summaryrefslogtreecommitdiff
path: root/Userland/Utilities/cut.cpp
blob: 792ae3be20cdd6ff84311ce2e8d119efa1284e75 (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
/*
 * Copyright (c) 2019-2020, Marios Prokopakis <mariosprokopakis@gmail.com>
 *
 * SPDX-License-Identifier: BSD-2-Clause
 */

#include <AK/QuickSort.h>
#include <AK/StdLibExtras.h>
#include <AK/String.h>
#include <AK/Vector.h>
#include <LibCore/ArgsParser.h>
#include <LibMain/Main.h>
#include <stdio.h>
#include <stdlib.h>

struct Range {
    size_t m_from { 1 };
    size_t m_to { SIZE_MAX };

    [[nodiscard]] bool intersects(const Range& other) const
    {
        return !(other.m_from > m_to || other.m_to < m_from);
    }

    void merge(const Range& other)
    {
        // Can't merge two ranges that are disjoint.
        VERIFY(intersects(other));

        m_from = min(m_from, other.m_from);
        m_to = max(m_to, other.m_to);
    }
};

static bool expand_list(String& list, Vector<Range>& ranges)
{
    Vector<String> tokens = list.split(',');

    for (auto& token : tokens) {
        if (token.length() == 0) {
            warnln("cut: byte/character positions are numbered from 1");
            return false;
        }

        if (token == "-") {
            warnln("cut: invalid range with no endpoint: {}", token);
            return false;
        }

        if (token[0] == '-') {
            auto index = token.substring(1, token.length() - 1).to_uint();
            if (!index.has_value()) {
                warnln("cut: invalid byte/character position '{}'", token);
                return false;
            }

            if (index.value() == 0) {
                warnln("cut: byte/character positions are numbered from 1");
                return false;
            }

            ranges.append({ 1, index.value() });
        } else if (token[token.length() - 1] == '-') {
            auto index = token.substring(0, token.length() - 1).to_uint();
            if (!index.has_value()) {
                warnln("cut: invalid byte/character position '{}'", token);
                return false;
            }

            if (index.value() == 0) {
                warnln("cut: byte/character positions are numbered from 1");
                return false;
            }

            ranges.append({ index.value(), SIZE_MAX });
        } else {
            auto range = token.split('-');
            if (range.size() == 2) {
                auto index1 = range[0].to_uint();
                if (!index1.has_value()) {
                    warnln("cut: invalid byte/character position '{}'", range[0]);
                    return false;
                }

                auto index2 = range[1].to_uint();
                if (!index2.has_value()) {
                    warnln("cut: invalid byte/character position '{}'", range[1]);
                    return false;
                }

                if (index1.value() > index2.value()) {
                    warnln("cut: invalid decreasing range");
                    return false;
                } else if (index1.value() == 0 || index2.value() == 0) {
                    warnln("cut: byte/character positions are numbered from 1");
                    return false;
                }

                ranges.append({ index1.value(), index2.value() });
            } else if (range.size() == 1) {
                auto index = range[0].to_uint();
                if (!index.has_value()) {
                    warnln("cut: invalid byte/character position '{}'", range[0]);
                    return false;
                }

                if (index.value() == 0) {
                    warnln("cut: byte/character positions are numbered from 1");
                    return false;
                }

                ranges.append({ index.value(), index.value() });
            } else {
                warnln("cut: invalid byte or character range");
                return false;
            }
        }
    }

    return true;
}

static void process_line_bytes(char* line, size_t length, const Vector<Range>& ranges)
{
    for (auto& i : ranges) {
        if (i.m_from >= length)
            continue;

        auto to = min(i.m_to, length);
        auto sub_string = String(line).substring(i.m_from - 1, to - i.m_from + 1);
        out("{}", sub_string);
    }
    outln();
}

static void process_line_fields(char* line, size_t length, const Vector<Range>& ranges, char delimiter)
{
    auto string_split = String(line, length).split(delimiter);
    Vector<String> output_fields;

    for (auto& range : ranges) {
        for (size_t i = range.m_from - 1; i < min(range.m_to, string_split.size()); i++) {
            output_fields.append(string_split[i]);
        }
    }

    outln("{}", String::join(delimiter, output_fields));
}

ErrorOr<int> serenity_main(Main::Arguments arguments)
{
    String byte_list = "";
    String fields_list = "";
    String delimiter = "\t";

