1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
|
#include "rssignores.h"
#include <algorithm>
#include <cerrno>
#include <cstring>
#include <curl/curl.h>
#include <functional>
#include <iostream>
#include <langinfo.h>
#include <sstream>
#include <sys/utsname.h>
#include <string.h>
#include <time.h>
#include "cache.h"
#include "config.h"
#include "configcontainer.h"
#include "confighandlerexception.h"
#include "configparser.h"
#include "dbexception.h"
#include "htmlrenderer.h"
#include "logger.h"
#include "rssfeed.h"
#include "regexowner.h"
#include "strprintf.h"
#include "tagsouppullparser.h"
#include "utils.h"
namespace newsboat {
const std::string RssIgnores::REGEX_PREFIX = "regex:";
void RssIgnores::handle_action(const std::string& action,
const std::vector<std::string>& params)
{
if (action == "ignore-article") {
if (params.size() < 2) {
throw ConfigHandlerException(ActionHandlerStatus::TOO_FEW_PARAMS);
}
std::string ignore_rssurl = params[0];
std::string ignore_expr = params[1];
auto m = std::make_shared<Matcher>();
if (!m->parse(ignore_expr)) {
throw ConfigHandlerException(strprintf::fmt(
_("couldn't parse filter expression `%s': %s"),
ignore_expr,
m->get_parse_error()));
}
const int prefix_len = REGEX_PREFIX.length();
if (!ignore_rssurl.compare(0, prefix_len, REGEX_PREFIX)) {
std::string errorMessage;
const std::string pattern = ignore_rssurl.substr(prefix_len,
ignore_rssurl.length() - prefix_len);
const auto regex = Regex::compile(pattern, REG_EXTENDED | REG_ICASE, errorMessage);
if (regex == nullptr) {
throw ConfigHandlerException(strprintf::fmt(
_("`%s' is not a valid regular expression: %s"),
pattern, errorMessage));
}
}
ignores.push_back(FeedUrlExprPair(ignore_rssurl, m));
} else if (action == "always-download") {
if (params.empty()) {
throw ConfigHandlerException(ActionHandlerStatus::TOO_FEW_PARAMS);
}
for (const auto& param : params) {
ignores_lastmodified.push_back(param);
}
} else if (action == "reset-unread-on-update") {
if (params.empty()) {
throw ConfigHandlerException(ActionHandlerStatus::TOO_FEW_PARAMS);
}
for (const auto& param : params) {
resetflag.push_back(param);
}
} else {
throw ConfigHandlerException(ActionHandlerStatus::INVALID_COMMAND);
}
}
void RssIgnores::dump_config(std::vector<std::string>& config_output) const
{
for (const auto& ign : ignores) {
std::string configline = "ignore-article ";
if (ign.first == "*") {
configline.append("*");
} else {
configline.append(utils::quote(ign.first));
}
configline.append(" ");
configline.append(utils::quote(ign.second->get_expression()));
config_output.push_back(configline);
}
for (const auto& ign_lm : ignores_lastmodified) {
config_output.push_back(strprintf::fmt(
"always-download %s", utils::quote(ign_lm)));
}
for (const auto& rf : resetflag) {
config_output.push_back(strprintf::fmt(
"reset-unread-on-update %s", utils::quote(rf)));
}
}
bool RssIgnores::matches(RssItem* item)
{
const int prefix_len = REGEX_PREFIX.length();
for (const auto& ign : ignores) {
bool matched = false;
LOG(Level::DEBUG,
"RssIgnores::matches: ign.first = `%s' item->feedurl = `%s'",
ign.first,
item->feedurl());
if (!ign.first.compare(0, prefix_len, REGEX_PREFIX)) {
const std::string pattern = ign.first.substr(prefix_len, ign.first.length() - prefix_len);
std::string errorMessage;
const auto regex = Regex::compile(pattern, REG_EXTENDED | REG_ICASE, errorMessage);
const auto matches = regex->matches(item->feedurl(), 1, 0);
matched = !matches.empty();
} else {
matched = ign.first == "*" || item->feedurl() == ign.first;
}
if (matched && ign.second->matches(item)) {
LOG(Level::DEBUG,
"RssIgnores::matches: found match");
return true;
}
}
return false;
}
bool RssIgnores::matches_lastmodified(const std::string& url)
{
return std::find_if(ignores_lastmodified.begin(),
ignores_lastmodified.end(),
[&](const std::string& u) {
return u == url;
}) !=
ignores_lastmodified.end();
}
bool RssIgnores::matches_resetunread(const std::string& url)
{
return std::find_if(resetflag.begin(),
resetflag.end(),
[&](const std::string& u) {
return u == url;
}) !=
resetflag.end();
}
} // namespace newsboat
|
