aboutsummaryrefslogtreecommitdiff
path: root/src/NetUtils.cpp
blob: 28256cb0270190269ca02c0b2610669ff8544909 (plain)
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
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
#include "../include/NetUtils.hpp"
#include "../include/StringUtils.hpp"
#include "../generated/Tlds.hpp"
#include <array>
#include <sstream>
#include <iomanip>
#include <assert.h>
#include <string.h>
#include <unordered_set>

namespace QuickMedia {
    struct HtmlEscapeSequence {
        char unescape_char;
        std::string escape_sequence;
    };

    void html_escape_sequences(std::string &str) {
        const std::array<HtmlEscapeSequence, 6> escape_sequences = {
            HtmlEscapeSequence { '&', "&amp;" }, // This should be first, to not accidentally replace a new sequence caused by replacing this
            HtmlEscapeSequence { '"', "&quot;" },
            HtmlEscapeSequence { '\'', "&#39;" },
            HtmlEscapeSequence { '<', "&lt;" },
            HtmlEscapeSequence { '>', "&gt;" },
            HtmlEscapeSequence { '\n', "<br>" }
        };

        for(const HtmlEscapeSequence &escape_sequence : escape_sequences) {
            string_replace_all(str, escape_sequence.unescape_char, escape_sequence.escape_sequence);
        }
    }

    struct HtmlUnescapeSequence {
        std::string escape_sequence;
        std::string unescaped_str;
    };

    static bool to_num(const char *str, size_t size, int &num) {
        num = 0;
        for(size_t i = 0; i < size; ++i) {
            const char num_c = str[i] - '0';
            if(num_c < 0 || num_c > 9)
                return false;
            num = (num * 10) + num_c;
        }
        return true;
    }

    static void html_unescape_sequence_numbers(std::string &str) {
        size_t index = 0;
        while(true) {
            index = str.find("&#", index);
            if(index == std::string::npos)
                break;
            
            index += 2;
            size_t end_index = str.find(';', index);
            if(end_index != std::string::npos && end_index - index <= 3) {
                const size_t num_length = end_index - index;
                int num;
                if(to_num(str.c_str() + index, num_length, num)) {
                    const char num_c = (char)num;
                    str.replace(index - 2, 2 + num_length + 1, &num_c, 1);
                    index += (-2 + 1);
                }
            }
        }
    }

    void html_unescape_sequences(std::string &str) {
        html_unescape_sequence_numbers(str);

        const std::array<HtmlUnescapeSequence, 4> unescape_sequences = {
            HtmlUnescapeSequence { "&quot;", "\"" },
            HtmlUnescapeSequence { "&lt;", "<" },
            HtmlUnescapeSequence { "&gt;", ">" },
            HtmlUnescapeSequence { "&amp;", "&" } // This should be last, to not accidentally replace a new sequence caused by replacing this
        };

        for(const HtmlUnescapeSequence &unescape_sequence : unescape_sequences) {
            string_replace_all(str, unescape_sequence.escape_sequence, unescape_sequence.unescaped_str);
        }
    }

    static bool is_alpha(char c) {
        return (c >= 'a' && c <= 'z') || (c >= 'A' && c <= 'Z');
    }

    static bool is_digit(char c) {
        return c >= '0' && c <= '9';
    }

    // Returns -1 if its not a hex value
    static int get_hex_value(char c) {
        if(c >= '0' && c <= '9')
            return c - '0';
        else if(c >= 'A' && c <= 'F')
            return 10 + (c - 'A');
        else if(c >= 'a' && c <= 'f')
            return 10 + (c - 'a');
        else
            return -1;
    }

    static bool is_whitespace(char c) {
        return c == ' ' || c == '\t' || c == '\n';
    }

    std::string url_param_encode(const std::string &param) {
        std::ostringstream result;
        result.fill('0');
        result << std::hex;

        for(char c : param) {
            if(is_alpha(c) || is_digit(c) || c == '-' || c == '_' || c == '.' || c == '~') {
                result << c;
            } else {
                result << std::uppercase;
                result << "%" << std::setw(2) << (int)(unsigned char)(c);
            }
        }

        return result.str();
    }

    std::string url_param_decode(const std::string &param) {
        std::string result;
        for(int i = 0; i < (int)param.size();) {
            char c = param[i];
            if(c == '%') {
                if(i < (int)param.size() - 1 && param[i + 1] == '%') {
                    result += c;
                    i += 2;
                } else if(i < (int)param.size() - 2) {
                    int first_c = get_hex_value(param[i + 1]);
                    int second_c = get_hex_value(param[i + 2]);
                    if(first_c != -1 && second_c != -1) {
                        result += (char)((first_c << 4) | second_c);
                        i += 3;
                    } else {
                        i += 1;
                    }
                } else {
                    i += 1;
                }
            } else if(c == '+') {
                result += ' ';
                i += 1;
            } else {
                result += c;
                i += 1;
            }
        }
        return result;
    }

    static bool is_url_start_char(char c) {
        return is_alpha(c) || is_digit(c) || c == '-' || c == '.' || c == '_' || c == '~';
    }

    static bool is_url_domain_char(char c) {
        return is_url_start_char(c);
    }

    // Implementation follows URI standard in general: https://tools.ietf.org/html/rfc3986#section-2.2.
    // Also checks for balanced parentheses to allow text such as: (see: example.com/) that excludes the last parenthesis.
    std::vector<Range> extract_urls(const std::string &str) {
        std::vector<Range> ranges;
        if(str.empty())
            return ranges;

        int parentheses_depth = 0;
        bool is_valid_url = false;
        bool is_domain_part = true;
        bool contains_dot = false;
        size_t url_start = std::string::npos;