    Vector<StringView> files;

    Core::ArgsParser args_parser;
    args_parser.add_positional_argument(files, "file(s) to cut", "file", Core::ArgsParser::Required::No);
    args_parser.add_option(byte_list, "select only these bytes", "bytes", 'b', "list");
    args_parser.add_option(fields_list, "select only these fields", "fields", 'f', "list");
    args_parser.add_option(delimiter, "set a custom delimiter", "delimiter", 'd', "delimiter");
    args_parser.parse(arguments);

    bool selected_bytes = (byte_list != "");
    bool selected_fields = (fields_list != "");

    int selected_options_count = (selected_bytes ? 1 : 0) + (selected_fields ? 1 : 0);

    if (selected_options_count == 0) {
        warnln("cut: you must specify a list of bytes, or fields");
        args_parser.print_usage(stderr, arguments.strings[0].characters_without_null_termination());
        return 1;
    }

    if (selected_options_count > 1) {
        warnln("cut: you must specify only one of bytes, or fields");
        args_parser.print_usage(stderr, arguments.strings[0].characters_without_null_termination());
        return 1;
    }

    if (delimiter.length() != 1) {
        warnln("cut: the delimiter must be a single character");
        args_parser.print_usage(stderr, arguments.strings[0].characters_without_null_termination());
        return 1;
    }

    String ranges_list;
    Vector<Range> ranges_vector;

    if (selected_bytes) {
        ranges_list = byte_list;
    } else if (selected_fields) {
        ranges_list = fields_list;
    } else {
        // This should never happen, since we already checked the options count above.
        VERIFY_NOT_REACHED();
    }

    auto expansion_successful = expand_list(ranges_list, ranges_vector);

    if (!expansion_successful) {
        args_parser.print_usage(stderr, arguments.strings[0].characters_without_null_termination());
        return 1;
    }

    quick_sort(ranges_vector, [](auto& a, auto& b) { return a.m_from < b.m_from; });

    Vector<Range> disjoint_ranges;
    for (auto& range : ranges_vector) {
        if (disjoint_ranges.is_empty()) {
            disjoint_ranges.append(range);
            continue;
        }

        Range& last_range = disjoint_ranges.last();

        if (!last_range.intersects(range)) {
            disjoint_ranges.append(range);
            continue;
        }

        last_range.merge(range);
    }

    if (files.is_empty())
        files.append(String());

    /* Process each file */
    for (auto& file : files) {
        FILE* fp = stdin;
        if (!file.is_null()) {
            fp = fopen(String(file).characters(), "r");
            if (!fp) {
                warnln("cut: Could not open file '{}'", file);
                continue;
            }
        }

        char* line = nullptr;
        ssize_t line_length = 0;
        size_t line_capacity = 0;
        while ((line_length = getline(&line, &line_capacity, fp)) != -1) {
            if (line_length < 0) {
                warnln("cut: Failed to read line from file '{}'", file);
                break;
            }
            line[line_length - 1] = '\0';
            line_length--;

            if (selected_bytes) {
                process_line_bytes(line, line_length, disjoint_ranges);
            } else if (selected_fields) {
                process_line_fields(line, line_length, disjoint_ranges, delimiter[0]);
            } else {
                VERIFY_NOT_REACHED();
            }
        }

        if (line)
            free(line);

        if (!file.is_null())
            fclose(fp);
    }

    return 0;
}