2 },
361  { "sigma", 0x03C3 },
362  { "tau", 0x03C4 },
363  { "upsilon", 0x03C5 },
364  { "phi", 0x03C6 },
365  { "chi", 0x03C7 },
366  { "psi", 0x03C8 },
367  { "omega", 0x03C9 },
368  { "thetasym", 0x03D1 },
369  { "upsih", 0x03D2 },
370  { "piv", 0x03D6 },
371  { "ensp", 0x2002 },
372  { "emsp", 0x2003 },
373  { "thinsp", 0x2009 },
374  { "zwnj", 0x200C },
375  { "zwj", 0x200D },
376  { "lrm", 0x200E },
377  { "rlm", 0x200F },
378  { "ndash", 0x2013 },
379  { "mdash", 0x2014 },
380  { "horbar", 0x2015 },
381  { "lsquo", 0x2018 },
382  { "rsquo", 0x2019 },
383  { "sbquo", 0x201A },
384  { "ldquo", 0x201C },
385  { "rdquo", 0x201D },
386  { "bdquo", 0x201E },
387  { "dagger", 0x2020 },
388  { "Dagger", 0x2021 },
389  { "bull", 0x2022 },
390  { "hellip", 0x2026 },
391  { "permil", 0x2030 },
392  { "prime", 0x2032 },
393  { "Prime", 0x2033 },
394  { "lsaquo", 0x2039 },
395  { "rsaquo", 0x203A },
396  { "oline", 0x203E },
397  { "frasl", 0x2044 },
398  { "euro", 0x20AC },
399  { "image", 0x2111 },
400  { "weierp", 0x2118 },
401  { "real", 0x211C },
402  { "trade", 0x2122 },
403  { "alefsym", 0x2135 },
404  { "larr", 0x2190 },
405  { "uarr", 0x2191 },
406  { "rarr", 0x2192 },
407  { "darr", 0x2193 },
408  { "harr", 0x2194 },
409  { "crarr", 0x21B5 },
410  { "lArr", 0x21D0 },
411  { "uArr", 0x21D1 },
412  { "rArr", 0x21D2 },
413  { "dArr", 0x21D3 },
414  { "hArr", 0x21D4 },
415  { "forall", 0x2200 },
416  { "part", 0x2202 },
417  { "exist", 0x2203 },
418  { "empty", 0x2205 },
419  { "nabla", 0x2207 },
420  { "isin", 0x2208 },
421  { "notin", 0x2209 },
422  { "ni", 0x220B },
423  { "prod", 0x220F },
424  { "sum", 0x2211 },
425  { "minus", 0x2212 },
426  { "lowast", 0x2217 },
427  { "radic", 0x221A },
428  { "prop", 0x221D },
429  { "infin", 0x221E },
430  { "ang", 0x2220 },
431  { "and", 0x2227 },
432  { "or", 0x2228 },
433  { "cap", 0x2229 },
434  { "cup", 0x222A },
435  { "int", 0x222B },
436  { "there4", 0x2234 },
437  { "sim", 0x223C },
438  { "cong", 0x2245 },
439  { "asymp", 0x2248 },
440  { "ne", 0x2260 },
441  { "equiv", 0x2261 },
442  { "le", 0x2264 },
443  { "ge", 0x2265 },
444  { "sub", 0x2282 },
445  { "sup", 0x2283 },
446  { "nsub", 0x2284 },
447  { "sube", 0x2286 },
448  { "supe", 0x2287 },
449  { "oplus", 0x2295 },
450  { "otimes", 0x2297 },
451  { "perp", 0x22A5 },
452  { "sdot", 0x22C5 },
453  { "lceil", 0x2308 },
454  { "rceil", 0x2309 },
455  { "lfloor", 0x230A },
456  { "rfloor", 0x230B },
457  { "lang", 0x2329 },
458  { "rang", 0x232A },
459  { "loz", 0x25CA },
460  { "spades", 0x2660 },
461  { "clubs", 0x2663 },
462  { "hearts", 0x2665 },
463  { "diams", 0x2666 }
464  }};
465 
466  for (auto &pair : names)
467  {
468  const regex re('&' + pair.first + ';');
469  output = regex_replace(output, re, u8c.to_bytes(pair.second));
470  }
471 
472  return output;
473  }
+
269  {
270  string buffer = html;
271  string output;
272 
273  // Used to convert int to utf-8 char.
274  std::wstring_convert<std::codecvt_utf8<char32_t>, char32_t> u8c;
275  regex re_entity("&#(x)?([[:alnum:]]{1,8});");
276  smatch match;
277 
278  while (regex_search(buffer, match, re_entity))
279  {
280  char32_t codepoint = 0;
281  // 'x' in front of the number means it's hexadecimal, else decimal.
282  if (match[1].length() == 1)
283  {
284  codepoint = std::stoi(match[2].str(), nullptr, 16);
285  }
286  else
287  {
288  codepoint = std::stoi(match[2].str(), nullptr, 10);
289  }
290  output += match.prefix().str() + u8c.to_bytes(codepoint);
291  buffer = match.suffix().str();
292  }
293  output += buffer;
294 
295  // Source: https://en.wikipedia.org/wiki/List_of_XML_and_HTML_character_
296  // entity_references#Character_entity_references_in_HTML
297  const array<const std::pair<const string, const char32_t>, 258> names =
298  {{
299  { "exclamation", 0x0021 },
300  { "quot", 0x0022 },
301  { "percent", 0x0025 },
302  { "amp", 0x0026 },
303  { "apos", 0x0027 },
304  { "add", 0x002B },
305  { "lt", 0x003C },
306  { "equal", 0x003D },
307  { "gt", 0x003E },
308  { "nbsp", 0x00A0 },
309  { "iexcl", 0x00A1 },
310  { "cent", 0x00A2 },
311  { "pound", 0x00A3 },
312  { "curren", 0x00A4 },
313  { "yen", 0x00A5 },
314  { "brvbar", 0x00A6 },
315  { "sect", 0x00A7 },
316  { "uml", 0x00A8 },
317  { "copy", 0x00A9 },
318  { "ordf", 0x00AA },
319  { "laquo", 0x00AB },
320  { "not", 0x00AC },
321  { "shy", 0x00AD },
322  { "reg", 0x00AE },
323  { "macr", 0x00AF },
324  { "deg", 0x00B0 },
325  { "plusmn", 0x00B1 },
326  { "sup2", 0x00B2 },
327  { "sup3", 0x00B3 },
328  { "acute", 0x00B4 },
329  { "micro", 0x00B5 },
330  { "para", 0x00B6 },
331  { "middot", 0x00B7 },
332  { "cedil", 0x00B8 },
333  { "sup1", 0x00B9 },
334  { "ordm", 0x00BA },
335  { "raquo", 0x00BB },
336  { "frac14", 0x00BC },
337  { "frac12", 0x00BD },
338  { "frac34", 0x00BE },
339  { "iquest", 0x00BF },
340  { "Agrave", 0x00C0 },
341  { "Aacute", 0x00C1 },
342  { "Acirc", 0x00C2 },
343  { "Atilde", 0x00C3 },
344  { "Auml", 0x00C4 },
345  { "Aring", 0x00C5 },
346  { "AElig", 0x00C6 },
347  { "Ccedil", 0x00C7 },
348  { "Egrave", 0x00C8 },
349  { "Eacute", 0x00C9 },
350  { "Ecirc", 0x00CA },
351  { "Euml", 0x00CB },
352  { "Igrave", 0x00CC },
353  { "Iacute", 0x00CD },
354  { "Icirc", 0x00CE },
355  { "Iuml", 0x00CF },
356  { "ETH", 0x00D0 },
357  { "Ntilde", 0x00D1 },
358  { "Ograve", 0x00D2 },
359  { "Oacute", 0x00D3 },
360  { "Ocirc", 0x00D4 },
361  { "Otilde", 0x00D5 },
362  { "Ouml", 0x00D6 },
363  { "times", 0x00D7 },
364  { "Oslash", 0x00D8 },
