unicode: Simplify width table generation
[glib.git] / gio / gconverter.c
blobc39700165da48e7f877a23e1ad184cf22a7c5fa9
1 /* GIO - GLib Input, Output and Streaming Library
3 * Copyright (C) 2009 Red Hat, Inc.
5 * This library is free software; you can redistribute it and/or
6 * modify it under the terms of the GNU Lesser General Public
7 * License as published by the Free Software Foundation; either
8 * version 2 of the License, or (at your option) any later version.
10 * This library is distributed in the hope that it will be useful,
11 * but WITHOUT ANY WARRANTY; without even the implied warranty of
12 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
13 * Lesser General Public License for more details.
15 * You should have received a copy of the GNU Lesser General
16 * Public License along with this library; if not, see <http://www.gnu.org/licenses/>.
18 * Author: Alexander Larsson <alexl@redhat.com>
21 #include "config.h"
22 #include "gconverter.h"
23 #include "glibintl.h"
26 /**
27 * SECTION:gconverter
28 * @short_description: Data conversion interface
29 * @include: gio/gio.h
30 * @see_also: #GInputStream, #GOutputStream
32 * #GConverter is implemented by objects that convert
33 * binary data in various ways. The conversion can be
34 * stateful and may fail at any place.
36 * Some example conversions are: character set conversion,
37 * compression, decompression and regular expression
38 * replace.
40 * Since: 2.24
41 **/
44 typedef GConverterIface GConverterInterface;
45 G_DEFINE_INTERFACE (GConverter, g_converter, G_TYPE_OBJECT)
47 static void
48 g_converter_default_init (GConverterInterface *iface)
52 /**
53 * g_converter_convert:
54 * @converter: a #GConverter.
55 * @inbuf: (array length=inbuf_size) (element-type guint8): the buffer
56 * containing the data to convert.
57 * @inbuf_size: the number of bytes in @inbuf
58 * @outbuf: a buffer to write converted data in.
59 * @outbuf_size: the number of bytes in @outbuf, must be at least one
60 * @flags: a #GConverterFlags controlling the conversion details
61 * @bytes_read: (out): will be set to the number of bytes read from @inbuf on success
62 * @bytes_written: (out): will be set to the number of bytes written to @outbuf on success
63 * @error: location to store the error occurring, or %NULL to ignore
65 * This is the main operation used when converting data. It is to be called
66 * multiple times in a loop, and each time it will do some work, i.e.
67 * producing some output (in @outbuf) or consuming some input (from @inbuf) or
68 * both. If its not possible to do any work an error is returned.
70 * Note that a single call may not consume all input (or any input at all).
71 * Also a call may produce output even if given no input, due to state stored
72 * in the converter producing output.
74 * If any data was either produced or consumed, and then an error happens, then
75 * only the successful conversion is reported and the error is returned on the
76 * next call.
78 * A full conversion loop involves calling this method repeatedly, each time
79 * giving it new input and space output space. When there is no more input
80 * data after the data in @inbuf, the flag %G_CONVERTER_INPUT_AT_END must be set.
81 * The loop will be (unless some error happens) returning %G_CONVERTER_CONVERTED
82 * each time until all data is consumed and all output is produced, then
83 * %G_CONVERTER_FINISHED is returned instead. Note, that %G_CONVERTER_FINISHED
84 * may be returned even if %G_CONVERTER_INPUT_AT_END is not set, for instance
85 * in a decompression converter where the end of data is detectable from the
86 * data (and there might even be other data after the end of the compressed data).
88 * When some data has successfully been converted @bytes_read and is set to
89 * the number of bytes read from @inbuf, and @bytes_written is set to indicate
90 * how many bytes was written to @outbuf. If there are more data to output
91 * or consume (i.e. unless the %G_CONVERTER_INPUT_AT_END is specified) then
92 * %G_CONVERTER_CONVERTED is returned, and if no more data is to be output
93 * then %G_CONVERTER_FINISHED is returned.
95 * On error %G_CONVERTER_ERROR is returned and @error is set accordingly.
