annotate src/file-coding.h @ 5781:0853e1ec8529

Use alloca_{rawbytes,ibytes} in #'copy-file, #'insert-file-contents-internal src/ChangeLog addition: 2014-01-20 Aidan Kehoe <kehoea@parhasard.net> * fileio.c (Fcopy_file, Finsert_file_contents_internal): Use alloca_{rawbytes,ibytes} here instead of the implicit alloca on the stack; doesn't change where the buffers are allocated for these two functions, but does mean that decisions about alloca vs. malloc based on buffer size are made in the same place (ultimately, the ALLOCA() macro).
author Aidan Kehoe <kehoea@parhasard.net>
date Mon, 20 Jan 2014 17:53:07 +0000
parents 65d65b52d608
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
1 /* Header for encoding conversion functions; coding-system object.
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
2 #### rename me to coding-system.h
428
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
3 Copyright (C) 1991, 1995 Free Software Foundation, Inc.
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
4 Copyright (C) 1995 Sun Microsystems, Inc.
793
e38acbeb1cae [xemacs-hg @ 2002-03-29 04:46:17 by ben]
ben
parents: 771
diff changeset
5 Copyright (C) 2000, 2001, 2002 Ben Wing.
428
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
6
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
7 This file is part of XEmacs.
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
8
5402
308d34e9f07d Changed bulk of GPLv2 or later files identified by script
Mats Lidell <matsl@xemacs.org>
parents: 5127
diff changeset
9 XEmacs is free software: you can redistribute it and/or modify it
428
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
10 under the terms of the GNU General Public License as published by the
5402
308d34e9f07d Changed bulk of GPLv2 or later files identified by script
Mats Lidell <matsl@xemacs.org>
parents: 5127
diff changeset
11 Free Software Foundation, either version 3 of the License, or (at your
308d34e9f07d Changed bulk of GPLv2 or later files identified by script
Mats Lidell <matsl@xemacs.org>
parents: 5127
diff changeset
12 option) any later version.
428
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
13
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
14 XEmacs is distributed in the hope that it will be useful, but WITHOUT
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
15 ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
16 FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
17 for more details.
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
18
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
19 You should have received a copy of the GNU General Public License
5402
308d34e9f07d Changed bulk of GPLv2 or later files identified by script
Mats Lidell <matsl@xemacs.org>
parents: 5127
diff changeset
20 along with XEmacs. If not, see <http://www.gnu.org/licenses/>. */
428
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
21
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
22 /* Synched up with: Mule 2.3. Not in FSF. */
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
23
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
24 /* Authorship:
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
25
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
26 Current primary author: Ben Wing <ben@xemacs.org>
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
27
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
28 Written by Ben Wing <ben@xemacs.org> for XEmacs, 1995, loosely based
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
29 on code written 91.10.09 by K.Handa <handa@etl.go.jp>.
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
30 Rewritten again 2000-2001 by Ben Wing to support properly
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
31 abstracted coding systems.
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
32 September 2001: Finished last part of abstraction, the detection
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
33 mechanism.
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
34 */
428
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
35
440
8de8e3f6228a Import from CVS: tag r21-2-28
cvs
parents: 438
diff changeset
36 #ifndef INCLUDED_file_coding_h_
8de8e3f6228a Import from CVS: tag r21-2-28
cvs
parents: 438
diff changeset
37 #define INCLUDED_file_coding_h_
428
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
38
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
39 /* Capsule description of the different structures, what their purpose is,
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
40 how they fit together, and where various bits of data are stored.
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
41
2297
13a418960a88 [xemacs-hg @ 2004-09-22 02:05:42 by stephent]
stephent
parents: 2132
diff changeset
42 A "coding system" is an algorithm for converting stream data in one format
13a418960a88 [xemacs-hg @ 2004-09-22 02:05:42 by stephent]
stephent
parents: 2132
diff changeset
43 into stream data in another format. Currently most of the coding systems
13a418960a88 [xemacs-hg @ 2004-09-22 02:05:42 by stephent]
stephent
parents: 2132
diff changeset
44 we have created concern internationalized text, and convert between the
13a418960a88 [xemacs-hg @ 2004-09-22 02:05:42 by stephent]
stephent
parents: 2132
diff changeset
45 XEmacs internal format for multilingual text, and various external
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
46 representations of such text. However, any such conversion is possible,
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
47 for example, compressing or uncompressing text using the gzip algorithm.
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
48 All coding systems provide both encode and decode routines, so that the
2297
13a418960a88 [xemacs-hg @ 2004-09-22 02:05:42 by stephent]
stephent
parents: 2132
diff changeset
49 conversion can go both ways. Unfortunately encoding and decoding may not
13a418960a88 [xemacs-hg @ 2004-09-22 02:05:42 by stephent]
stephent
parents: 2132
diff changeset
50 be exact inverses, even for a specific instance of a coding system. Care
13a418960a88 [xemacs-hg @ 2004-09-22 02:05:42 by stephent]
stephent
parents: 2132
diff changeset
51 must be taken when this is not the case.
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
52
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
53 The way we handle this is by dividing the various potential coding
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
54 systems into types, analogous to classes in C++. Each coding system
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
55 type encompasses a series of related coding systems that it can
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
56 implement, and it has properties which control how exactly the encoding
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
57 works. A particular set of values for each of the properties makes up a
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
58 "coding system", and specifies one particular encoding. A `struct
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
59 Lisp_Coding_System' object encapsulates those settings -- its type, the
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
60 values chosen for all properties of that type, a name for the coding
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
61 system, some documentation.
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
62
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
63 In addition, there are of course methods associated with a coding system
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
64 type, implementing the encoding, decoding, etc. These are stored in a
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
65 `struct coding_system_methods' object, one per coding-system type, which
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
66 contains mostly function pointers. This is retrievable from the
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
67 coding-system object (i.e. the struct Lisp_Coding_System), which has a
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
68 pointer to it.
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
69
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
70 In order to actually use a coding system to do an encoding or decoding
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
71 operation, you need to use a coding Lstream.
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
72
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
73 Now let's look more at attached data. All coding systems have certain
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
74 common data fields -- name, type, documentation, etc. -- as well as a
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
75 bunch more that are defined by the coding system type. To handle this
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
76 cleanly, each coding system type defines a structure that holds just the
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
77 fields of data particular to it, and calls it e.g. `struct
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
78 iso2022_coding_system' for coding system type `iso2022'. When the
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
79 memory block holding the coding system object is created, it is sized
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
80 such that it can hold both the struct Lisp_Coding_System and the struct
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
81 iso2022_coding_system (or whatever) directly following it. (This is a
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
82 common trick; another possibility is to have a void * pointer in the
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
83 struct Lisp_Coding_System, which points to another memory block holding
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
84 the struct iso2022_coding_system.) A macro is provided
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
85 (CODING_SYSTEM_TYPE_DATA) to retrieve a pointer of the right type to the
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
86 type-specific data contained within the overall `struct
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
87 Lisp_Coding_System' block.
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
88
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
89 Lstreams, similarly, are objects of type `struct lstream' holding data
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
90 about the stream operation (how much data has been read or written, any
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
91 buffered data, any error conditions, etc.), and like coding systems have
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
92 different types. They have a structure called `Lstream_implementation',
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
93 one per lstream type, exactly analogous to `struct
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
94 coding_system_methods'. In addition, they have type-specific data
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
95 (specifying, e.g., the file number, FILE *, memory location, other
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
96 lstream, etc. to read the data from or write it to, and for conversion
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
97 processes, the current state of the process -- are we decoding ASCII or
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
98 Kanji characters? are we in the middle of a processing an escape
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
99 sequence? etc.). This type-specific data is stored in a structure
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
100 named `struct coding_stream'. Just like for coding systems, the
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
101 type-independent data in the `struct lstream' and the type-dependent
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
102 data in the `struct coding_stream' are stored together in the same
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
103 memory block.
428
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
104
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
105 Now things get a bit tricky. The `struct coding_stream' is
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
106 type-specific from the point of view of an lstream, but not from the
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
107 point of view of a coding system. It contains only general data about
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
108 the conversion process, e.g. the name of the coding system used for
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
109 conversion, the lstream that we take data from or write it to (depending
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
110 on whether this was created as a read stream or a write stream), a
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
111 buffer to hold extra data we retrieved but can't send on yet, some
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
112 flags, etc. It also needs some data specific to the particular coding
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
113 system and thus to the particular operation going on. This data is held
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
114 in a structure named (e.g.) `struct iso2022_coding_stream', and it's
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
115 held in a separate memory block and pointed to by the generic `struct
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
116 coding_stream'. It's not glommed into a single memory block both
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
117 because that would require making changes to the generic lstream code
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
118 and more importantly because the coding system used in a particular
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
119 coding lstream can be changed at any point during the lifetime of the
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
120 lstream, and possibly multiple times. (For example, it can be set using
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
121 the Lisp primitives `set-process-input-coding-system' and
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
122 `set-console-tty-input-coding-system', as well as getting set when a
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
123 conversion operation was started with coding system `undecided' and the
2297
13a418960a88 [xemacs-hg @ 2004-09-22 02:05:42 by stephent]
stephent
parents: 2132
diff changeset
124 correct coding system was then detected.) #### This suggests implementing
13a418960a88 [xemacs-hg @ 2004-09-22 02:05:42 by stephent]
stephent
parents: 2132
diff changeset
125 compound text extended segments by saving the state of the ctext stream,
13a418960a88 [xemacs-hg @ 2004-09-22 02:05:42 by stephent]
stephent
parents: 2132
diff changeset
126 and installing an appropriate for the duration of the segment.