365  { "Ugrave", 0x00D9 },
366  { "Uacute", 0x00DA },
367  { "Ucirc", 0x00DB },
368  { "Uuml", 0x00DC },
369  { "Yacute", 0x00DD },
370  { "THORN", 0x00DE },
371  { "szlig", 0x00DF },
372  { "agrave", 0x00E0 },
373  { "aacute", 0x00E1 },
374  { "acirc", 0x00E2 },
375  { "atilde", 0x00E3 },
376  { "auml", 0x00E4 },
377  { "aring", 0x00E5 },
378  { "aelig", 0x00E6 },
379  { "ccedil", 0x00E7 },
380  { "egrave", 0x00E8 },
381  { "eacute", 0x00E9 },
382  { "ecirc", 0x00EA },
383  { "euml", 0x00EB },
384  { "igrave", 0x00EC },
385  { "iacute", 0x00ED },
386  { "icirc", 0x00EE },
387  { "iuml", 0x00EF },
388  { "eth", 0x00F0 },
389  { "ntilde", 0x00F1 },
390  { "ograve", 0x00F2 },
391  { "oacute", 0x00F3 },
392  { "ocirc", 0x00F4 },
393  { "otilde", 0x00F5 },
394  { "ouml", 0x00F6 },
395  { "divide", 0x00F7 },
396  { "oslash", 0x00F8 },
397  { "ugrave", 0x00F9 },
398  { "uacute", 0x00FA },
399  { "ucirc", 0x00FB },
400  { "uuml", 0x00FC },
401  { "yacute", 0x00FD },
402  { "thorn", 0x00FE },
403  { "yuml", 0x00FF },
404  { "OElig", 0x0152 },
405  { "oelig", 0x0153 },
406  { "Scaron", 0x0160 },
407  { "scaron", 0x0161 },
408  { "Yuml", 0x0178 },
409  { "fnof", 0x0192 },
410  { "circ", 0x02C6 },
411  { "tilde", 0x02DC },
412  { "Alpha", 0x0391 },
413  { "Beta", 0x0392 },
414  { "Gamma", 0x0393 },
415  { "Delta", 0x0394 },
416  { "Epsilon", 0x0395 },
417  { "Zeta", 0x0396 },
418  { "Eta", 0x0397 },
419  { "Theta", 0x0398 },
420  { "Iota", 0x0399 },
421  { "Kappa", 0x039A },
422  { "Lambda", 0x039B },
423  { "Mu", 0x039C },
424  { "Nu", 0x039D },
425  { "Xi", 0x039E },
426  { "Omicron", 0x039F },
427  { "Pi", 0x03A0 },
428  { "Rho", 0x03A1 },
429  { "Sigma", 0x03A3 },
430  { "Tau", 0x03A4 },
431  { "Upsilon", 0x03A5 },
432  { "Phi", 0x03A6 },
433  { "Chi", 0x03A7 },
434  { "Psi", 0x03A8 },
435  { "Omega", 0x03A9 },
436  { "alpha", 0x03B1 },
437  { "beta", 0x03B2 },
438  { "gamma", 0x03B3 },
439  { "delta", 0x03B4 },
440  { "epsilon", 0x03B5 },
441  { "zeta", 0x03B6 },
442  { "eta", 0x03B7 },
443  { "theta", 0x03B8 },
444  { "iota", 0x03B9 },
445  { "kappa", 0x03BA },
446  { "lambda", 0x03BB },
447  { "mu", 0x03BC },
448  { "nu", 0x03BD },
449  { "xi", 0x03BE },
450  { "omicron", 0x03BF },
451  { "pi", 0x03C0 },
452  { "rho", 0x03C1 },
453  { "sigmaf", 0x03C2 },
454  { "sigma", 0x03C3 },
455  { "tau", 0x03C4 },
456  { "upsilon", 0x03C5 },
457  { "phi", 0x03C6 },
458  { "chi", 0x03C7 },
459  { "psi", 0x03C8 },
460  { "omega", 0x03C9 },
461  { "thetasym", 0x03D1 },
462  { "upsih", 0x03D2 },
463  { "piv", 0x03D6 },
464  { "ensp", 0x2002 },
465  { "emsp", 0x2003 },
466  { "thinsp", 0x2009 },
467  { "zwnj", 0x200C },
468  { "zwj", 0x200D },
469  { "lrm", 0x200E },
470  { "rlm", 0x200F },
471  { "ndash", 0x2013 },
472  { "mdash", 0x2014 },
473  { "horbar", 0x2015 },
474  { "lsquo", 0x2018 },
475  { "rsquo", 0x2019 },
476  { "sbquo", 0x201A },
477  { "ldquo", 0x201C },
478  { "rdquo", 0x201D },
479  { "bdquo", 0x201E },
480  { "dagger", 0x2020 },
481  { "Dagger", 0x2021 },
482  { "bull", 0x2022 },
483  { "hellip", 0x2026 },
484  { "permil", 0x2030 },
485  { "prime", 0x2032 },
486  { "Prime", 0x2033 },
487  { "lsaquo", 0x2039 },
488  { "rsaquo", 0x203A },
489  { "oline", 0x203E },
490  { "frasl", 0x2044 },
491  { "euro", 0x20AC },
492  { "image", 0x2111 },
493  { "weierp", 0x2118 },
494  { "real", 0x211C },
495  { "trade", 0x2122 },
496  { "alefsym", 0x2135 },
497  { "larr", 0x2190 },
498  { "uarr", 0x2191 },
499  { "rarr", 0x2192 },
500  { "darr", 0x2193 },
501  { "harr", 0x2194 },
502  { "crarr", 0x21B5 },
503  { "lArr", 0x21D0 },
504  { "uArr", 0x21D1 },
505  { "rArr", 0x21D2 },
506  { "dArr", 0x21D3 },
507  { "hArr", 0x21D4 },
508  { "forall", 0x2200 },
509  { "part", 0x2202 },
510  { "exist", 0x2203 },
511  { "empty", 0x2205 },
512  { "nabla", 0x2207 },
513  { "isin", 0x2208 },
514  { "notin", 0x2209 },
515  { "ni", 0x220B },
516  { "prod", 0x220F },
517  { "sum", 0x2211 },
518  { "minus", 0x2212 },
519  { "lowast", 0x2217 },
520  { "radic", 0x221A },
521  { "prop", 0x221D },
522  { "infin", 0x221E },
523  { "ang", 0x2220 },
524  { "and", 0x2227 },
525  { "or", 0x2228 },
526  { "cap", 0x2229 },
527  { "cup", 0x222A },
528  { "int", 0x222B },
529  { "there4", 0x2234 },
530  { "sim", 0x223C },
531  { "cong", 0x2245 },
532  { "asymp", 0x2248 },
533  { "ne", 0x2260 },
534  { "equiv", 0x2261 },
535  { "le", 0x2264 },
536  { "ge", 0x2265 },
537  { "sub", 0x2282 },
538  { "sup", 0x2283 },
539  { "nsub", 0x2284 },
540  { "sube", 0x2286 },
541  { "supe", 0x2287 },
542  { "oplus", 0x2295 },
543  { "otimes", 0x2297 },
544  { "perp", 0x22A5 },
545  { "sdot", 0x22C5 },
546  { "lceil", 0x2308 },
547  { "rceil", 0x2309 },
548  { "lfloor", 0x230A },
549  { "rfloor", 0x230B },
550  { "lang", 0x2329 },
551  { "rang", 0x232A },
552  { "loz", 0x25CA },
553  { "spades", 0x2660 },
554  { "clubs", 0x2663 },
555  { "hearts", 0x2665 },
556  { "diams", 0x2666 }
557  }};
558 
559  for (auto &pair : names)
560  {
561  const regex re('&' + pair.first + ';');
562  output = regex_replace(output, re, u8c.to_bytes(pair.second));
563  }
564 
565  return output;
566  }
The documentation for this class was generated from the following files: diff --git a/docs/dir_c85d3e3c5052e9ad9ce18c6863244a25.html b/docs/dir_c85d3e3c5052e9ad9ce18c6863244a25.html index 8845406..da0928e 100644 --- a/docs/dir_c85d3e3c5052e9ad9ce18c6863244a25.html +++ b/docs/dir_c85d3e3c5052e9ad9ce18c6863244a25.html @@ -73,15 +73,6 @@ $(function() { -

