forked from shuboc/LeetCode-2
-
Notifications
You must be signed in to change notification settings - Fork 1
/
web-crawler-multithreaded.cpp
151 lines (144 loc) · 4.68 KB
/
web-crawler-multithreaded.cpp
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
// Time: O(|V| + |E|)
// Space: O(|V|)
/**
* // This is the HtmlParser's API interface.
* // You should not implement it, or speculate about its implementation
* class HtmlParser {
* public:
* vector<string> getUrls(string url);
* };
*/
class Solution {
public:
vector<string> crawl(string startUrl, HtmlParser htmlParser) {
q_.emplace(startUrl);
unordered_set<string> lookup = {startUrl};
vector<thread> workers;
const auto& worker = [this](HtmlParser *htmlParser, unordered_set<string> *lookup) {
while (true) {
string from_url;
{
unique_lock<mutex> lock{m_};
cv_.wait(lock, [this]() { return !q_.empty(); });
from_url = q_.front(); q_.pop();
if (from_url.empty()) {
break;
}
++working_count_;
}
const auto& name = hostname(from_url);
for (const auto& to_url: htmlParser->getUrls(from_url)) {
if (name != hostname(to_url)) {
continue;
}
unique_lock<mutex> lock{m_};
if (!lookup->count(to_url)) {
lookup->emplace(to_url);
q_.emplace(to_url);
cv_.notify_all();
}
}
{
unique_lock<mutex> lock{m_};
--working_count_;
if (q_.empty() && !working_count_) {
cv_.notify_all();
}
}
}
};
for (int i = 0; i < NUMBER_OF_WORKERS; ++i) {
workers.emplace_back(worker, &htmlParser, &lookup);
}
{
unique_lock<mutex> lock{m_};
cv_.wait(lock, [this]() { return q_.empty() && !working_count_; });
for (const auto& t : workers) {
q_.emplace();
}
cv_.notify_all();
}
for (auto& t : workers) {
t.join();
}
return vector<string>(lookup.cbegin(), lookup.cend());
}
private:
string hostname(const string& url) {
static const string scheme = "http://";
return url.substr(0, url.find('/', scheme.length()));
}
static const int NUMBER_OF_WORKERS = 4;
queue<string> q_;
int working_count_ = 0;
mutex m_;
condition_variable cv_;
};
// Time: O(|V| + |E|)
// Space: O(|V|)
class Solution2 {
public:
vector<string> crawl(string startUrl, HtmlParser htmlParser) {
q_.emplace(startUrl);
unordered_set<string> lookup = {startUrl};
vector<thread> workers;
for (int i = 0; i < NUMBER_OF_WORKERS; ++i) {
workers.emplace_back(bind(&Solution2::worker, this, &htmlParser, &lookup));
}
{
unique_lock<mutex> lock{m_};
cv_.wait(lock, [this]() { return q_.empty() && !working_count_; });
for (const auto& t : workers) {
q_.emplace();
}
cv_.notify_all();
}
for (auto& t : workers) {
t.join();
}
return vector<string>(lookup.cbegin(), lookup.cend());
}
private:
void worker(HtmlParser *htmlParser, unordered_set<string> *lookup) {
while (true) {
string from_url;
{
unique_lock<mutex> lock{m_};
cv_.wait(lock, [this]() { return !q_.empty(); });
from_url = q_.front(); q_.pop();
if (from_url.empty()) {
break;
}
++working_count_;
}
const auto& name = hostname(from_url);
for (const auto& to_url: htmlParser->getUrls(from_url)) {
if (name != hostname(to_url)) {
continue;
}
unique_lock<mutex> lock{m_};
if (!lookup->count(to_url)) {
lookup->emplace(to_url);
q_.emplace(to_url);
cv_.notify_all();
}
}
{
unique_lock<mutex> lock{m_};
--working_count_;
if (q_.empty() && !working_count_) {
cv_.notify_all();
}
}
}
}
string hostname(const string& url) {
static const string scheme = "http://";
return url.substr(0, url.find('/', scheme.length()));
}
static const int NUMBER_OF_WORKERS = 4;
queue<string> q_;
int working_count_ = 0;
mutex m_;
condition_variable cv_;
};