428
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
127
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
128 IMPORTANT NOTE: There are at least two ancillary data structures
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
129 associated with a coding system type. (There may also be detection data;
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
130 see elsewhere.) It's important, when writing a coding system type, to
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
131 keep straight which type of data goes where. In particular, `struct
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
132 foo_coding_system' is attached to the coding system object itself. This
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
133 is a permanent object and there's only one per coding system. It's
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
134 created once, usually at init time, and never destroyed. So, `struct
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
135 foo_coding_system' should in general not contain dynamic data! (Just
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
136 data describing the properties of the coding system.) In particular,
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
137 *NO* data about any conversion in progress. There may be many
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
138 conversions going on simultaneously using a particular coding system,
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
139 and by storing conversion data in the coding system, these conversions
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
140 will overwrite each other's data.
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
141
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
142 Instead, use the lstream object, whose purpose is to encapsulate a
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
143 particular conversion and all associated data. From the lstream object,
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
144 you can get the struct coding_stream using something like
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
145
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
146 struct coding_stream *str = LSTREAM_TYPE_DATA (lstr, coding);
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
147
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
148 But usually this structure is already passed to you as one of the
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
149 parameters of the method being invoked.
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
150
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
151 From the struct coding_stream, you can retrieve the
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
152 coding-system-type-specific data using something like
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
153
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
154 struct foo_coding_stream *data = CODING_STREAM_TYPE_DATA (str, foo);
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
155
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
156 Then, use this structure to hold all data relevant to the particular
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
157 conversion being done.
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
158
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
159 Initialize this structure whenever init_coding_stream_method is called
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
160 (this may happen more than once), and finalize it (free resources, etc.)
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
161 when finalize_coding_stream_method is called.
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
162 */
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
163
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
164 struct coding_stream;
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
165 struct detection_state;
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
166
1204
e22b0213b713 [xemacs-hg @ 2003-01-12 11:07:58 by michaels]
michaels
parents: 985
diff changeset
167 extern const struct sized_memory_description coding_system_methods_description;
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
168
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
169 struct coding_system_methods;
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
170
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
171 enum source_sink_type
428
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
172 {
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
173 DECODES_CHARACTER_TO_BYTE,
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
174 DECODES_BYTE_TO_BYTE,
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
175 DECODES_BYTE_TO_CHARACTER,
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
176 DECODES_CHARACTER_TO_CHARACTER
428
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
177 };
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
178
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
179 enum eol_type
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
180 {
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
181 EOL_LF,
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
182 EOL_CRLF,
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
183 EOL_CR,
1429
969b7290edca [xemacs-hg @ 2003-04-24 05:33:43 by youngs]
youngs
parents: 1315
diff changeset
184 EOL_AUTODETECT
428
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
185 };
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
186
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
187 struct Lisp_Coding_System
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
188 {
5127
a9c41067dd88 more cleanups, terminology clarification, lots of doc work
Ben Wing <ben@xemacs.org>
parents: 5124
diff changeset
189 NORMAL_LISP_OBJECT_HEADER header;
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
190 struct coding_system_methods *methods;
428
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
191
1204
e22b0213b713 [xemacs-hg @ 2003-01-12 11:07:58 by michaels]
michaels
parents: 985
diff changeset
192 #define CODING_SYSTEM_SLOT_DECLARATION
e22b0213b713 [xemacs-hg @ 2003-01-12 11:07:58 by michaels]
michaels
parents: 985
diff changeset
193 #define MARKED_SLOT(x) Lisp_Object x;
e22b0213b713 [xemacs-hg @ 2003-01-12 11:07:58 by michaels]
michaels
parents: 985
diff changeset
194 #include "coding-system-slots.h"
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
195
1204
e22b0213b713 [xemacs-hg @ 2003-01-12 11:07:58 by michaels]
michaels
parents: 985
diff changeset
196 /* Eol type requested by user. See comment about EOL junk in
e22b0213b713 [xemacs-hg @ 2003-01-12 11:07:58 by michaels]
michaels
parents: 985
diff changeset
197 coding-system-slots.h. */
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
198 enum eol_type eol_type;
428
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
199
2132
34ca43a57692 [xemacs-hg @ 2004-06-16 12:01:17 by malcolmp]
malcolmp
parents: 1429
diff changeset
200 /* If true, this is an internal coding system, which will not show up in
34ca43a57692 [xemacs-hg @ 2004-06-16 12:01:17 by malcolmp]
malcolmp
parents: 1429
diff changeset
201 coding-system-list unless a special parameter is given to it. */
34ca43a57692 [xemacs-hg @ 2004-06-16 12:01:17 by malcolmp]
malcolmp
parents: 1429
diff changeset
202 int internal_p;
34ca43a57692 [xemacs-hg @ 2004-06-16 12:01:17 by malcolmp]
malcolmp
parents: 1429
diff changeset
203
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
204 /* type-specific extra data attached to a coding_system */
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
205 char data[1];
428
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
206 };
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
207 typedef struct Lisp_Coding_System Lisp_Coding_System;
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
208
5118
e0db3c197671 merge up to latest default branch, doesn't compile yet
Ben Wing <ben@xemacs.org>
parents: 4690
diff changeset
209 DECLARE_LISP_OBJECT (coding_system, Lisp_Coding_System);
440
8de8e3f6228a Import from CVS: tag r21-2-28
cvs
parents: 438
diff changeset
210 #define XCODING_SYSTEM(x) XRECORD (x, coding_system, Lisp_Coding_System)
617
af57a77cbc92 [xemacs-hg @ 2001-06-18 07:09:50 by ben]
ben
parents: 528
diff changeset
211 #define wrap_coding_system(p) wrap_record (p, coding_system)
428
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
212 #define CODING_SYSTEMP(x) RECORDP (x, coding_system)
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
213 #define CHECK_CODING_SYSTEM(x) CHECK_RECORD (x, coding_system)
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
214 #define CONCHECK_CODING_SYSTEM(x) CONCHECK_RECORD (x, coding_system)
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
215
1204
e22b0213b713 [xemacs-hg @ 2003-01-12 11:07:58 by michaels]
michaels
parents: 985
diff changeset
216 enum coding_system_variant
e22b0213b713 [xemacs-hg @ 2003-01-12 11:07:58 by michaels]
michaels
parents: 985
diff changeset
217 {
e22b0213b713 [xemacs-hg @ 2003-01-12 11:07:58 by michaels]
michaels
parents: 985
diff changeset
218 no_conversion_coding_system,
e22b0213b713 [xemacs-hg @ 2003-01-12 11:07:58 by michaels]
michaels
parents: 985
diff changeset
219 convert_eol_coding_system,
e22b0213b713 [xemacs-hg @ 2003-01-12 11:07:58 by michaels]
michaels
parents: 985
diff changeset
220 undecided_coding_system,
e22b0213b713 [xemacs-hg @ 2003-01-12 11:07:58 by michaels]
michaels
parents: 985
diff changeset
221 chain_coding_system,
e22b0213b713 [xemacs-hg @ 2003-01-12 11:07:58 by michaels]
michaels
parents: 985
diff changeset
222 text_file_wrapper_coding_system,
e22b0213b713 [xemacs-hg @ 2003-01-12 11:07:58 by michaels]
michaels
parents: 985
diff changeset
223 internal_coding_system,
e22b0213b713 [xemacs-hg @ 2003-01-12 11:07:58 by michaels]
michaels
parents: 985
diff changeset
224 gzip_coding_system,
e22b0213b713 [xemacs-hg @ 2003-01-12 11:07:58 by michaels]
michaels
parents: 985
diff changeset
225 mswindows_multibyte_to_unicode_coding_system,
e22b0213b713 [xemacs-hg @ 2003-01-12 11:07:58 by michaels]
michaels
parents: 985
diff changeset
226 mswindows_multibyte_coding_system,
e22b0213b713 [xemacs-hg @ 2003-01-12 11:07:58 by michaels]
michaels
parents: 985
diff changeset
227 iso2022_coding_system,
e22b0213b713 [xemacs-hg @ 2003-01-12 11:07:58 by michaels]
michaels
parents: 985
diff changeset
228 ccl_coding_system,
e22b0213b713 [xemacs-hg @ 2003-01-12 11:07:58 by michaels]
michaels
parents: 985
diff changeset
229 shift_jis_coding_system,
e22b0213b713 [xemacs-hg @ 2003-01-12 11:07:58 by michaels]
michaels
parents: 985
diff changeset
230 big5_coding_system,
4690
257b468bf2ca Move the #'query-coding-region implementation to C.
Aidan Kehoe <kehoea@parhasard.net>
parents: 4569
diff changeset
231 unicode_coding_system,
257b468bf2ca Move the #'query-coding-region implementation to C.