Directories

- - - - - - -

-Files

file  search.hpp [code]
 
file  time.hpp [code]
 
file  types.hpp [code]
 
diff --git a/docs/dir_d44c64559bbebec7f509842c48db8b23.html b/docs/dir_d44c64559bbebec7f509842c48db8b23.html new file mode 100644 index 0000000..904ca33 --- /dev/null +++ b/docs/dir_d44c64559bbebec7f509842c48db8b23.html @@ -0,0 +1,91 @@ + + + + + + + +remwharead: include Directory Reference + + + + + + + + + +
+
+ + + + + + +
+
remwharead +  0.6.3 +
+
+
+ + + + + + + + +
+
+ + +
+ +
+ + +
+
+
+
include Directory Reference
+
+
+ + + + + + + + +

+Files

file  search.hpp [code]
 
file  time.hpp [code]
 
file  types.hpp [code]
 
+
+ +
+Generated by   +doxygen + 1.8.14 +
+ + diff --git a/docs/files.html b/docs/files.html index 78f411a..a785235 100644 --- a/docs/files.html +++ b/docs/files.html @@ -67,21 +67,14 @@ $(function() {
Here is a list of all documented files with brief descriptions:
-
[detail level 1234]
- - - - - - - - - - - - - - +
[detail level 12]
 ▼ src
 ▼ lib
 ▼ export
 adoc.hpp
 bookmarks.hpp
 csv.hpp
 export.hpp
 simple.hpp
 remwharead.hpp
 search.hpp
 sqlite.hpp
 time.hpp
 types.hpp
 uri.hpp
+ + + + + + +
 ▼ include
 remwharead.hpp
 search.hpp
 sqlite.hpp
 time.hpp
 types.hpp
 uri.hpp
diff --git a/docs/functions.html b/docs/functions.html index 2f76da5..8f5520e 100644 --- a/docs/functions.html +++ b/docs/functions.html @@ -72,9 +72,6 @@ $(function() {
  • entry : remwharead::Database
    • -
  • ExportBase() -: remwharead::Export::ExportBase -
  • extract_description() : remwharead::URI
    • @@ -87,19 +84,15 @@ $(function() {
  • get() : remwharead::URI
    • +
  • make_request() +: remwharead::URI +
  • operator bool() : remwharead::Database
  • operator== : remwharead::Database::entry
    • -
  • print() -: remwharead::Export::AsciiDoc -, remwharead::Export::Bookmarks -, remwharead::Export::CSV -, remwharead::Export::ExportBase -, remwharead::Export::Simple -
  • remove_html_tags() : remwharead::URI
    • @@ -109,12 +102,6 @@ $(function() {
  • retrieve() : remwharead::Database
    • -
  • set_curlpp_options() -: remwharead::URI -
    • -
  • sort_entries() -: remwharead::Export::ExportBase -
  • store() : remwharead::Database
    • diff --git a/docs/functions_func.html b/docs/functions_func.html index d616fa7..e5f9cd8 100644 --- a/docs/functions_func.html +++ b/docs/functions_func.html @@ -69,9 +69,6 @@ $(function() {
  • Database() : remwharead::Database
    • -
  • ExportBase() -: remwharead::Export::ExportBase -
  • extract_description() : remwharead::URI
    • @@ -84,16 +81,12 @@ $(function() {
  • get() : remwharead::URI
    • +
  • make_request() +: remwharead::URI +
  • operator bool() : remwharead::Database
    • -
  • print() -: remwharead::Export::AsciiDoc -, remwharead::Export::Bookmarks -, remwharead::Export::CSV -, remwharead::Export::ExportBase -, remwharead::Export::Simple -
  • remove_html_tags() : remwharead::URI
    • @@ -103,12 +96,6 @@ $(function() {
  • retrieve() : remwharead::Database
    • -
  • set_curlpp_options() -: remwharead::URI -
    • -
  • sort_entries() -: remwharead::Export::ExportBase -
  • store() : remwharead::Database
    • diff --git a/docs/index.html b/docs/index.html index 4ece598..9fe4ec3 100644 --- a/docs/index.html +++ b/docs/index.html @@ -69,7 +69,8 @@ $(function() {

    Using the library

    The easiest way is to include remwharead.hpp, which then includes all other headers.

    -
    #include <remwharead/remwharead.hpp>

    Compile your code with g++ $(pkg-config --cflags --libs remwharead).

