summaryrefslogtreecommitdiff
path: root/src/core/BufferedCharReader.cpp
blob: aeedf12a1bc9a47764bf2f46047a28651639e0a1 (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
/*
    Ousía
    Copyright (C) 2014, 2015  Benjamin Paaßen, Andreas Stöckel

    This program is free software: you can redistribute it and/or modify
    it under the terms of the GNU General Public License as published by
    the Free Software Foundation, either version 3 of the License, or
    (at your option) any later version.

    This program is distributed in the hope that it will be useful,
    but WITHOUT ANY WARRANTY; without even the implied warranty of
    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
    GNU General Public License for more details.

    You should have received a copy of the GNU General Public License
    along with this program.  If not, see <http://www.gnu.org/licenses/>.
*/

#include <array>

#include "Utils.hpp"

#include "BufferedCharReader.hpp"

namespace ousia {

// Constants used within the linebreak statemachine.
static const uint8_t LB_STATE_NONE = 0x00;
static const uint8_t LB_STATE_ONE = 0x01;
static const uint8_t LB_STATE_LF = 0x10;
static const uint8_t LB_STATE_CR = 0x20;
static const uint8_t LB_STATE_MASK_CNT = 0x0F;
static const uint8_t LB_STATE_MASK_TYPE = 0xF0;

/* Struct BufferedCharReader::ReadCursor */

BufferedCharReader::ReadCursor::ReadCursor(unsigned int line,
                                           unsigned int column,
                                           bool destructive)
    : line(line),
      column(column),
      bufferElem(0),
      bufferPos(0),
      destructive(destructive),
      lbState(LB_STATE_NONE)
{
}

void BufferedCharReader::ReadCursor::assign(const ReadCursor &cursor)
{
	this->line = cursor.line;
	this->column = cursor.column;
	this->bufferElem = cursor.bufferElem;
	this->bufferPos = cursor.bufferPos;
	this->lbState = cursor.lbState;
}

/* Class BufferedCharReader */

BufferedCharReader::BufferedCharReader(int line, int column)
    : inputStream(nullptr),
      readCursor(line, column, true),
      peekCursor(line, column, false),
      depleted(false)
{
}

BufferedCharReader::BufferedCharReader(const std::string &str, int line,
                                       int column)
    : inputStream(nullptr),
      readCursor(line, column, true),
      peekCursor(line, column, false),
      depleted(true)
{
	buffer.push_back(str);
}

BufferedCharReader::BufferedCharReader(const std::string &str)
    : inputStream(nullptr),
      readCursor(1, 1, true),
      peekCursor(1, 1, false),
      depleted(true)
{
	buffer.push_back(str);
}

BufferedCharReader::BufferedCharReader(std::istream &inputStream, int line,
                                       int column)
    : inputStream(&inputStream),
      readCursor(line, column, true),
      peekCursor(line, column, false),
      depleted(false)
{
}

void BufferedCharReader::feed(const std::string &data)
{
	if (!depleted && !inputStream) {
		buffer.push_back(data);
	}
}

void BufferedCharReader::close()
{
	if (!inputStream) {
		depleted = true;
	}
}

bool BufferedCharReader::substituteLinebreaks(ReadCursor &cursor, char *c)
{
	// Handle line breaks, inserts breakes after the following character
	// combinations: \n, \r, \n\r, \r\n TODO: Change behaviour to \n, \n\r, \r\n
	if ((*c == '\n') || (*c == '\r')) {
		// Determine the type of the current linebreak character
		const uint8_t type = (*c == '\n') ? LB_STATE_LF : LB_STATE_CR;

		// Read the last count and the last type from the state
		const uint8_t lastCount = cursor.lbState & LB_STATE_MASK_CNT;
		const uint8_t lastType = cursor.lbState & LB_STATE_MASK_TYPE;

		// Set the current linebreak type and counter in the state
		cursor.lbState = ((lastCount + 1) & 1) | type;

		// If either this is the first instance of this character or the same
		// return character is repeated
		if (!lastCount || (lastType == type)) {
			*c = '\n';
			return true;
		}
		return false;
	}

	// Find the state
	cursor.lbState = LB_STATE_NONE;
	return true;
}

bool BufferedCharReader::readCharacterAtCursor(ReadCursor &cursor, char *c)
{
	bool hasChar = false;
	while (!hasChar) {
		// Abort if the current buffer element does not point to a valid entry
		// in the buffer -- we must try to feed another data block into the
		// internal buffer
		if (cursor.bufferElem >= buffer.size()) {
			// Abort if there is no more data or no input stream is set
			if (depleted || !inputStream) {
				return false;
			}

			// Read a buffer of the specified size
			constexpr std::streamsize BUFFER_SIZE = 1024;
			std::array<char, BUFFER_SIZE> buf;
			const std::streamsize cnt =
			    (*inputStream).read(buf.data(), BUFFER_SIZE).gcount();

			// If data has been read, append it to the input buffer and try
			// again
			if (cnt > 0) {
				buffer.emplace_back(std::string(buf.data(), cnt));
				continue;
			}

			// End of file handling
			if (inputStream->fail() || inputStream->eof()) {
				depleted = true;
				return false;
			}
		}

		// Fetch the current element the peek pointer points to
		const std::string &data = buffer[cursor.bufferElem];

		// Handle the "no data" case -- either in a destructive or
		// non-destructive manner.
		if (cursor.bufferPos >= data.length()) {
			if (cursor.destructive) {
				buffer.pop_front();
			} else {
				cursor.bufferElem++;
			}
			cursor.bufferPos = 0;
			continue;
		}

		// Read the character, advance the buffer position
		*c = *(data.data() + cursor.bufferPos);
		cursor.bufferPos++;

		// Substitute linebreaks with a single LF (0x0A)
		hasChar = substituteLinebreaks(cursor, c);
	}

	// Update the position counter
	if (*c == '\n') {
		cursor.line++;
		cursor.column = 1;
	} else {
		// Ignore UTF-8 continuation bytes
		if (!((*c & 0x80) && !(*c & 0x40))) {
			cursor.column++;
		}
	}

	return true;
}

bool BufferedCharReader::peek(char *c)
{
	return readCharacterAtCursor(peekCursor, c);
}

bool BufferedCharReader::read(char *c)
{
	resetPeek();
	return readCharacterAtCursor(readCursor, c);
}

void BufferedCharReader::consumePeek()
{
	// Remove all no longer needed buffer elements
	for (unsigned int i = 0; i < peekCursor.bufferElem; i++) {
		buffer.pop_front();
	}
	peekCursor.bufferElem = 0;

	// Copy the peek cursor to the read cursor
	readCursor.assign(peekCursor);
}

bool BufferedCharReader::consumeWhitespace()
{
	char c;
	while (peek(&c)) {
		if (!Utils::isWhitespace(c)) {
			resetPeek();
			return true;
		}
		consumePeek();
	}
	return false;
}

void BufferedCharReader::resetPeek()
{
	// Reset the peek cursor to the read cursor
	peekCursor.assign(readCursor);
}

bool BufferedCharReader::atEnd() const
{
	if (depleted || !inputStream) {
		if (buffer.size() <= 0) {
			return true;
		} else if (buffer.size() == 1) {
			return buffer[0].size() == readCursor.bufferPos;
		}
	}
	return false;
}
}