Aidan Kehoe <kehoea@parhasard.net>
parents: 4569
diff changeset
232 fixed_width_coding_system
1204
e22b0213b713 [xemacs-hg @ 2003-01-12 11:07:58 by michaels]
michaels
parents: 985
diff changeset
233 };
e22b0213b713 [xemacs-hg @ 2003-01-12 11:07:58 by michaels]
michaels
parents: 985
diff changeset
234
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
235 struct coding_system_methods
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
236 {
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
237 Lisp_Object type;
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
238 Lisp_Object predicate_symbol;
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
239
1204
e22b0213b713 [xemacs-hg @ 2003-01-12 11:07:58 by michaels]
michaels
parents: 985
diff changeset
240 /* Type expressed as an enum, needed for KKCC marking of the
e22b0213b713 [xemacs-hg @ 2003-01-12 11:07:58 by michaels]
michaels
parents: 985
diff changeset
241 type-specific lstream data; copied into the struct coding_stream. */
e22b0213b713 [xemacs-hg @ 2003-01-12 11:07:58 by michaels]
michaels
parents: 985
diff changeset
242
e22b0213b713 [xemacs-hg @ 2003-01-12 11:07:58 by michaels]
michaels
parents: 985
diff changeset
243 enum coding_system_variant enumtype;
e22b0213b713 [xemacs-hg @ 2003-01-12 11:07:58 by michaels]
michaels
parents: 985
diff changeset
244
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
245 /* Implementation specific methods: */
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
246
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
247 /* Init method: Initialize coding-system data. Optional. */
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
248 void (*init_method) (Lisp_Object coding_system);
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
249
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
250 /* Mark method: Mark any Lisp objects in the type-specific data
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
251 attached to the coding-system object. Optional. */
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
252 void (*mark_method) (Lisp_Object coding_system);
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
253
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
254 /* Print method: Print the type-specific properties of this coding
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
255 system, as part of `print'-ing the object. If this method is defined
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
256 and prints anything, it should print a space as the first thing it
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
257 does. Optional. */
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
258 void (*print_method) (Lisp_Object cs, Lisp_Object printcharfun,
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
259 int escapeflag);
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
260
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
261 /* Canonicalize method: Convert this coding system to another one; called
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
262 once, at creation time, after all properties have been parsed. The
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
263 returned value should be a coding system created with
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
264 make_internal_coding_system() (passing the existing coding system as the
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
265 first argument), and will become the coding system returned by
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
266 `make-coding-system'. Optional.
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
267
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
268 NOTE: There are *three* different uses of "canonical" or "canonicalize"
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
269 w.r.t. coding systems, and it's important to keep them straight.
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
270
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
271 1. The canonicalize method. Used to specify a different coding
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
272 system, used when doing conversions, in place of the actual coding
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
273 system itself. Stored in the CANONICAL field of a coding system.
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
274
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
275 2. The canonicalize-after-coding method. Used to return the encoding
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
276 that was "actually" used to decode some text, such that this
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
277 particular encoding can be used to encode the text again with the
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
278 expectation that the result will be the same as the original encoding.
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
279 Particularly important with auto-detecting coding systems.
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
280
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
281 3. From the perspective of aliases, a "canonical" coding system is one
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
282 that's not an alias to some other coding system, and "canonicalization"
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
283 is the process of traversing the alias pointers to find the canonical
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
284 coding system that's equivalent to the alias.
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
285 */
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
286 Lisp_Object (*canonicalize_method) (Lisp_Object coding_system);
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
287
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
288 /* Canonicalize after coding method: Convert this coding system to
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
289 another one, after coding (usually decoding) has finished. This is
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
290 meant to be used by auto-detecting coding systems, which should return
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
291 the actually detected coding system. Optional. */
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
292 Lisp_Object (*canonicalize_after_coding_method)
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
293 (struct coding_stream *str);
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
294
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
295 /* Convert method: Decode or encode the data in SRC of size N, writing
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
296 the results into the Dynarr DST. If the conversion_end_type method
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
297 indicates that the source is characters (as opposed to bytes), you are
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
298 guaranteed to get only whole characters in the data in SRC/N. STR, a
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
299 struct coding_stream, stores all necessary state and other info about
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
300 the conversion. Coding-specific state (struct TYPE_coding_stream) can
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
301 be retrieved from STR using CODING_STREAM_TYPE_DATA(). Return value
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
302 indicates the number of bytes of the *INPUT* that were converted (not
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
303 the number of bytes written to the Dynarr!). This can be less than
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
304 the total amount of input passed in; if so, the remainder is
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
305 considered "rejected" and will appear again at the beginning of the
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
306 data passed in the next time the convert method is called. When EOF
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
307 is returned on the other end and there's no more data, the convert
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
308 method will be called one last time, STR->eof set and the passed-in
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
309 data will consist only of any rejected data from the previous
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
310 call. (At this point, file handles and similar resources can be
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
311 closed, but do NOT arbitrarily free data structures in the
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
312 type-specific data, because there are operations that can be done on
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
313 closed streams to query the results of the processing -- specifically,
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
314 for coding streams, there's the canonicalize_after_coding() method.)
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
315 Required. */
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
316 Bytecount (*convert_method) (struct coding_stream *str,
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
317 const unsigned char *src,
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
318 unsigned_char_dynarr *dst, Bytecount n);
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
319
4690
257b468bf2ca Move the #'query-coding-region implementation to C.
Aidan Kehoe <kehoea@parhasard.net>
parents: 4569
diff changeset
320 /* Query method: Check whether the buffer text between point and END
257b468bf2ca Move the #'query-coding-region implementation to C.
Aidan Kehoe <kehoea@parhasard.net>
parents: 4569
diff changeset
321 can be encoded by this coding system. Returns
257b468bf2ca Move the #'query-coding-region implementation to C.
Aidan Kehoe <kehoea@parhasard.net>
parents: 4569
diff changeset
322 either nil (meaning the text can be encoded by the coding system) or a
257b468bf2ca Move the #'query-coding-region implementation to C.
Aidan Kehoe <kehoea@parhasard.net>
parents: 4569
diff changeset
323 range table object describing the stretches that the coding system
257b468bf2ca Move the #'query-coding-region implementation to C.
Aidan Kehoe <kehoea@parhasard.net>
parents: 4569
diff changeset
324 cannot encode.
257b468bf2ca Move the #'query-coding-region implementation to C.
Aidan Kehoe <kehoea@parhasard.net>
parents: 4569
diff changeset
325
257b468bf2ca Move the #'query-coding-region implementation to C.
Aidan Kehoe <kehoea@parhasard.net>
parents: 4569
diff changeset
326 Possible values for flags are below, search for
257b468bf2ca Move the #'query-coding-region implementation to C.
Aidan Kehoe <kehoea@parhasard.net>
parents: 4569
diff changeset
327 QUERY_METHOD_IGNORE_INVALID_SEQUENCES.
257b468bf2ca Move the #'query-coding-region implementation to C.
Aidan Kehoe <kehoea@parhasard.net>
parents: 4569
diff changeset
328
257b468bf2ca Move the #'query-coding-region implementation to C.
Aidan Kehoe <kehoea@parhasard.net>
parents: 4569
diff changeset
329 Coding systems are expected to be able to behave sensibly with all
257b468bf2ca Move the #'query-coding-region implementation to C.
Aidan Kehoe <kehoea@parhasard.net>
parents: 4569
diff changeset
330 possible octets on decoding, which is why this method is only available
257b468bf2ca Move the #'query-coding-region implementation to C.
Aidan Kehoe <kehoea@parhasard.net>
parents: 4569
diff changeset
331 for encoding. */
257b468bf2ca Move the #'query-coding-region implementation to C.
Aidan Kehoe <kehoea@parhasard.net>
parents: 4569
diff changeset
332 Lisp_Object (*query_method) (Lisp_Object coding_system, struct buffer *buf,
257b468bf2ca Move the #'query-coding-region implementation to C.
Aidan Kehoe <kehoea@parhasard.net>
parents: 4569
diff changeset
333 Charbpos end, int flags);
257b468bf2ca Move the #'query-coding-region implementation to C.
Aidan Kehoe <kehoea@parhasard.net>
parents: 4569
diff changeset
334
257b468bf2ca Move the #'query-coding-region implementation to C.
Aidan Kehoe <kehoea@parhasard.net>
parents: 4569
diff changeset
335 /* Same as the previous method, but this works in the context of
257b468bf2ca Move the #'query-coding-region implementation to C.
Aidan Kehoe <kehoea@parhasard.net>
parents: 4569
diff changeset
336 lstreams. (Where the data do need to be copied, unfortunately.) The
257b468bf2ca Move the #'query-coding-region implementation to C.
Aidan Kehoe <kehoea@parhasard.net>
parents: 4569
diff changeset
337 intention is to implement the query method for the mswindows-multibyte
257b468bf2ca Move the #'query-coding-region implementation to C.
Aidan Kehoe <kehoea@parhasard.net>
parents: 4569
diff changeset
338 coding systems in terms of a query_lstream method. */
257b468bf2ca Move the #'query-coding-region implementation to C.
Aidan Kehoe <kehoea@parhasard.net>
parents: 4569
diff changeset
339 Lisp_Object (*query_lstream_method) (struct coding_stream *str,
257b468bf2ca Move the #'query-coding-region implementation to C.
Aidan Kehoe <kehoea@parhasard.net>
parents: 4569
diff changeset
340 const Ibyte *start, Bytecount n);
257b468bf2ca Move the #'query-coding-region implementation to C.
Aidan Kehoe <kehoea@parhasard.net>
parents: 4569
diff changeset
341
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
342 /* Coding mark method: Mark any Lisp objects in the type-specific data
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
343 attached to `struct coding_stream'. Optional. */
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
344 void (*mark_coding_stream_method) (struct coding_stream *str);
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
345
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
346 /* Init coding stream method: Initialize the type-specific data attached
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
347 to the coding stream (i.e. in struct TYPE_coding_stream), when the
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
348 coding stream is opened. The type-specific data will be zeroed out.