    +
    #include <remwharead/remwharead.hpp>

    Use it in your CMake project like this:

    +
    find_package(remwharead CONFIG REQUIRED)
    target_link_libraries(MyProject remwharead::remwharead)

    Or compile your code with g++ $(pkg-config --cflags --libs remwharead).

    diff --git a/docs/menudata.js b/docs/menudata.js index 1693fb2..d08bf52 100644 --- a/docs/menudata.js +++ b/docs/menudata.js @@ -26,7 +26,6 @@ var menudata={children:[ {text:"Classes",url:"annotated.html",children:[ {text:"Class List",url:"annotated.html"}, {text:"Class Index",url:"classes.html"}, -{text:"Class Hierarchy",url:"hierarchy.html"}, {text:"Class Members",url:"functions.html",children:[ {text:"All",url:"functions.html"}, {text:"Functions",url:"functions_func.html"}, diff --git a/docs/remwharead_8hpp_source.html b/docs/remwharead_8hpp_source.html index 1d02985..069511b 100644 --- a/docs/remwharead_8hpp_source.html +++ b/docs/remwharead_8hpp_source.html @@ -5,7 +5,7 @@ -remwharead: src/lib/remwharead.hpp Source File +remwharead: include/remwharead.hpp Source File @@ -62,7 +62,7 @@ $(function() {
    @@ -70,7 +70,7 @@ $(function() {
    remwharead.hpp
    -
    1 /* This file is part of remwharead.
    2  * Copyright © 2019 tastytea <tastytea@tastytea.de>
    3  *
    4  * This program is free software: you can redistribute it and/or modify
    5  * it under the terms of the GNU General Public License as published by
    6  * the Free Software Foundation, version 3.
    7  *
    8  * This program is distributed in the hope that it will be useful,
    9  * but WITHOUT ANY WARRANTY; without even the implied warranty of
    10  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
    11  * GNU General Public License for more details.
    12  *
    13  * You should have received a copy of the GNU General Public License
    14  * along with this program. If not, see <http://www.gnu.org/licenses/>.
    15  */
    16 
    17 #ifndef REMWHAREAD_HPP
    18 #define REMWHAREAD_HPP
    19 
    35 #include "export/adoc.hpp"
    36 #include "export/bookmarks.hpp"
    37 #include "export/csv.hpp"
    38 #include "export/export.hpp"
    39 #include "export/simple.hpp"
    40 #include "search.hpp"
    41 #include "sqlite.hpp"
    42 #include "time.hpp"
    43 #include "types.hpp"
    44 #include "uri.hpp"
    45 
    46 #endif // REMWHAREAD_HPP
    +
    1 /* This file is part of remwharead.
    2  * Copyright © 2019 tastytea <tastytea@tastytea.de>
    3  *
    4  * This program is free software: you can redistribute it and/or modify
    5  * it under the terms of the GNU General Public License as published by
    6  * the Free Software Foundation, version 3.
    7  *
    8  * This program is distributed in the hope that it will be useful,
    9  * but WITHOUT ANY WARRANTY; without even the implied warranty of
    10  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
    11  * GNU General Public License for more details.
    12  *
    13  * You should have received a copy of the GNU General Public License
    14  * along with this program. If not, see <http://www.gnu.org/licenses/>.
    15  */
    16 
    17 #ifndef REMWHAREAD_HPP
    18 #define REMWHAREAD_HPP
    19 
    42 #include "export/adoc.hpp"
    43 #include "export/bookmarks.hpp"
    44 #include "export/csv.hpp"
    45 #include "export/export.hpp"
    46 #include "export/simple.hpp"
    47 #include "search.hpp"
    48 #include "sqlite.hpp"
    49 #include "time.hpp"
    50 #include "types.hpp"
    51 #include "uri.hpp"
    52 
    53 #endif // REMWHAREAD_HPP
    diff --git a/docs/search/all_0.js b/docs/search/all_0.js index b843e8b..7ec321d 100644 --- a/docs/search/all_0.js +++ b/docs/search/all_0.js @@ -1,5 +1,4 @@ var searchData= [ - ['archive',['archive',['../classremwharead_1_1URI.html#a074b3aa3ec7658b184869599c9ab6445',1,'remwharead::URI']]], - ['asciidoc',['AsciiDoc',['../classremwharead_1_1Export_1_1AsciiDoc.html',1,'remwharead::Export']]] + ['archive',['archive',['../classremwharead_1_1URI.html#a074b3aa3ec7658b184869599c9ab6445',1,'remwharead::URI']]] ]; diff --git a/docs/search/all_1.js b/docs/search/all_1.js index 0239cc4..513e711 100644 --- a/docs/search/all_1.js +++ b/docs/search/all_1.js @@ -1,4 +1,4 @@ var searchData= [ - ['bookmarks',['Bookmarks',['../classremwharead_1_1Export_1_1Bookmarks.html',1,'remwharead::Export']]] + ['database',['Database',['../classremwharead_1_1Database.html',1,'remwharead::Database'],['../classremwharead_1_1Database.html#a8576436b2cc1e3d8ecfdeabfc0ff88ca',1,'remwharead::Database::Database()']]] ]; diff --git a/docs/search/all_2.js b/docs/search/all_2.js index b9ded6e..15df538 100644 --- a/docs/search/all_2.js +++ b/docs/search/all_2.js @@ -1,4 +1,7 @@ var searchData= [ - ['csv',['CSV',['../classremwharead_1_1Export_1_1CSV.html',1,'remwharead::Export']]] + ['entry',['entry',['../structremwharead_1_1Database_1_1entry.html',1,'remwharead::Database::entry'],['../classremwharead_1_1Database.html#a5ef85b43b21a900046b9233ee259ae7d',1,'remwharead::Database::entry()']]], + ['export_5fformat',['export_format',['../types_8hpp.html#a937b5e962f810e493ec0629c86a9fd7e',1,'remwharead']]], + ['extract_5fdescription',['extract_description',['../classremwharead_1_1URI.html#ae6ff7a41b9529eb8f4c7f2ace7260dc7',1,'remwharead::URI']]], + ['extract_5ftitle',['extract_title',['../classremwharead_1_1URI.html#a37f93c46371d9b3753ae04bd2ef2c362',1,'remwharead::URI']]] ]; diff --git a/docs/search/all_3.js b/docs/search/all_3.js index 513e711..8113eef 100644 --- a/docs/search/all_3.js +++ b/docs/search/all_3.js @@ -1,4 +1,4 @@ var searchData= [ - ['database',['Database',['../classremwharead_1_1Database.html',1,'remwharead::Database'],['../classremwharead_1_1Database.html#a8576436b2cc1e3d8ecfdeabfc0ff88ca',1,'remwharead::Database::Database()']]] + ['fulltext_5foneline',['fulltext_oneline',['../structremwharead_1_1Database_1_1entry.html#a0e19bad458eedf6ecdcf4b33ce319e8d',1,'remwharead::Database::entry']]] ]; diff --git a/docs/search/all_4.js b/docs/search/all_4.js index 789c313..18aa3a4 100644 --- a/docs/search/all_4.js +++ b/docs/search/all_4.js @@ -1,8 +1,4 @@ var searchData= [ - ['entry',['entry',['../structremwharead_1_1Database_1_1entry.html',1,'remwharead::Database::entry'],['../classremwharead_1_1Database.html#a5ef85b43b21a900046b9233ee259ae7d',1,'remwharead::Database::entry()']]], - ['export_5fformat',['export_format',['../types_8hpp.html#a937b5e962f810e493ec0629c86a9fd7e',1,'remwharead']]], - ['exportbase',['ExportBase',['../classremwharead_1_1Export_1_1ExportBase.html',1,'remwharead::Export::ExportBase'],['../classremwharead_1_1Export_1_1ExportBase.html#aa3c6d5cb261aaf26aafc8c4a81c83678',1,'remwharead::Export::ExportBase::ExportBase()']]], - ['extract_5fdescription',['extract_description',['../classremwharead_1_1URI.html#ae6ff7a41b9529eb8f4c7f2ace7260dc7',1,'remwharead::URI']]], - ['extract_5ftitle',['extract_title',['../classremwharead_1_1URI.html#a37f93c46371d9b3753ae04bd2ef2c362',1,'remwharead::URI']]] + ['get',['get',['../classremwharead_1_1URI.html#a8d6ac084a823749ed38c12e7bf8f3461',1,'remwharead::URI']]] ]; diff --git a/docs/search/all_5.js b/docs/search/all_5.js index 8113eef..ce5019c 100644 --- a/docs/search/all_5.js +++ b/docs/search/all_5.js @@ -1,4 +1,4 @@ var searchData= [ - ['fulltext_5foneline',['fulltext_oneline',['../structremwharead_1_1Database_1_1entry.html#a0e19bad458eedf6ecdcf4b33ce319e8d',1,'remwharead::Database::entry']]] + ['html_5fextract',['html_extract',['../structremwharead_1_1html__extract.html',1,'remwharead']]] ]; diff --git a/docs/search/all_6.js b/docs/search/all_6.js index 18aa3a4..303b720 100644 --- a/docs/search/all_6.js +++ b/docs/search/all_6.js @@ -1,4 +1,4 @@ var searchData= [ - ['get',['get',['../classremwharead_1_1URI.html#a8d6ac084a823749ed38c12e7bf8f3461',1,'remwharead::URI']]] + ['make_5frequest',['make_request',['../classremwharead_1_1URI.html#a2eadd0b24e6a37c8c42d710707bbfedf',1,'remwharead::URI']]] ]; diff --git a/docs/search/all_7.js b/docs/search/all_7.js index ce5019c..3035cae 100644 --- a/docs/search/all_7.js +++ b/docs/search/all_7.js @@ -1,4 +1,5 @@ var searchData= [ - ['html_5fextract',['html_extract',['../structremwharead_1_1html__extract.html',1,'remwharead']]] + ['operator_20bool',['operator bool',['../classremwharead_1_1Database.html#adf363243852b2a5fec1911139d4936c1',1,'remwharead::Database']]], + ['operator_3d_3d',['operator==',['../structremwharead_1_1Database_1_1entry.html#a67f257a407ec46c00d205fd4c9215846',1,'remwharead::Database::entry']]] ]; diff --git a/docs/search/all_8.js b/docs/search/all_8.js index 3035cae..ca63a6c 100644 --- a/docs/search/all_8.js +++ b/docs/search/all_8.js @@ -1,5 +1,7 @@ var searchData= [ - ['operator_20bool',['operator bool',['../classremwharead_1_1Database.html#adf363243852b2a5fec1911139d4936c1',1,'remwharead::Database']]], - ['operator_3d_3d',['operator==',['../structremwharead_1_1Database_1_1entry.html#a67f257a407ec46c00d205fd4c9215846',1,'remwharead::Database::entry']]] + ['remwharead_20reference',['remwharead Reference',['../index.html',1,'']]], + ['remove_5fhtml_5ftags',['remove_html_tags',['../classremwharead_1_1URI.html#a8b340b13ccf0bc3ae9059872ce48e06a',1,'remwharead::URI']]], + ['remove_5fnewlines',['remove_newlines',['../classremwharead_1_1URI.html#a9373cb28de198ae2db624980273ece4a',1,'remwharead::URI']]], + ['retrieve',['retrieve',['../classremwharead_1_1Database.html#abc9c9adf58b786342b0492baeef8f4ec',1,'remwharead::Database']]] ]; diff --git a/docs/search/all_9.js b/docs/search/all_9.js index 28a43a7..1999ccf 100644 --- a/docs/search/all_9.js +++ b/docs/search/all_9.js @@ -1,4 +1,6 @@ var searchData= [ - ['print',['print',['../classremwharead_1_1Export_1_1AsciiDoc.html#a20ce832d0cea815b048bbe5c51496a77',1,'remwharead::Export::AsciiDoc::print()'],['../classremwharead_1_1Export_1_1Bookmarks.html#af92b6e7c8bf46032dcf65267ce83d043',1,'remwharead::Export::Bookmarks::print()'],['../classremwharead_1_1Export_1_1CSV.html#a107c3390677129f00a6f45b924e2a539',1,'remwharead::Export::CSV::print()'],['../classremwharead_1_1Export_1_1ExportBase.html#aee596eaefecdb1c21c37f5e3d129ed56',1,'remwharead::Export::ExportBase::print()'],['../classremwharead_1_1Export_1_1Simple.html#af688d80f3d7903d59ef730311e32b7f8',1,'remwharead::Export::Simple::print()']]] + ['search_2ehpp',['search.hpp',['../search_8hpp.html',1,'']]], + ['store',['store',['../classremwharead_1_1Database.html#ab3ea9062c5c0ef5d9f2b7eea6f0fd1bd',1,'remwharead::Database']]], + ['strip_5fhtml',['strip_html',['../classremwharead_1_1URI.html#ad6ad5351ecf2983e01f9f4a51c2057a5',1,'remwharead::URI']]] ]; diff --git a/docs/search/all_a.js b/docs/search/all_a.js index ca63a6c..efa44b2 100644 --- a/docs/search/all_a.js +++ b/docs/search/all_a.js @@ -1,7 +1,5 @@ var searchData= [ - ['remwharead_20reference',['remwharead Reference',['../index.html',1,'']]], - ['remove_5fhtml_5ftags',['remove_html_tags',['../classremwharead_1_1URI.html#a8b340b13ccf0bc3ae9059872ce48e06a',1,'remwharead::URI']]], - ['remove_5fnewlines',['remove_newlines',['../classremwharead_1_1URI.html#a9373cb28de198ae2db624980273ece4a',1,'remwharead::URI']]], - ['retrieve',['retrieve',['../classremwharead_1_1Database.html#abc9c9adf58b786342b0492baeef8f4ec',1,'remwharead::Database']]] + ['time_2ehpp',['time.hpp',['../time_8hpp.html',1,'']]], + ['types_2ehpp',['types.hpp',['../types_8hpp.html',1,'']]] ]; diff --git a/docs/search/all_b.js b/docs/search/all_b.js index 1eaa5db..3e83984 100644 --- a/docs/search/all_b.js +++ b/docs/search/all_b.js @@ -1,9 +1,5 @@ var searchData= [ - ['search_2ehpp',['search.hpp',['../search_8hpp.html',1,'']]], - ['set_5fcurlpp_5foptions',['set_curlpp_options',['../classremwharead_1_1URI.html#a203f46af6271ecd5a1ff01c63461d842',1,'remwharead::URI']]], - ['simple',['Simple',['../classremwharead_1_1Export_1_1Simple.html',1,'remwharead::Export']]], - ['sort_5fentries',['sort_entries',['../classremwharead_1_1Export_1_1ExportBase.html#a0a0515408c0af2f0d74fe8e483882384',1,'remwharead::Export::ExportBase']]], - ['store',['store',['../classremwharead_1_1Database.html#ab3ea9062c5c0ef5d9f2b7eea6f0fd1bd',1,'remwharead::Database']]], - ['strip_5fhtml',['strip_html',['../classremwharead_1_1URI.html#ad6ad5351ecf2983e01f9f4a51c2057a5',1,'remwharead::URI']]] + ['unescape_5fhtml',['unescape_html',['../classremwharead_1_1URI.html#a37c36dbf8ccc03c8cc132be29e49f4ec',1,'remwharead::URI']]], + ['uri',['URI',['../classremwharead_1_1URI.html',1,'remwharead::URI'],['../classremwharead_1_1URI.html#acda508768b1fd3b4df81ea66dd4fab87',1,'remwharead::URI::URI()']]] ]; diff --git a/docs/search/classes_0.js b/docs/search/classes_0.js index c88e671..acbcf84 100644 --- a/docs/search/classes_0.js +++ b/docs/search/classes_0.js @@ -1,4 +1,4 @@ var searchData= [ - ['asciidoc',['AsciiDoc',['../classremwharead_1_1Export_1_1AsciiDoc.html',1,'remwharead::Export']]] + ['database',['Database',['../classremwharead_1_1Database.html',1,'remwharead']]] ]; diff --git a/docs/search/classes_1.js b/docs/search/classes_1.js index 0239cc4..81eef80 100644 --- a/docs/search/classes_1.js +++ b/docs/search/classes_1.js @@ -1,4 +1,4 @@ var searchData= [ - ['bookmarks',['Bookmarks',['../classremwharead_1_1Export_1_1Bookmarks.html',1,'remwharead::Export']]] + ['entry',['entry',['../structremwharead_1_1Database_1_1entry.html',1,'remwharead::Database']]] ]; diff --git a/docs/search/classes_2.js b/docs/search/classes_2.js index b9ded6e..ce5019c 100644 --- a/docs/search/classes_2.js +++ b/docs/search/classes_2.js @@ -1,4 +1,4 @@ var searchData= [ - ['csv',['CSV',['../classremwharead_1_1Export_1_1CSV.html',1,'remwharead::Export']]] + ['html_5fextract',['html_extract',['../structremwharead_1_1html__extract.html',1,'remwharead']]] ]; diff --git a/docs/search/classes_3.js b/docs/search/classes_3.js index acbcf84..893656f 100644 --- a/docs/search/classes_3.js +++ b/docs/search/classes_3.js @@ -1,4 +1,4 @@ var searchData= [ - ['database',['Database',['../classremwharead_1_1Database.html',1,'remwharead']]] + ['uri',['URI',['../classremwharead_1_1URI.html',1,'remwharead']]] ]; diff --git a/docs/search/functions_2.js b/docs/search/functions_2.js index 7c19138..72d4b72 100644 --- a/docs/search/functions_2.js +++ b/docs/search/functions_2.js @@ -1,6 +1,5 @@ var searchData= [ - ['exportbase',['ExportBase',['../classremwharead_1_1Export_1_1ExportBase.html#aa3c6d5cb261aaf26aafc8c4a81c83678',1,'remwharead::Export::ExportBase']]], ['extract_5fdescription',['extract_description',['../classremwharead_1_1URI.html#ae6ff7a41b9529eb8f4c7f2ace7260dc7',1,'remwharead::URI']]], ['extract_5ftitle',['extract_title',['../classremwharead_1_1URI.html#a37f93c46371d9b3753ae04bd2ef2c362',1,'remwharead::URI']]] ]; diff --git a/docs/search/functions_5.js b/docs/search/functions_5.js index 05a1343..303b720 100644 --- a/docs/search/functions_5.js +++ b/docs/search/functions_5.js @@ -1,4 +1,4 @@ var searchData= [ - ['operator_20bool',['operator