96 * Some errors need special handling:
98 * %G_IO_ERROR_NO_SPACE is returned if there is not enough space
99 * to write the resulting converted data, the application should
100 * call the function again with a larger @outbuf to continue.
102 * %G_IO_ERROR_PARTIAL_INPUT is returned if there is not enough
103 * input to fully determine what the conversion should produce,
104 * and the %G_CONVERTER_INPUT_AT_END flag is not set. This happens for
105 * example with an incomplete multibyte sequence when converting text,
106 * or when a regexp matches up to the end of the input (and may match
107 * further input). It may also happen when @inbuf_size is zero and
108 * there is no more data to produce.
110 * When this happens the application should read more input and then
111 * call the function again. If further input shows that there is no
112 * more data call the function again with the same data but with
113 * the %G_CONVERTER_INPUT_AT_END flag set. This may cause the conversion
114 * to finish as e.g. in the regexp match case (or, to fail again with
115 * %G_IO_ERROR_PARTIAL_INPUT in e.g. a charset conversion where the
116 * input is actually partial).
118 * After g_converter_convert() has returned %G_CONVERTER_FINISHED the
119 * converter object is in an invalid state where its not allowed
120 * to call g_converter_convert() anymore. At this time you can only
121 * free the object or call g_converter_reset() to reset it to the
122 * initial state.
124 * If the flag %G_CONVERTER_FLUSH is set then conversion is modified
125 * to try to write out all internal state to the output. The application
126 * has to call the function multiple times with the flag set, and when
127 * the available input has been consumed and all internal state has
128 * been produced then %G_CONVERTER_FLUSHED (or %G_CONVERTER_FINISHED if
129 * really at the end) is returned instead of %G_CONVERTER_CONVERTED.
130 * This is somewhat similar to what happens at the end of the input stream,
131 * but done in the middle of the data.
133 * This has different meanings for different conversions. For instance
134 * in a compression converter it would mean that we flush all the
135 * compression state into output such that if you uncompress the
136 * compressed data you get back all the input data. Doing this may
137 * make the final file larger due to padding though. Another example
138 * is a regexp conversion, where if you at the end of the flushed data
139 * have a match, but there is also a potential longer match. In the
140 * non-flushed case we would ask for more input, but when flushing we
141 * treat this as the end of input and do the match.
143 * Flushing is not always possible (like if a charset converter flushes
144 * at a partial multibyte sequence). Converters are supposed to try
145 * to produce as much output as possible and then return an error
146 * (typically %G_IO_ERROR_PARTIAL_INPUT).
148 * Returns: a #GConverterResult, %G_CONVERTER_ERROR on error.
150 * Since: 2.24
152 GConverterResult
153 g_converter_convert (GConverter *converter,
154 const void *inbuf,
155 gsize inbuf_size,
156 void *outbuf,
157 gsize outbuf_size,
158 GConverterFlags flags,
159 gsize *bytes_read,
160 gsize *bytes_written,
161 GError **error)
163 GConverterIface *iface;
165 g_return_val_if_fail (G_IS_CONVERTER (converter), G_CONVERTER_ERROR);
166 g_return_val_if_fail (outbuf_size > 0, G_CONVERTER_ERROR);
168 *bytes_read = 0;
169 *bytes_written = 0;
171 iface = G_CONVERTER_GET_IFACE (converter);
173 return (* iface->convert) (converter,
174 inbuf, inbuf_size,
175 outbuf, outbuf_size,
176 flags,
177 bytes_read, bytes_written, error);
181 * g_converter_reset:
182 * @converter: a #GConverter.
184 * Resets all internal state in the converter, making it behave
185 * as if it was just created. If the converter has any internal
186 * state that would produce output then that output is lost.
188 * Since: 2.24
190 void
191 g_converter_reset (GConverter *converter)
193 GConverterIface *iface;
195 g_return_if_fail (G_IS_CONVERTER (converter));
197 iface = G_CONVERTER_GET_IFACE (converter);
199 (* iface->reset) (converter);