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
349 Optional. */
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
350 void (*init_coding_stream_method) (struct coding_stream *str);
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
351
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
352 /* Rewind coding stream method: Reset any necessary type-specific data as
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
353 a result of the stream being rewound. Optional. */
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
354 void (*rewind_coding_stream_method) (struct coding_stream *str);
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
355
5776
65d65b52d608 Pass character count from coding systems to buffer insertion code.
Aidan Kehoe <kehoea@parhasard.net>
parents: 5402
diff changeset
356 /* Return the number of characters *decoded*. Optional. */
65d65b52d608 Pass character count from coding systems to buffer insertion code.
Aidan Kehoe <kehoea@parhasard.net>
parents: 5402
diff changeset
357 Charcount (*character_tell_method) (struct coding_stream *str);
65d65b52d608 Pass character count from coding systems to buffer insertion code.
Aidan Kehoe <kehoea@parhasard.net>
parents: 5402
diff changeset
358
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
359 /* Finalize coding stream method: Clean up the type-specific data
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
360 attached to the coding stream (i.e. in struct TYPE_coding_stream).
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
361 Happens when the Lstream is deleted using Lstream_delete() or is
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
362 garbage-collected. Most streams are deleted after they've been used,
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
363 so it's less likely (but still possible) that allocated data will
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
364 stick around until GC time. (File handles can also be closed when EOF
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
365 is signalled; but some data must stick around after this point, for
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
366 the benefit of canonicalize_after_coding. See the convert method.)
5124
623d57b7fbe8 separate regular and disksave finalization, print method fixes.
Ben Wing <ben@xemacs.org>
parents: 5120
diff changeset
367 Called only once. Optional. */
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
368 void (*finalize_coding_stream_method) (struct coding_stream *str);
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
369
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
370 /* Finalize method: Clean up type-specific data (e.g. free allocated
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
371 data) attached to the coding system (i.e. in struct
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
372 TYPE_coding_system), when the coding system is about to be garbage
5124
623d57b7fbe8 separate regular and disksave finalization, print method fixes.
Ben Wing <ben@xemacs.org>
parents: 5120
diff changeset
373 collected. (Currently not called.) Called only once. Optional. */
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
374 void (*finalize_method) (Lisp_Object codesys);
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
375
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
376 /* Conversion end type method: Does this coding system encode bytes ->
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
377 characters, characters -> characters, bytes -> bytes, or
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
378 characters -> bytes?. Default is characters -> bytes. Optional. */
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
379 enum source_sink_type (*conversion_end_type_method) (Lisp_Object codesys);
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
380
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
381 /* Putprop method: Set the value of a type-specific property. If
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
382 the property name is unrecognized, return 0. If the value is disallowed
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
383 or erroneous, signal an error. Currently called only at creation time.
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
384 Optional. */
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
385 int (*putprop_method) (Lisp_Object codesys,
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
386 Lisp_Object key,
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
387 Lisp_Object value);
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
388
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
389 /* Getprop method: Return the value of a type-specific property. If
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
390 the property name is unrecognized, return Qunbound. Optional.
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
391 */
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
392 Lisp_Object (*getprop_method) (Lisp_Object coding_system,
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
393 Lisp_Object prop);
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
394
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
395 /* These next three are set as part of the call to
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
396 INITIALIZE_CODING_SYSTEM_TYPE_WITH_DATA. */
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
397
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
398 /* Description of the extra data (struct foo_coding_system) attached to a
1204
e22b0213b713 [xemacs-hg @ 2003-01-12 11:07:58 by michaels]
michaels
parents: 985
diff changeset
399 coding system, for pdump purposes. */
e22b0213b713 [xemacs-hg @ 2003-01-12 11:07:58 by michaels]
michaels
parents: 985
diff changeset
400 const struct sized_memory_description *extra_description;
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
401 /* size of struct foo_coding_system -- extra data associated with
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
402 the coding system */
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
403 int extra_data_size;
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
404 /* size of struct foo_coding_stream -- extra data associated with the
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
405 struct coding_stream, needed for each active coding process
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
406 using this coding system. note that we can have more than one
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
407 process active at once (simply by creating more than one coding
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
408 lstream using this coding system), so we can't store this data in
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
409 the coding system object. */
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
410 int coding_data_size;
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
411 };
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
412
4690
257b468bf2ca Move the #'query-coding-region implementation to C.
Aidan Kehoe <kehoea@parhasard.net>
parents: 4569
diff changeset
413 /* Values for flags, as passed to query_method. */
257b468bf2ca Move the #'query-coding-region implementation to C.
Aidan Kehoe <kehoea@parhasard.net>
parents: 4569
diff changeset
414
257b468bf2ca Move the #'query-coding-region implementation to C.
Aidan Kehoe <kehoea@parhasard.net>
parents: 4569
diff changeset
415 #define QUERY_METHOD_IGNORE_INVALID_SEQUENCES 0x0001
257b468bf2ca Move the #'query-coding-region implementation to C.
Aidan Kehoe <kehoea@parhasard.net>
parents: 4569
diff changeset
416 #define QUERY_METHOD_ERRORP 0x0002
257b468bf2ca Move the #'query-coding-region implementation to C.
Aidan Kehoe <kehoea@parhasard.net>
parents: 4569
diff changeset
417 #define QUERY_METHOD_HIGHLIGHT 0x0004
257b468bf2ca Move the #'query-coding-region implementation to C.
Aidan Kehoe <kehoea@parhasard.net>
parents: 4569
diff changeset
418
257b468bf2ca Move the #'query-coding-region implementation to C.
Aidan Kehoe <kehoea@parhasard.net>
parents: 4569
diff changeset
419 enum query_coding_failure_reasons
257b468bf2ca Move the #'query-coding-region implementation to C.
Aidan Kehoe <kehoea@parhasard.net>
parents: 4569
diff changeset
420 {
257b468bf2ca Move the #'query-coding-region implementation to C.
Aidan Kehoe <kehoea@parhasard.net>
parents: 4569
diff changeset
421 query_coding_succeeded = 0,
257b468bf2ca Move the #'query-coding-region implementation to C.
Aidan Kehoe <kehoea@parhasard.net>
parents: 4569
diff changeset
422 query_coding_unencodable = 1,
257b468bf2ca Move the #'query-coding-region implementation to C.
Aidan Kehoe <kehoea@parhasard.net>
parents: 4569
diff changeset
423 query_coding_invalid_sequence = 2
257b468bf2ca Move the #'query-coding-region implementation to C.
Aidan Kehoe <kehoea@parhasard.net>
parents: 4569
diff changeset
424 };
257b468bf2ca Move the #'query-coding-region implementation to C.
Aidan Kehoe <kehoea@parhasard.net>
parents: 4569
diff changeset
425
257b468bf2ca Move the #'query-coding-region implementation to C.
Aidan Kehoe <kehoea@parhasard.net>
parents: 4569
diff changeset
426 extern Lisp_Object Qquery_coding_warning_face;
257b468bf2ca Move the #'query-coding-region implementation to C.
Aidan Kehoe <kehoea@parhasard.net>
parents: 4569
diff changeset
427
257b468bf2ca Move the #'query-coding-region implementation to C.
Aidan Kehoe <kehoea@parhasard.net>
parents: 4569
diff changeset
428 Lisp_Object default_query_method (Lisp_Object, struct buffer *, Charbpos,
257b468bf2ca Move the #'query-coding-region implementation to C.
Aidan Kehoe <kehoea@parhasard.net>
parents: 4569
diff changeset
429 int);
257b468bf2ca Move the #'query-coding-region implementation to C.
Aidan Kehoe <kehoea@parhasard.net>
parents: 4569
diff changeset
430
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
431 /***** Calling a coding-system method *****/
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
432
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
433 #define RAW_CODESYSMETH(cs, m) ((cs)->methods->m##_method)
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
434 #define HAS_CODESYSMETH_P(cs, m) (!!RAW_CODESYSMETH (cs, m))
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
435 #define CODESYSMETH(cs, m, args) (((cs)->methods->m##_method) args)
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
436
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
437 /* Call a void-returning coding-system method, if it exists. */
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
438 #define MAYBE_CODESYSMETH(cs, m, args) do { \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
439 Lisp_Coding_System *maybe_codesysmeth_cs = (cs); \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
440 if (HAS_CODESYSMETH_P (maybe_codesysmeth_cs, m)) \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
441 CODESYSMETH (maybe_codesysmeth_cs, m, args); \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
442 } while (0)
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
443
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
444 /* Call a coding-system method, if it exists, or return GIVEN.
