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
|
////////////////////////////////////////////////////////////////////////
//
// Copyright (C) 2009-2021 The Octave Project Developers
//
// See the file COPYRIGHT.md in the top-level directory of this
// distribution or <https://octave.org/copyright/>.
//
// This file is part of Octave.
//
// Octave 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.
//
// Octave 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 Octave; see the file COPYING. If not, see
// <https://www.gnu.org/licenses/>.
//
////////////////////////////////////////////////////////////////////////
#if defined (HAVE_CONFIG_H)
# include "config.h"
#endif
#include "ls-ascii-helper.h"
#include <istream>
#include <sstream>
// Helper functions when reading from ascii files.
// These functions take care of different line endings (LF, CR, CRLF)
// when files were opened in text mode for writing and are now opened in
// binary mode for reading.
// Even though we no longer store files in text mode, keep this logic
// to allow loading older files that might have CRLF or CR line endings.
// Skip characters from stream IS until a newline is reached.
// Depending on KEEP_NEWLINE, either eat newline from stream or
// keep it unread.
void
skip_until_newline (std::istream& is, bool keep_newline)
{
if (! is)
return;
while (is)
{
char c = is.peek ();
if (c == '\n' || c == '\r')
{
// Reached newline.
if (! keep_newline)
{
// Eat the CR or LF character.
char d;
is.get (d);
// Make sure that for binary-mode opened ascii files
// containing CRLF line endings we skip the LF after CR.
if (c == '\r' && is.peek () == '\n')
{
// Yes, LF following CR, eat it.
is.get (d);
}
}
// Newline was found, and read from stream if
// keep_newline == true, so exit loop.
break;
}
else
{
// No newline character peeked, so read it and proceed to next
// character.
char d;
is.get (d);
}
}
}
// If stream IS currently points to a newline (a leftover from a previous read)
// then eat newline(s) until a non-newline character is found.
void
skip_preceeding_newline (std::istream& is)
{
if (! is)
return;
// Check whether IS currently points to newline character.
char c = is.peek ();
if (c == '\n' || c == '\r')
{
// Yes, at newline.
do
{
// Eat the CR or LF character.
char d;
is.get (d);
// Make sure that for binary-mode opened ascii files
// containing CRLF line endings we skip the LF after CR.
if (c == '\r' && is.peek () == '\n')
{
// Yes, LF following CR, eat it.
is.get (d);
}
// Peek into next character.
c = is.peek ();
// Loop while still a newline ahead.
}
while (c == '\n' || c == '\r');
}
}
// Read characters from stream IS until a newline is reached.
// Depending on KEEP_NEWLINE, either eat newline from stream or keep
// it unread. Characters read are stored and returned as
// std::string.
std::string
read_until_newline (std::istream& is, bool keep_newline)
{
if (! is)
return "";
std::ostringstream buf;
while (is)
{
char c = is.peek ();
if (c == '\n' || c == '\r')
{
// Reached newline.
if (! keep_newline)
{
// Eat the CR or LF character.
char d;
is.get (d);
// Make sure that for binary-mode opened ascii files
// containing CRLF line endings we skip the LF after
// CR.
if (c == '\r' && is.peek () == '\n')
{
// Yes, LF following CR, eat it.
is.get (d);
}
}
// Newline was found, and read from stream if
// keep_newline == true, so exit loop.
break;
}
else
{
// No newline character peeked, so read it, store it, and
// proceed to next.
char d;
is.get (d);
buf << d;
}
}
return buf.str ();
}
|