bool',['../classremwharead_1_1Database.html#adf363243852b2a5fec1911139d4936c1',1,'remwharead::Database']]] + ['make_5frequest',['make_request',['../classremwharead_1_1URI.html#a2eadd0b24e6a37c8c42d710707bbfedf',1,'remwharead::URI']]] ]; diff --git a/docs/search/functions_6.js b/docs/search/functions_6.js index 28a43a7..05a1343 100644 --- a/docs/search/functions_6.js +++ b/docs/search/functions_6.js @@ -1,4 +1,4 @@ var searchData= [ - ['print',['print',['../classremwharead_1_1Export_1_1AsciiDoc.html#a20ce832d0cea815b048bbe5c51496a77',1,'remwharead::Export::AsciiDoc::print()'],['../classremwharead_1_1Export_1_1Bookmarks.html#af92b6e7c8bf46032dcf65267ce83d043',1,'remwharead::Export::Bookmarks::print()'],['../classremwharead_1_1Export_1_1CSV.html#a107c3390677129f00a6f45b924e2a539',1,'remwharead::Export::CSV::print()'],['../classremwharead_1_1Export_1_1ExportBase.html#aee596eaefecdb1c21c37f5e3d129ed56',1,'remwharead::Export::ExportBase::print()'],['../classremwharead_1_1Export_1_1Simple.html#af688d80f3d7903d59ef730311e32b7f8',1,'remwharead::Export::Simple::print()']]] + ['operator_20bool',['operator bool',['../classremwharead_1_1Database.html#adf363243852b2a5fec1911139d4936c1',1,'remwharead::Database']]] ]; diff --git a/docs/search/functions_8.js b/docs/search/functions_8.js index 0d0ae49..540cc63 100644 --- a/docs/search/functions_8.js +++ b/docs/search/functions_8.js @@ -1,7 +1,5 @@ var searchData= [ - ['set_5fcurlpp_5foptions',['set_curlpp_options',['../classremwharead_1_1URI.html#a203f46af6271ecd5a1ff01c63461d842',1,'remwharead::URI']]], - ['sort_5fentries',['sort_entries',['../classremwharead_1_1Export_1_1ExportBase.html#a0a0515408c0af2f0d74fe8e483882384',1,'remwharead::Export::ExportBase']]], ['store',['store',['../classremwharead_1_1Database.html#ab3ea9062c5c0ef5d9f2b7eea6f0fd1bd',1,'remwharead::Database']]], ['strip_5fhtml',['strip_html',['../classremwharead_1_1URI.html#ad6ad5351ecf2983e01f9f4a51c2057a5',1,'remwharead::URI']]] ]; diff --git a/docs/search/searchdata.js b/docs/search/searchdata.js index f28a50d..d472540 100644 --- a/docs/search/searchdata.js +++ b/docs/search/searchdata.js @@ -1,9 +1,9 @@ var indexSectionsWithContent = { - 0: "abcdefghoprstu", - 1: "abcdehsu", + 0: "adefghmorstu", + 1: "dehu", 2: "st", - 3: "adefgoprsu", + 3: "adefgmorsu", 4: "e", 5: "e", 6: "o", diff --git a/docs/search_8hpp.html b/docs/search_8hpp.html index 888dfb4..9a61082 100644 --- a/docs/search_8hpp.html +++ b/docs/search_8hpp.html @@ -5,7 +5,7 @@ -remwharead: src/lib/search.hpp File Reference +remwharead: include/search.hpp File Reference @@ -62,7 +62,7 @@ $(function() {
    diff --git a/docs/search_8hpp_source.html b/docs/search_8hpp_source.html index ba62ced..bc53b8f 100644 --- a/docs/search_8hpp_source.html +++ b/docs/search_8hpp_source.html @@ -5,7 +5,7 @@ -remwharead: src/lib/search.hpp Source File +remwharead: include/search.hpp Source File @@ -62,7 +62,7 @@ $(function() {
    diff --git a/docs/sqlite_8hpp_source.html b/docs/sqlite_8hpp_source.html index aaf1086..53f7835 100644 --- a/docs/sqlite_8hpp_source.html +++ b/docs/sqlite_8hpp_source.html @@ -5,7 +5,7 @@ -remwharead: src/lib/sqlite.hpp Source File +remwharead: include/sqlite.hpp Source File @@ -62,7 +62,7 @@ $(function() {
    @@ -72,12 +72,12 @@ $(function() {
    1 /* This file is part of remwharead.
    2  * Copyright © 2019 tastytea <tastytea@tastytea.de>
    3  *
    4  * This program is free software: you can redistribute it and/or modify
    5  * it under the terms of the GNU General Public License as published by
    6  * the Free Software Foundation, version 3.
    7  *
    8  * This program is distributed in the hope that it will be useful,
    9  * but WITHOUT ANY WARRANTY; without even the implied warranty of
    10  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
    11  * GNU General Public License for more details.
    12  *
    13  * You should have received a copy of the GNU General Public License
    14  * along with this program. If not, see <http://www.gnu.org/licenses/>.
    15  */
    16 
    17 #ifndef REMWHAREAD_SQLITE_HPP
    18 #define REMWHAREAD_SQLITE_HPP
    19 
    20 #include <experimental/filesystem>
    21 #include <memory>
    22 #include <string>
    23 #include <vector>
    24 #include <chrono>
    25 #include <sqlite/connection.hpp>
    26 
    27 namespace remwharead
    28 {
    29  namespace fs = std::experimental::filesystem;
    30  using std::string;
    31  using std::vector;
    32  using std::chrono::system_clock;
    33  using time_point = system_clock::time_point;
    34 
    36  class Database
    37  {
    38  public:
    40  typedef struct entry
    41  {
    42  string uri;
    43  string archive_uri;
    44  time_point datetime;
    45  vector<string> tags;
    46  string title;
    47  string description;
    48  string fulltext;
    49 
    51  friend bool operator ==(const Database::entry &a,
    52  const Database::entry &b);
    54  const string fulltext_oneline() const;
    55  } entry;
    56 
    58  Database();
    59 
    61  operator bool() const;
    62 
    64  void store(const entry &data) const;
    65 
    67  const vector<entry> retrieve(
    68  const time_point &start = time_point(),
    69  const time_point &end = system_clock::now()) const;
    70 
    71  private:
    72  fs::path _dbpath;
    73  std::unique_ptr<sqlite::connection> _con;
    74  bool _connected;
    75  };
    76 
    77  using DB = Database;
    78 }
    79 
    80 #endif // REMWHAREAD_SQLITE_HPP
    remwharead::Database::entry
    struct remwharead::Database::entry entry
    Describes a database entry.
    remwharead::Database
    Store and retrieve files from/to SQLite.
    Definition: sqlite.hpp:36
    -
    remwharead::Database::store
    void store(const entry &data) const
    Store a Database::entry in the database.
    Definition: sqlite.cpp:87
    +
    remwharead::Database::store
    void store(const entry &data) const
    Store a Database::entry in the database.
    Definition: sqlite.cpp:82
    remwharead::Database::entry
    Describes a database entry.
    Definition: sqlite.hpp:40
    remwharead
    Definition: search.cpp:23
    remwharead::Database::entry::operator==
    friend bool operator==(const Database::entry &a, const Database::entry &b)
    Returns true if date and time are equal.
    Definition: sqlite.cpp:66
    -
    remwharead::Database::entry::fulltext_oneline
    const string fulltext_oneline() const
    The full text in one line.
    Definition: sqlite.cpp:76
    -
    remwharead::Database::retrieve
    const vector< entry > retrieve(const time_point &start=time_point(), const time_point &end=system_clock::now()) const
    Retrieve a vector of Database::entry from the database.
    Definition: sqlite.cpp:114
    +
    remwharead::Database::entry::fulltext_oneline
    const string fulltext_oneline() const
    The full text in one line.
    Definition: sqlite.cpp:71
    +
    remwharead::Database::retrieve
    const vector< entry > retrieve(const time_point &start=time_point(), const time_point &end=system_clock::now()) const
    Retrieve a vector of Database::entry from the database.
    Definition: sqlite.cpp:109
    remwharead::Database::Database
    Database()
    Connects to the database and creates it if necessary.
    Definition: sqlite.cpp:31
    diff --git a/docs/structremwharead_1_1Database_1_1entry.html b/docs/structremwharead_1_1Database_1_1entry.html index e2509d2..c5201c6 100644 --- a/docs/structremwharead_1_1Database_1_1entry.html +++ b/docs/structremwharead_1_1Database_1_1entry.html @@ -136,7 +136,7 @@ Friends