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
445 NOTE: Multiply-evaluates CS. */
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
446 #define CODESYSMETH_OR_GIVEN(cs, m, args, given) \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
447 (HAS_CODESYSMETH_P (cs, m) ? \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
448 CODESYSMETH (cs, m, args) : (given))
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
449
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
450 #define XCODESYSMETH(cs, m, args) \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
451 CODESYSMETH (XCODING_SYSTEM (cs), m, args)
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
452 #define MAYBE_XCODESYSMETH(cs, m, args) \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
453 MAYBE_CODESYSMETH (XCODING_SYSTEM (cs), m, args)
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
454 #define XCODESYSMETH_OR_GIVEN(cs, m, args, given) \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
455 CODESYSMETH_OR_GIVEN (XCODING_SYSTEM (cs), m, args, given)
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
456
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
457 /***** Defining new coding-system types *****/
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
458
1204
e22b0213b713 [xemacs-hg @ 2003-01-12 11:07:58 by michaels]
michaels
parents: 985
diff changeset
459 extern const struct sized_memory_description coding_system_empty_extra_description;
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
460
800
a5954632b187 [xemacs-hg @ 2002-03-31 08:27:14 by ben]
ben
parents: 793
diff changeset
461 #ifdef ERROR_CHECK_TYPES
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
462 #define DECLARE_CODING_SYSTEM_TYPE(type) \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
463 \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
464 extern struct coding_system_methods * type##_coding_system_methods; \
826
6728e641994e [xemacs-hg @ 2002-05-05 11:30:15 by ben]
ben
parents: 814
diff changeset
465 DECLARE_INLINE_HEADER ( \
6728e641994e [xemacs-hg @ 2002-05-05 11:30:15 by ben]
ben
parents: 814
diff changeset
466 struct type##_coding_system * \
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
467 error_check_##type##_coding_system_data (Lisp_Coding_System *cs) \
826
6728e641994e [xemacs-hg @ 2002-05-05 11:30:15 by ben]
ben
parents: 814
diff changeset
468 ) \
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
469 { \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
470 assert (CODING_SYSTEM_TYPE_P (cs, type)); \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
471 /* Catch accidental use of INITIALIZE_CODING_SYSTEM_TYPE in place \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
472 of INITIALIZE_CODING_SYSTEM_TYPE_WITH_DATA. */ \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
473 assert (cs->methods->extra_data_size > 0); \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
474 return (struct type##_coding_system *) cs->data; \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
475 } \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
476 \
826
6728e641994e [xemacs-hg @ 2002-05-05 11:30:15 by ben]
ben
parents: 814
diff changeset
477 DECLARE_INLINE_HEADER ( \
6728e641994e [xemacs-hg @ 2002-05-05 11:30:15 by ben]
ben
parents: 814
diff changeset
478 struct type##_coding_stream * \
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
479 error_check_##type##_coding_stream_data (struct coding_stream *s) \
826
6728e641994e [xemacs-hg @ 2002-05-05 11:30:15 by ben]
ben
parents: 814
diff changeset
480 ) \
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
481 { \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
482 assert (XCODING_SYSTEM_TYPE_P (s->codesys, type)); \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
483 return (struct type##_coding_stream *) s->data; \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
484 } \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
485 \
826
6728e641994e [xemacs-hg @ 2002-05-05 11:30:15 by ben]
ben
parents: 814
diff changeset
486 DECLARE_INLINE_HEADER ( \
6728e641994e [xemacs-hg @ 2002-05-05 11:30:15 by ben]
ben
parents: 814
diff changeset
487 Lisp_Coding_System * \
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
488 error_check_##type##_coding_system_type (Lisp_Object obj) \
826
6728e641994e [xemacs-hg @ 2002-05-05 11:30:15 by ben]
ben
parents: 814
diff changeset
489 ) \
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
490 { \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
491 Lisp_Coding_System *cs = XCODING_SYSTEM (obj); \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
492 assert (CODING_SYSTEM_TYPE_P (cs, type)); \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
493 return cs; \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
494 } \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
495 \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
496 DECLARE_NOTHING
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
497 #else
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
498 #define DECLARE_CODING_SYSTEM_TYPE(type) \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
499 extern struct coding_system_methods * type##_coding_system_methods
800
a5954632b187 [xemacs-hg @ 2002-03-31 08:27:14 by ben]
ben
parents: 793
diff changeset
500 #endif /* ERROR_CHECK_TYPES */
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
501
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
502 #define DEFINE_CODING_SYSTEM_TYPE(type) \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
503 struct coding_system_methods * type##_coding_system_methods
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
504
1204
e22b0213b713 [xemacs-hg @ 2003-01-12 11:07:58 by michaels]
michaels
parents: 985
diff changeset
505 #define DEFINE_CODING_SYSTEM_TYPE_WITH_DATA(type) \
e22b0213b713 [xemacs-hg @ 2003-01-12 11:07:58 by michaels]
michaels
parents: 985
diff changeset
506 struct coding_system_methods * type##_coding_system_methods; \
e22b0213b713 [xemacs-hg @ 2003-01-12 11:07:58 by michaels]
michaels
parents: 985
diff changeset
507 static const struct sized_memory_description \
e22b0213b713 [xemacs-hg @ 2003-01-12 11:07:58 by michaels]
michaels
parents: 985
diff changeset
508 type##_coding_system_description_0 = { \
e22b0213b713 [xemacs-hg @ 2003-01-12 11:07:58 by michaels]
michaels
parents: 985
diff changeset
509 sizeof (struct type##_coding_system), \
e22b0213b713 [xemacs-hg @ 2003-01-12 11:07:58 by michaels]
michaels
parents: 985
diff changeset
510 type##_coding_system_description \
e22b0213b713 [xemacs-hg @ 2003-01-12 11:07:58 by michaels]
michaels
parents: 985
diff changeset
511 }
e22b0213b713 [xemacs-hg @ 2003-01-12 11:07:58 by michaels]
michaels
parents: 985
diff changeset
512
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
513 #define INITIALIZE_CODING_SYSTEM_TYPE(ty, pred_sym) do { \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
514 ty##_coding_system_methods = \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
515 xnew_and_zero (struct coding_system_methods); \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
516 ty##_coding_system_methods->type = Q##ty; \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
517 ty##_coding_system_methods->extra_description = \
1204
e22b0213b713 [xemacs-hg @ 2003-01-12 11:07:58 by michaels]
michaels
parents: 985
diff changeset
518 &coding_system_empty_extra_description; \
e22b0213b713 [xemacs-hg @ 2003-01-12 11:07:58 by michaels]
michaels
parents: 985
diff changeset
519 ty##_coding_system_methods->enumtype = ty##_coding_system; \
4690
257b468bf2ca Move the #'query-coding-region implementation to C.
Aidan Kehoe <kehoea@parhasard.net>
parents: 4569
diff changeset
520 ty##_coding_system_methods->query_method = default_query_method; \
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
521 defsymbol_nodump (&ty##_coding_system_methods->predicate_symbol, \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
522 pred_sym); \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
523 add_entry_to_coding_system_type_list (ty##_coding_system_methods); \
2367
ecf1ebac70d8 [xemacs-hg @ 2004-11-04 23:05:23 by ben]
ben
parents: 2297
diff changeset
524 dump_add_root_block_ptr (&ty##_coding_system_methods, \
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
525 &coding_system_methods_description); \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
526 } while (0)
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
527
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
528 #define REINITIALIZE_CODING_SYSTEM_TYPE(type) do { \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
529 staticpro_nodump (&type##_coding_system_methods->predicate_symbol); \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
530 } while (0)
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
531
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
532 /* This assumes the existence of two structures:
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
533
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
534 struct foo_coding_system (attached to the coding system)
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
535 struct foo_coding_stream (per coding process, attached to the
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
536 struct coding_stream)
1204
e22b0213b713 [xemacs-hg @ 2003-01-12 11:07:58 by michaels]
michaels
parents: 985
diff changeset
537 const struct memory_description foo_coding_system_description[]
e22b0213b713 [xemacs-hg @ 2003-01-12 11:07:58 by michaels]
michaels
parents: 985
diff changeset
538 (data description of struct foo_coding_system)
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
539
1204
e22b0213b713 [xemacs-hg @ 2003-01-12 11:07:58 by michaels]
michaels
parents: 985
diff changeset
540 For an example of how to do the description, see
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
541 chain_coding_system_description.