        // str.size() is fine, we want to include the NULL character so we can extract url at the end of the string
        for(size_t i = 0; i < (size_t)str.size() + 1;) {
            char c = str[i];

            if(url_start != std::string::npos) {
                if(c == '(')
                    ++parentheses_depth;
                else if(c == ')')
                    --parentheses_depth;
            }

            if(url_start != std::string::npos && c == '.') {
                contains_dot = true;
            }

            if(url_start != std::string::npos && !is_valid_url && contains_dot && (is_whitespace(c) || c == '/' || c == ',' || c == ':' || c == '?' || c == ')' || c == '\0' || (c == '.' && i == str.size()))) {
                size_t tld_end = i - 1;
                char prev_char = str[i - 1];
                // We want to remove the last . or , because the string could contain for example "click on this link: example.com. There you can..."
                // and we want those links to work, I guess?
                if(prev_char == '.' || prev_char == ',' || prev_char == ':' || prev_char == '?')
                    --tld_end;
                else if(prev_char == ')' && parentheses_depth != 0)
                    --tld_end;
                size_t tld_start = tld_end;
                
                while(tld_start > url_start) {
                    if(str[tld_start] == '.')
                        break;
                    --tld_start;
                }

                if(tld_start > url_start && is_tld(str.substr(tld_start + 1, tld_end - tld_start))) {
                    is_valid_url = true;
                    is_domain_part = false;
                }
            }

            if(url_start != std::string::npos && is_domain_part && c == ':') {
                if(i + 2 < (size_t)str.size() + 1 && str[i + 1] == '/' && str[i + 2] == '/') {
                    i += 3;
                    continue;
                } else if(i + 1 < (size_t)str.size() + 1 && is_whitespace(str[i + 1])) {
                    i += 1;
                } else {
                    url_start = std::string::npos;
                    is_valid_url = false;
                    is_domain_part = true;
                    contains_dot = false;
                }
            }

            if(url_start != std::string::npos && is_domain_part && !is_url_domain_char(c)) {
                url_start = std::string::npos;
                is_valid_url = false;
                contains_dot = false;
            }

            if(url_start == std::string::npos && is_url_start_char(c)) {
                url_start = i;
            } else if(url_start != std::string::npos && (is_whitespace(c) || c == '\0')) {
                // Its only an url if there is a dot and the dot is not the last character in the url, for example "example.com" is an url but "example." is not.
                if(is_valid_url) {
                    size_t url_length = i - url_start;
                    char prev_char = str[i - 1];
                    // We want to remove the last . or , because the string could contain for example "click on this link: example.com. There you can..."
                    // and we want those links to work, I guess?
                    if(prev_char == '.' || prev_char == ',' || prev_char == ':' || prev_char == '?')
                        --url_length;
                    else if(prev_char == ')' && parentheses_depth != 0)
                        --url_length;
                    if(url_length > 0)
                        ranges.push_back({url_start, url_length});
                }

                url_start = std::string::npos;
                is_valid_url = false;
                is_domain_part = true;
                contains_dot = false;
            }

            ++i;
        }

        return ranges;
    }

    std::vector<std::string> ranges_get_strings(const std::string &str, const std::vector<Range> &ranges) {
        std::vector<std::string> strings(ranges.size());
        for(size_t i = 0; i < ranges.size(); ++i) {
            const Range &range = ranges[i];
            strings[i].assign(str.begin() + range.start, str.begin() + range.start + range.length);
        }
        return strings;
    }

    static size_t is_start_of_utf8_codepoint(uint8_t c) {
        if((c & 0x80) == 0)
            return true;
        else if((c & 0xE0) == 0xC0)
            return true;
        else if((c & 0xF0) == 0xE0)
            return true;
        else if((c & 0xF8) == 0xF0)
            return true;
        else
            return false;
    }

    void convert_utf8_to_utf32_ranges(const std::string &str, std::vector<Range> &ranges) {
        if(ranges.empty())
            return;

        size_t ranges_index = 0;
        size_t prev_range_offset = 0;
        size_t num_codepoints = 0;
        bool in_range = false;

        for(size_t i = 0; i < str.size(); ++i) {
            if(ranges_index > 0 && in_range) {
                ++prev_range_offset;
                if(prev_range_offset == ranges[ranges_index - 1].length) {
                    ranges[ranges_index - 1].length = num_codepoints - ranges[ranges_index - 1].start;
                    prev_range_offset = 0;
                    in_range = false;
                }
            }

            if(i == ranges[ranges_index].start) {
                in_range = true;
                ranges[ranges_index].start = num_codepoints;
                ++ranges_index;
                if(ranges_index == ranges.size())
                    break;
            }

            if(is_start_of_utf8_codepoint(*(uint8_t*)&str[i]))
                ++num_codepoints;
        }
    }

    std::string header_extract_value(const std::string &header, const std::string &type) {
        std::string result;
        string_split(header, '\n', [&type, &result](const char *str, size_t size) {
            while(size > 0 && (*str == ' ' || *str == '\t')) { ++str; --size; }
            if(size < type.size() || strncasecmp(str, type.c_str(), type.size()) != 0 || size == type.size())
                return true;

            str += type.size();
            size -= type.size();

            const void *colon_ptr = memchr(str, ':', size);
            if(!colon_ptr)
                return true;

            const size_t colon_offset = (const char*)colon_ptr - str;
            str += (colon_offset + 1);
            size -= (colon_offset + 1);

            while(size > 0 && (*str == ' ' || *str == '\t')) { ++str; --size; }
            while(size > 0 && (str[size - 1] == ' ' || str[size - 1] == '\t' || str[size - 1] == '\r' || str[size - 1] == '\n')) { --size; }

            result.assign(str, size);
            return false;
        });
        return result;
    }
}