    The full text in one line.

    -
    77  {
    78  string oneline = fulltext;
    79  size_t pos = 0;
    80  while ((pos = oneline.find('\n', pos)) != std::string::npos)
    81  {
    82  oneline.replace(pos, 1, "\\n");
    83  }
    84  return oneline;
    85  }
    +
    72  {
    73  string oneline = fulltext;
    74  size_t pos = 0;
    75  while ((pos = oneline.find('\n', pos)) != std::string::npos)
    76  {
    77  oneline.replace(pos, 1, "\\n");
    78  }
    79  return oneline;
    80  }

    Friends And Related Function Documentation

    @@ -175,11 +175,11 @@ Friends

    Returns true if date and time are equal.

    -
    67  {
    68  if (a.datetime == b.datetime)
    69  {
    70  return true;
    71  }
    72 
    73  return false;
    74  }
    +
    67  {
    68  return (a.datetime == b.datetime);
    69  }
    The documentation for this struct was generated from the following files: diff --git a/docs/structremwharead_1_1html__extract.html b/docs/structremwharead_1_1html__extract.html index 2b6eb70..b82183a 100644 --- a/docs/structremwharead_1_1html__extract.html +++ b/docs/structremwharead_1_1html__extract.html @@ -94,7 +94,7 @@ string fulltext

    Detailed Description

    A processed HTML page.