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
542 */
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
543 #define INITIALIZE_CODING_SYSTEM_TYPE_WITH_DATA(type, pred_sym) \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
544 do { \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
545 INITIALIZE_CODING_SYSTEM_TYPE (type, pred_sym); \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
546 type##_coding_system_methods->extra_data_size = \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
547 sizeof (struct type##_coding_system); \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
548 type##_coding_system_methods->extra_description = \
1204
e22b0213b713 [xemacs-hg @ 2003-01-12 11:07:58 by michaels]
michaels
parents: 985
diff changeset
549 &type##_coding_system_description_0; \
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
550 type##_coding_system_methods->coding_data_size = \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
551 sizeof (struct type##_coding_stream); \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
552 } while (0)
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
553
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
554 /* Declare that coding-system-type TYPE has method METH; used in
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
555 initialization routines */
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
556 #define CODING_SYSTEM_HAS_METHOD(type, meth) \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
557 (type##_coding_system_methods->meth##_method = type##_##meth)
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
558
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
559 /***** Macros for accessing coding-system types *****/
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
560
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
561 #define CODING_SYSTEM_TYPE_P(cs, type) \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
562 ((cs)->methods == type##_coding_system_methods)
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
563 #define XCODING_SYSTEM_TYPE_P(cs, type) \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
564 CODING_SYSTEM_TYPE_P (XCODING_SYSTEM (cs), type)
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
565
800
a5954632b187 [xemacs-hg @ 2002-03-31 08:27:14 by ben]
ben
parents: 793
diff changeset
566 #ifdef ERROR_CHECK_TYPES
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
567 # define CODING_SYSTEM_TYPE_DATA(cs, type) \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
568 error_check_##type##_coding_system_data (cs)
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
569 #else
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
570 # define CODING_SYSTEM_TYPE_DATA(cs, type) \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
571 ((struct type##_coding_system *) \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
572 (cs)->data)
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
573 #endif
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
574
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
575 #define XCODING_SYSTEM_TYPE_DATA(cs, type) \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
576 CODING_SYSTEM_TYPE_DATA (XCODING_SYSTEM_OF_TYPE (cs, type), type)
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
577
800
a5954632b187 [xemacs-hg @ 2002-03-31 08:27:14 by ben]
ben
parents: 793
diff changeset
578 #ifdef ERROR_CHECK_TYPES
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
579 # define XCODING_SYSTEM_OF_TYPE(x, type) \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
580 error_check_##type##_coding_system_type (x)
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
581 # define XSETCODING_SYSTEM_OF_TYPE(x, p, type) do \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
582 { \
793
e38acbeb1cae [xemacs-hg @ 2002-03-29 04:46:17 by ben]
ben
parents: 771
diff changeset
583 x = wrap_coding_system (p); \
e38acbeb1cae [xemacs-hg @ 2002-03-29 04:46:17 by ben]
ben
parents: 771
diff changeset
584 assert (CODING_SYSTEM_TYPEP (XCODING_SYSTEM (x), type)); \
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
585 } while (0)
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
586 #else
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
587 # define XCODING_SYSTEM_OF_TYPE(x, type) XCODING_SYSTEM (x)
793
e38acbeb1cae [xemacs-hg @ 2002-03-29 04:46:17 by ben]
ben
parents: 771
diff changeset
588 # define XSETCODING_SYSTEM_OF_TYPE(x, p, type) do \
e38acbeb1cae [xemacs-hg @ 2002-03-29 04:46:17 by ben]
ben
parents: 771
diff changeset
589 { \
e38acbeb1cae [xemacs-hg @ 2002-03-29 04:46:17 by ben]
ben
parents: 771
diff changeset
590 x = wrap_coding_system (p); \
e38acbeb1cae [xemacs-hg @ 2002-03-29 04:46:17 by ben]
ben
parents: 771
diff changeset
591 } while (0)
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
592 #endif /* ERROR_CHECK_TYPE_CHECK */
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
593
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
594 #define CODING_SYSTEM_TYPEP(x, type) \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
595 (CODING_SYSTEMP (x) && CODING_SYSTEM_TYPE_P (XCODING_SYSTEM (x), type))
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
596 #define CHECK_CODING_SYSTEM_OF_TYPE(x, type) do { \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
597 CHECK_CODING_SYSTEM (x); \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
598 if (!CODING_SYSTEM_TYPE_P (XCODING_SYSTEM (x), type)) \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
599 dead_wrong_type_argument \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
600 (type##_coding_system_methods->predicate_symbol, x); \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
601 } while (0)
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
602 #define CONCHECK_CODING_SYSTEM_OF_TYPE(x, type) do { \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
603 CONCHECK_CODING_SYSTEM (x); \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
604 if (!(CODING_SYSTEM_TYPEP (x, type))) \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
605 x = wrong_type_argument \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
606 (type##_coding_system_methods->predicate_symbol, x); \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
607 } while (0)
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
608
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
609 #define CODING_SYSTEM_METHODS(codesys) ((codesys)->methods)
428
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
610 #define CODING_SYSTEM_NAME(codesys) ((codesys)->name)
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
611 #define CODING_SYSTEM_DESCRIPTION(codesys) ((codesys)->description)
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
612 #define CODING_SYSTEM_TYPE(codesys) ((codesys)->methods->type)
428
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
613 #define CODING_SYSTEM_MNEMONIC(codesys) ((codesys)->mnemonic)
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
614 #define CODING_SYSTEM_DOCUMENTATION(codesys) ((codesys)->documentation)
428
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
615 #define CODING_SYSTEM_POST_READ_CONVERSION(codesys) \
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
616 ((codesys)->post_read_conversion)
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
617 #define CODING_SYSTEM_PRE_WRITE_CONVERSION(codesys) \
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
618 ((codesys)->pre_write_conversion)
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
619 #define CODING_SYSTEM_EOL_TYPE(codesys) ((codesys)->eol_type)
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
620 #define CODING_SYSTEM_EOL_LF(codesys) ((codesys)->eol[EOL_LF])
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
621 #define CODING_SYSTEM_EOL_CRLF(codesys) ((codesys)->eol[EOL_CRLF])
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
622 #define CODING_SYSTEM_EOL_CR(codesys) ((codesys)->eol[EOL_CR])
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
623 #define CODING_SYSTEM_TEXT_FILE_WRAPPER(codesys) ((codesys)->text_file_wrapper)
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
624 #define CODING_SYSTEM_AUTO_EOL_WRAPPER(codesys) ((codesys)->auto_eol_wrapper)
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
625 #define CODING_SYSTEM_SUBSIDIARY_PARENT(codesys) ((codesys)->subsidiary_parent)
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
626 #define CODING_SYSTEM_CANONICAL(codesys) ((codesys)->canonical)
4568
1d74a1d115ee Add #'query-coding-region tests; do the work necessary to get them running.
Aidan Kehoe <kehoea@parhasard.net>
parents: 3017
diff changeset
627 #define CODING_SYSTEM_SAFE_CHARSETS(codesys) ((codesys)->safe_charsets)
1d74a1d115ee Add #'query-coding-region tests; do the work necessary to get them running.
Aidan Kehoe <kehoea@parhasard.net>
parents: 3017
diff changeset
628 #define CODING_SYSTEM_SAFE_CHARS(codesys) ((codesys)->safe_chars)
428
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
629
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
630 #define CODING_SYSTEM_CHAIN_CHAIN(codesys) \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
631 (CODING_SYSTEM_TYPE_DATA (codesys, chain)->chain)
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
632 #define CODING_SYSTEM_CHAIN_COUNT(codesys) \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
633 (CODING_SYSTEM_TYPE_DATA (codesys, chain)->count)
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
634 #define CODING_SYSTEM_CHAIN_CANONICALIZE_AFTER_CODING(codesys) \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
635 (CODING_SYSTEM_TYPE_DATA (codesys, chain)->canonicalize_after_coding)
428
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
636
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
637 #define XCODING_SYSTEM_METHODS(codesys) \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
638 CODING_SYSTEM_METHODS (XCODING_SYSTEM (codesys))
428
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
639 #define XCODING_SYSTEM_NAME(codesys) \
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
640 CODING_SYSTEM_NAME (XCODING_SYSTEM (codesys))
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
641 #define XCODING_SYSTEM_DESCRIPTION(codesys) \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
642 CODING_SYSTEM_DESCRIPTION (XCODING_SYSTEM (codesys))
428
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
643 #define XCODING_SYSTEM_TYPE(codesys) \
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
644 CODING_SYSTEM_TYPE (XCODING_SYSTEM (codesys))
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
645 #define XCODING_SYSTEM_MNEMONIC(codesys) \
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
646 CODING_SYSTEM_MNEMONIC (XCODING_SYSTEM (codesys))
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
647 #define XCODING_SYSTEM_DOCUMENTATION(codesys) \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
648 CODING_SYSTEM_DOCUMENTATION (XCODING_SYSTEM (codesys))
428
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
649 #define XCODING_SYSTEM_POST_READ_CONVERSION(codesys) \
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
650 CODING_SYSTEM_POST_READ_CONVERSION (XCODING_SYSTEM (codesys))
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
651 #define XCODING_SYSTEM_PRE_WRITE_CONVERSION(codesys) \
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
652 CODING_SYSTEM_PRE_WRITE_CONVERSION (XCODING_SYSTEM (codesys))
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
653 #define XCODING_SYSTEM_EOL_TYPE(codesys) \
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
654 CODING_SYSTEM_EOL_TYPE (XCODING_SYSTEM (codesys))
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
655 #define XCODING_SYSTEM_EOL_LF(codesys) \
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
656 CODING_SYSTEM_EOL_LF (XCODING_SYSTEM (codesys))
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
657 #define XCODING_SYSTEM_EOL_CRLF(codesys) \
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
658 CODING_SYSTEM_EOL_CRLF (XCODING_SYSTEM (codesys))
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
659 #define XCODING_SYSTEM_EOL_CR(codesys) \
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
660 CODING_SYSTEM_EOL_CR (XCODING_SYSTEM (codesys))
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
661 #define XCODING_SYSTEM_TEXT_FILE_WRAPPER(codesys) \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
662 CODING_SYSTEM_TEXT_FILE_WRAPPER (XCODING_SYSTEM (codesys))
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
663 #define XCODING_SYSTEM_AUTO_EOL_WRAPPER(codesys) \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
664 CODING_SYSTEM_AUTO_EOL_WRAPPER (XCODING_SYSTEM (codesys))
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
665 #define XCODING_SYSTEM_SUBSIDIARY_PARENT(codesys) \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
666 CODING_SYSTEM_SUBSIDIARY_PARENT (XCODING_SYSTEM (codesys))
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
667 #define XCODING_SYSTEM_CANONICAL(codesys) \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
668 CODING_SYSTEM_CANONICAL (XCODING_SYSTEM (codesys))
4568
1d74a1d115ee Add #'query-coding-region tests; do the work necessary to get them running.
Aidan Kehoe <kehoea@parhasard.net>
parents: 3017
diff changeset
669 #define XCODING_SYSTEM_SAFE_CHARSETS(codesys) \
1d74a1d115ee Add #'query-coding-region tests; do the work necessary to get them running.