    The documentation for this struct was generated from the following file: diff --git a/docs/time_8hpp.html b/docs/time_8hpp.html index b34e433..58bbd7c 100644 --- a/docs/time_8hpp.html +++ b/docs/time_8hpp.html @@ -5,7 +5,7 @@ -remwharead: src/lib/time.hpp File Reference +remwharead: include/time.hpp File Reference @@ -62,7 +62,7 @@ $(function() {
    diff --git a/docs/time_8hpp_source.html b/docs/time_8hpp_source.html index 07fb5a8..03f9379 100644 --- a/docs/time_8hpp_source.html +++ b/docs/time_8hpp_source.html @@ -5,7 +5,7 @@ -remwharead: src/lib/time.hpp Source File +remwharead: include/time.hpp Source File @@ -62,7 +62,7 @@ $(function() {
    diff --git a/docs/types_8hpp.html b/docs/types_8hpp.html index d63f3e2..8163058 100644 --- a/docs/types_8hpp.html +++ b/docs/types_8hpp.html @@ -5,7 +5,7 @@ -remwharead: src/lib/types.hpp File Reference +remwharead: include/types.hpp File Reference @@ -62,7 +62,7 @@ $(function() {
    diff --git a/docs/types_8hpp_source.html b/docs/types_8hpp_source.html index 9ae4b8a..11c3c24 100644 --- a/docs/types_8hpp_source.html +++ b/docs/types_8hpp_source.html @@ -5,7 +5,7 @@ -remwharead: src/lib/types.hpp Source File +remwharead: include/types.hpp Source File @@ -62,7 +62,7 @@ $(function() {
    diff --git a/docs/uri_8hpp_source.html b/docs/uri_8hpp_source.html index c0e3381..6a5016a 100644 --- a/docs/uri_8hpp_source.html +++ b/docs/uri_8hpp_source.html @@ -5,7 +5,7 @@ -remwharead: src/lib/uri.hpp Source File +remwharead: include/uri.hpp Source File @@ -62,7 +62,7 @@ $(function() {
    @@ -70,18 +70,18 @@ $(function() {
    uri.hpp
    -
    1 /* This file is part of remwharead.
    2  * Copyright © 2019 tastytea <tastytea@tastytea.de>
    3  *
    4  * This program is free software: you can redistribute it and/or modify
    5  * it under the terms of the GNU General Public License as published by
    6  * the Free Software Foundation, version 3.
    7  *
    8  * This program is distributed in the hope that it will be useful,
    9  * but WITHOUT ANY WARRANTY; without even the implied warranty of
    10  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
    11  * GNU General Public License for more details.
    12  *
    13  * You should have received a copy of the GNU General Public License
    14  * along with this program. If not, see <http://www.gnu.org/licenses/>.
    15  */
    16 
    17 #ifndef REMWHAREAD_URI_HPP
    18 #define REMWHAREAD_URI_HPP
    19 
    20 #include <string>
    21 #include <curlpp/Easy.hpp>
    22 
    23 namespace remwharead
    24 {
    25  using std::string;
    26 
    28  typedef struct html_extract
    29  {
    30  string title;
    31  string description;
    32  string fulltext;
    33  } html_extract;
    34 
    36  class URI
    37  {
    38  public:
    40  explicit URI(const string &uri);
    41 
    43  const html_extract get();
    44 
    46  const string archive();
    47 
    48  protected:
    49  string _uri;
    50 
    52  void set_curlpp_options(curlpp::Easy &request);
    53 
    55  const string extract_title(const string &html);
    56 
    58  const string extract_description(const string &html);
    59 
    61  const string strip_html(const string &html);
    62 
    69  const string remove_html_tags(const string &html,
    70  const string &tag = "");
    71 
    73  const string unescape_html(const string &html);
    74 
    76  const string remove_newlines(string text);
    77  };
    78 }
    79 
    80 #endif // REMWHAREAD_URI_HPP
    remwharead::html_extract
    A processed HTML page.
    Definition: uri.hpp:28
    -
    remwharead::URI::URI
    URI(const string &uri)
    Construct object and set URL.
    Definition: uri.cpp:43
    -
    remwharead::URI::remove_html_tags
    const string remove_html_tags(const string &html, const string &tag="")
    Remove HTML tags.
    Definition: uri.cpp:137
    +
    1 /* This file is part of remwharead.
    2  * Copyright © 2019 tastytea <tastytea@tastytea.de>
    3  *
    4  * This program is free software: you can redistribute it and/or modify
    5  * it under the terms of the GNU General Public License as published by
    6  * the Free Software Foundation, version 3.
    7  *
    8  * This program is distributed in the hope that it will be useful,
    9  * but WITHOUT ANY WARRANTY; without even the implied warranty of
    10  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
    11  * GNU General Public License for more details.
    12  *
    13  * You should have received a copy of the GNU General Public License
    14  * along with this program. If not, see <http://www.gnu.org/licenses/>.
    15  */
    16 
    17 #ifndef REMWHAREAD_URI_HPP
    18 #define REMWHAREAD_URI_HPP
    19 
    20 #include <string>
    21 
    22 namespace remwharead
    23 {
    24  using std::string;
    25 
    27  typedef struct html_extract
    28  {
    29  string title;
    30  string description;
    31  string fulltext;
    32  } html_extract;
    33 
    35  class URI
    36  {
    37  public:
    39  explicit URI(const string &uri);
    40  ~URI();
    41 
    43  const html_extract get();
    44 
    46  const string archive();
    47 
    48  protected:
    49  string _uri;
    50 
    52  const string make_request(const string &uri) const;
    53 
    55  const string extract_title(const string &html);
    56 
    58  const string extract_description(const string &html);
    59 
    61  const string strip_html(const string &html);
    62 
    69  const string remove_html_tags(const string &html,
    70  const string &tag = "");
    71 
    73  const string unescape_html(const string &html);
    74 
    76  const string remove_newlines(string text);
    77  };
    78 }
    79 
    80 #endif // REMWHAREAD_URI_HPP
    remwharead::html_extract
    A processed HTML page.
    Definition: uri.hpp:27
    +
    remwharead::URI::URI
    URI(const string &uri)
    Construct object and set URL.
    Definition: uri.cpp:56
    +
    remwharead::URI::remove_html_tags
    const string remove_html_tags(const string &html, const string &tag="")
    Remove HTML tags.
    Definition: uri.cpp:230
    remwharead
    Definition: search.cpp:23
    -
    remwharead::URI::strip_html
    const string strip_html(const string &html)
    Removes HTML tags and superflous spaces from an HTML page.
    Definition: uri.cpp:118
    -
    remwharead::URI::remove_newlines
    const string remove_newlines(string text)
    Replace newlines with spaces.
    Definition: uri.cpp:514
    -
    remwharead::URI::unescape_html
    const string unescape_html(const string &html)
    Convert HTML entities to UTF-8.
    Definition: uri.cpp:175
    -
    remwharead::URI::set_curlpp_options
    void set_curlpp_options(curlpp::Easy &request)
    Sets common curlpp options.
    Definition: uri.cpp:83
    -
    remwharead::URI::extract_title
    const string extract_title(const string &html)
    Extract the title from an HTML page.
    Definition: uri.cpp:91
    -
    remwharead::URI
    Download, archive and process an URI.
    Definition: uri.hpp:36
    -
    remwharead::URI::archive
    const string archive()
    Save URI in archive and return archive-URI.
    Definition: uri.cpp:475
    -
    remwharead::URI::extract_description
    const string extract_description(const string &html)
    Extract the description from an HTML page.
    Definition: uri.cpp:104
    +
    remwharead::URI::strip_html
    const string strip_html(const string &html)
    Removes HTML tags and superflous spaces from an HTML page.
    Definition: uri.cpp:211
    +
    remwharead::URI::remove_newlines
    const string remove_newlines(string text)
    Replace newlines with spaces.
    Definition: uri.cpp:598
    +
    remwharead::URI::unescape_html
    const string unescape_html(const string &html)
    Convert HTML entities to UTF-8.
    Definition: uri.cpp:268
    +
    remwharead::URI::extract_title
    const string extract_title(const string &html)
    Extract the title from an HTML page.
    Definition: uri.cpp:184
    +
    remwharead::URI
    Download, archive and process an URI.
    Definition: uri.hpp:35
    +
    remwharead::URI::archive
    const string archive()
    Save URI in archive and return archive-URI.
    Definition: uri.cpp:568
    +
    remwharead::URI::extract_description
    const string extract_description(const string &html)
    Extract the description from an HTML page.
    Definition: uri.cpp:197
    +
    remwharead::URI::make_request
    const string make_request(const string &uri) const
    Make a HTTP(S) request.
    Definition: uri.cpp:129