Aidan Kehoe <kehoea@parhasard.net>
parents: 3017
diff changeset
670 CODING_SYSTEM_SAFE_CHARSETS (XCODING_SYSTEM (codesys))
1d74a1d115ee Add #'query-coding-region tests; do the work necessary to get them running.
Aidan Kehoe <kehoea@parhasard.net>
parents: 3017
diff changeset
671 #define XCODING_SYSTEM_SAFE_CHARS(codesys) \
1d74a1d115ee Add #'query-coding-region tests; do the work necessary to get them running.
Aidan Kehoe <kehoea@parhasard.net>
parents: 3017
diff changeset
672 CODING_SYSTEM_SAFE_CHARS (XCODING_SYSTEM (codesys))
428
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
673
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
674 #define XCODING_SYSTEM_CHAIN_CHAIN(codesys) \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
675 CODING_SYSTEM_CHAIN_CHAIN (XCODING_SYSTEM (codesys))
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
676 #define XCODING_SYSTEM_CHAIN_COUNT(codesys) \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
677 CODING_SYSTEM_CHAIN_COUNT (XCODING_SYSTEM (codesys))
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
678 #define XCODING_SYSTEM_CHAIN_CANONICALIZE_AFTER_CODING(codesys) \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
679 CODING_SYSTEM_CHAIN_CANONICALIZE_AFTER_CODING (XCODING_SYSTEM (codesys))
428
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
680
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
681 /**************************************************/
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
682 /* Detection */
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
683 /**************************************************/
428
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
684
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
685 #define MAX_DETECTOR_CATEGORIES 256
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
686 #define MAX_DETECTORS 64
428
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
687
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
688 #define MAX_BYTES_PROCESSED_FOR_DETECTION 65536
428
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
689
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
690 struct detection_state
428
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
691 {
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
692 int seen_non_ascii;
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
693 Bytecount bytes_seen;
428
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
694
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
695 char categories[MAX_DETECTOR_CATEGORIES];
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
696 Bytecount data_offset[MAX_DETECTORS];
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
697 /* ... more data follows; data_offset[detector_##TYPE] points to
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
698 the data for that type */
428
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
699 };
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
700
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
701 #define DETECTION_STATE_DATA(st, type) \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
702 ((struct type##_detector *) \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
703 ((char *) (st) + (st)->data_offset[detector_##type]))
428
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
704
448
3078fd1074e8 Import from CVS: tag r21-2-39
cvs
parents: 440
diff changeset
705 /* Distinguishable categories of encodings.
3078fd1074e8 Import from CVS: tag r21-2-39
cvs
parents: 440
diff changeset
706
3078fd1074e8 Import from CVS: tag r21-2-39
cvs
parents: 440
diff changeset
707 This list determines the initial priority of the categories.
3078fd1074e8 Import from CVS: tag r21-2-39
cvs
parents: 440
diff changeset
708
3078fd1074e8 Import from CVS: tag r21-2-39
cvs
parents: 440
diff changeset
709 For better or worse, currently Mule files are encoded in 7-bit ISO 2022.
3078fd1074e8 Import from CVS: tag r21-2-39
cvs
parents: 440
diff changeset
710 For this reason, under Mule ISO_7 gets highest priority.
3078fd1074e8 Import from CVS: tag r21-2-39
cvs
parents: 440
diff changeset
711
3078fd1074e8 Import from CVS: tag r21-2-39
cvs
parents: 440
diff changeset
712 Putting NO_CONVERSION second prevents "binary corruption" in the
3078fd1074e8 Import from CVS: tag r21-2-39
cvs
parents: 440
diff changeset
713 default case in all but the (presumably) extremely rare case of a
3078fd1074e8 Import from CVS: tag r21-2-39
cvs
parents: 440
diff changeset
714 binary file which contains redundant escape sequences but no 8-bit
3078fd1074e8 Import from CVS: tag r21-2-39
cvs
parents: 440
diff changeset
715 characters.
3078fd1074e8 Import from CVS: tag r21-2-39
cvs
parents: 440
diff changeset
716
3078fd1074e8 Import from CVS: tag r21-2-39
cvs
parents: 440
diff changeset
717 The remaining priorities are based on perceived "internationalization
3078fd1074e8 Import from CVS: tag r21-2-39
cvs
parents: 440
diff changeset
718 political correctness." An exception is UCS-4 at the bottom, since
3078fd1074e8 Import from CVS: tag r21-2-39
cvs
parents: 440
diff changeset
719 basically everything is compatible with UCS-4, but it is likely to
3078fd1074e8 Import from CVS: tag r21-2-39
cvs
parents: 440
diff changeset
720 be very rare as an external encoding. */
3078fd1074e8 Import from CVS: tag r21-2-39
cvs
parents: 440
diff changeset
721
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
722 /* Macros to define code of control characters for ISO2022's functions. */
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
723 /* Used by the detection routines of other coding system types as well. */
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
724 /* code */ /* function */
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
725 #define ISO_CODE_LF 0x0A /* line-feed */
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
726 #define ISO_CODE_CR 0x0D /* carriage-return */
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
727 #define ISO_CODE_SO 0x0E /* shift-out */
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
728 #define ISO_CODE_SI 0x0F /* shift-in */
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
729 #define ISO_CODE_ESC 0x1B /* escape */
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
730 #define ISO_CODE_DEL 0x7F /* delete */
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
731 #define ISO_CODE_SS2 0x8E /* single-shift-2 */
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
732 #define ISO_CODE_SS3 0x8F /* single-shift-3 */
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
733 #define ISO_CODE_CSI 0x9B /* control-sequence-introduce */
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
734
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
735 enum detection_result
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
736 {
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
737 /* Basically means a magic cookie was seen indicating this type, or
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
738 something similar. */
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
739 DET_NEAR_CERTAINTY = 4,
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
740 DET_HIGHEST = 4,
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
741 /* Characteristics seen that are unlikely to be other coding system types
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
742 -- e.g. ISO-2022 escape sequences, or perhaps a consistent pattern of
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
743 alternating zero bytes in UTF-16, along with Unicode LF or CRLF
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
744 sequences at regular intervals. (Zero bytes are unlikely or impossible
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
745 in most text encodings.) */
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
746 DET_QUITE_PROBABLE = 3,
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
747 /* Strong or medium statistical likelihood. At least some
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
748 characteristics seen that match what's normally found in this encoding
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
749 -- e.g. in Shift-JIS, a number of two-byte Japanese character
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
750 sequences in the right range, and nothing out of range; or in Unicode,
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
751 much higher statistical variance in the odd bytes than in the even
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
752 bytes, or vice-versa (perhaps the presence of regular EOL sequences
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
753 would bump this too to DET_QUITE_PROBABLE). This is quite often a
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
754 statistical test. */
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
755 DET_SOMEWHAT_LIKELY = 2,
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
756 /* Weak statistical likelihood. Pretty much any features at all that
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
757 characterize this encoding, and nothing that rules against it. */
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
758 DET_SLIGHTLY_LIKELY = 1,
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
759 /* Default state. Perhaps it indicates pure ASCII or something similarly
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
760 vague seen in Shift-JIS, or, exactly as the level says, it might mean
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
761 in a statistical-based detector that the pros and cons are balanced
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
762 out. This is also the lowest level that will be accepted by the
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
763 auto-detector without asking the user: If all available detectors
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
764 report lower levels for all categories with attached coding systems,
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
765 the user will be shown the results and explicitly prompted for action.
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
766 The user will also be prompted if this is the highest available level
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
767 and more than one detector reports the level. (See below about the
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
768 consequent necessity of an "ASCII" detector, which will return level 1
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
769 or higher for most plain text files.) */
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
770 DET_AS_LIKELY_AS_UNLIKELY = 0,
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
771 /* Some characteristics seen that are unusual for this encoding --
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
772 e.g. unusual control characters in a plain-text encoding, lots of
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
773 8-bit characters, or little statistical variance in the odd and even
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
774 bytes in UTF-16. */
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
775 DET_SOMEWHAT_UNLIKELY = -1,
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
776 /* This indicates that there is very little chance the data is in the
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
777 right format; this is probably the lowest level you can get when
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
778 presenting random binary data to a text file, because there are no
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
779 "specific sequences" you can see that would totally rule out
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
780 recognition. */
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
781 DET_QUITE_IMPROBABLE = -2,
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
782 /* An erroneous sequence was seen. */
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
783 DET_NEARLY_IMPOSSIBLE = -3,
1429
969b7290edca [xemacs-hg @ 2003-04-24 05:33:43 by youngs]
youngs
parents: 1315
diff changeset
784 DET_LOWEST = -3
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
785 };
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
786
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
787 extern int coding_detector_count;
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
788 extern int coding_detector_category_count;
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
789
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
790 struct detector_category
428
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
791 {
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
792 int id;
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
793 Lisp_Object sym;
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
794 };
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
795
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
796 typedef struct
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
797 {
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
798 Dynarr_declare (struct detector_category);
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
799 } detector_category_dynarr;
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
800
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
801 struct detector
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
802 {
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
803 int id;
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
804 detector_category_dynarr *cats;
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
805 Bytecount data_size;
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
806 /* Detect method: Required. */
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
807 void (*detect_method) (struct detection_state *st,
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
808 const unsigned char *src, Bytecount n);
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
809 /* Finalize detection state method: Clean up any allocated data in the
5124
623d57b7fbe8 separate regular and disksave finalization, print method fixes.
Ben Wing <ben@xemacs.org>
parents: 5120
diff changeset
810 detection state. Called only once. Optional. */
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
811 void (*finalize_detection_state_method) (struct detection_state *st);
428
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
812 };
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
813
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
814 /* Lvalue for a particular detection result -- detection state ST,
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
815 category CAT */
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
816 #define DET_RESULT(st, cat) ((st)->categories[detector_category_##cat])
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
817 /* In state ST, set all detection results associated with detector DET to
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
818 RESULT. */
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
819 #define SET_DET_RESULTS(st, det, result) \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
820 set_detection_results (st, detector_##det, result)
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
821
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
822 typedef struct
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
823 {
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
824 Dynarr_declare (struct detector);
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
825 } detector_dynarr;
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
826
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
827 extern detector_dynarr *all_coding_detectors;
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
828
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
829 #define DEFINE_DETECTOR_CATEGORY(detector, cat) \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
830 int detector_category_##cat
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
831 #define DECLARE_DETECTOR_CATEGORY(detector, cat) \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
832 extern int detector_category_##cat
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
833 #define INITIALIZE_DETECTOR_CATEGORY(detector, cat) \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
834 do { \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
835 struct detector_category dog; \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
836 xzero (dog); \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
837 detector_category_##cat = coding_detector_category_count++; \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
838 dump_add_opaque_int (&detector_category_##cat); \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
839 dog.id = detector_category_##cat; \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
840 dog.sym = Q##cat; \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
841 Dynarr_add (Dynarr_at (all_coding_detectors, detector_##detector).cats, \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
842 dog); \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
843 } while (0)
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
844
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
845 #define DEFINE_DETECTOR(Detector) \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
846 int detector_##Detector
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
847 #define DECLARE_DETECTOR(Detector) \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
848 extern int detector_##Detector
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
849 #define INITIALIZE_DETECTOR(Detector) \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
850 do { \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
851 struct detector det; \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
852 xzero (det); \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
853 detector_##Detector = coding_detector_count++; \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
854 dump_add_opaque_int (&detector_##Detector); \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
855 det.id = detector_##Detector; \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
856 det.cats = Dynarr_new2 (detector_category_dynarr, \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
857 struct detector_category); \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
858 det.data_size = sizeof (struct Detector##_detector); \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
859 Dynarr_add (all_coding_detectors, det); \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
860 } while (0)
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
861 #define DETECTOR_HAS_METHOD(Detector, Meth) \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
862 Dynarr_at (all_coding_detectors, detector_##Detector).Meth##_method = \
802
19dfb459d51a [xemacs-hg @ 2002-04-03 10:47:37 by ben]
ben
parents: 800
diff changeset
863 Detector##_##Meth
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
864
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
865
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
866 /**************************************************/
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
867 /* Decoding/Encoding */
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
868 /**************************************************/
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
869
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
870 /* Is the source (SOURCEP == 1) or sink (SOURCEP == 0) when encoding specified
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
871 in characters? */
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
872
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
873 enum source_or_sink
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
874 {
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
875 CODING_SOURCE,
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
876 CODING_SINK
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
877 };
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
878
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
879 enum encode_decode
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
880 {
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
881 CODING_ENCODE,
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
882 CODING_DECODE
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
883 };
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
884
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
885 /* Data structure attached to an lstream of type `coding',
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
886 containing values specific to the coding process. Additional
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
887 data is stored in the DATA field below; the exact form of that data
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
888 is controlled by the type of the coding system that governs the
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
889 conversion (field CODESYS). CODESYS may be set at any time
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
890 throughout the lifetime of the lstream and possibly more than once.
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
891 See long comment above for more info. */
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
892
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
893 struct coding_stream
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
894 {
1204
e22b0213b713 [xemacs-hg @ 2003-01-12 11:07:58 by michaels]
michaels
parents: 985
diff changeset
895 /* Enumerated constant listing which type of console this is (TTY, X,
e22b0213b713 [xemacs-hg @ 2003-01-12 11:07:58 by michaels]
michaels
parents: 985
diff changeset
896 MS-Windows, etc.). This duplicates the method structure in
e22b0213b713 [xemacs-hg @ 2003-01-12 11:07:58 by michaels]
michaels
parents: 985
diff changeset
897 XCODING_SYSTEM (str->codesys)->methods->type, which formerly was the
e22b0213b713 [xemacs-hg @ 2003-01-12 11:07:58 by michaels]
michaels
parents: 985
diff changeset
898 only way to determine the coding system type. We need this constant
e22b0213b713 [xemacs-hg @ 2003-01-12 11:07:58 by michaels]
michaels
parents: 985
diff changeset
899 now for KKCC, so that it can be used in an XD_UNION clause to
e22b0213b713 [xemacs-hg @ 2003-01-12 11:07:58 by michaels]
michaels
parents: 985
diff changeset
900 determine the Lisp objects in the type-specific data. */
e22b0213b713 [xemacs-hg @ 2003-01-12 11:07:58 by michaels]
michaels
parents: 985
diff changeset
901 enum coding_system_variant type;
e22b0213b713 [xemacs-hg @ 2003-01-12 11:07:58 by michaels]
michaels
parents: 985
diff changeset
902
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
903 /* Coding system that governs the conversion. */
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
904 Lisp_Object codesys;
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
905 /* Original coding system, pre-canonicalization. */
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
906 Lisp_Object orig_codesys;
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
907
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
908 /* Back pointer to current stream. */
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
909 Lstream *us;
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
910
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
911 /* Stream that we read the unprocessed data from or write the processed
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
912 data to. */
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
913 Lstream *other_end;
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
914
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
915 /* In order to handle both reading to and writing from a coding stream,
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
916 we phrase the conversion methods like write methods -- we can
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
917 implement reading in terms of a write method but not vice-versa,
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
918 because the write method is forced to take only what it's given but
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
919 the read method can read more data from the other end if necessary.
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
920 On the other hand, the write method is free to generate all the data
2297
13a418960a88 [xemacs-hg @ 2004-09-22 02:05:42 by stephent]
stephent
parents: 2132
diff changeset
921 it wants (and just write it to the other end), but the read method
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
922 can return only as much as was asked for, so we need to implement our
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
923 own buffering. */
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
924
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
925 /* If we are reading, then we can return only a fixed amount of data, but
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
926 the converter is free to return as much as it wants, so we direct it
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
927 to store the data here and lop off chunks as we need them. If we are
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
928 writing, we use this because the converter takes a Dynarr but we are
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
929 supposed to write into a fixed buffer. (NOTE: This introduces an extra
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
930 memory copy.) */
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
931 unsigned_char_dynarr *convert_to;
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
932
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
933 /* The conversion method might reject some of the data -- this typically
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
934 includes partial characters, partial escape sequences, etc. When
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
935 writing, we just pass the rejection up to the Lstream module, and it
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
936 will buffer the data. When reading, however, we need to do the
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
937 buffering ourselves, and we put it here, combined with newly read
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
938 data. */
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
939 unsigned_char_dynarr *convert_from;
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
940
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
941 /* If set, this is the last chunk of data being processed. When this is
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
942 finished, output any necessary terminating control characters, escape
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
943 sequences, etc. */
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
944 unsigned int eof:1;
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
945
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
946 /* CH holds a partially built-up character. This is really part of the
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
947 state-dependent data and should be moved there. */
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
948 unsigned int ch;
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
949
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
950 /* Coding-system-specific data holding extra state about the
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
951 conversion. Logically a struct TYPE_coding_stream; a pointer
800
a5954632b187 [xemacs-hg @ 2002-03-31 08:27:14 by ben]
ben
parents: 793
diff changeset
952 to such a struct, with (when ERROR_CHECK_TYPES is defined)
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
953 error-checking that this is really a structure of that type
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
954 (checking the corresponding coding system type) can be retrieved using
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
955 CODING_STREAM_TYPE_DATA(). Allocated at the same time that
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
956 CODESYS is set (which may occur at any time, even multiple times,
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
957 during the lifetime of the stream). The size comes from
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
958 methods->coding_data_size. */
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
959 void *data;
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
960
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
961 enum encode_decode direction;
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
962
800
a5954632b187 [xemacs-hg @ 2002-03-31 08:27:14 by ben]
ben
parents: 793
diff changeset
963 /* If set, don't close the stream at the other end when being closed. */
a5954632b187 [xemacs-hg @ 2002-03-31 08:27:14 by ben]
ben
parents: 793
diff changeset
964 unsigned int no_close_other:1;
802
19dfb459d51a [xemacs-hg @ 2002-04-03 10:47:37 by ben]
ben
parents: 800
diff changeset
965 /* If set, read only one byte at a time from other end to avoid any
19dfb459d51a [xemacs-hg @ 2002-04-03 10:47:37 by ben]
ben
parents: 800
diff changeset
966 possible blocking. */
19dfb459d51a [xemacs-hg @ 2002-04-03 10:47:37 by ben]
ben
parents: 800
diff changeset
967 unsigned int one_byte_at_a_time:1;
814
a634e3b7acc8 [xemacs-hg @ 2002-04-14 12:41:59 by ben]
ben
parents: 802
diff changeset
968 /* If set, and we're a read stream, we init char mode on ourselves as
a634e3b7acc8 [xemacs-hg @ 2002-04-14 12:41:59 by ben]
ben
parents: 802
diff changeset
969 necessary to prevent the caller from getting partial characters. (the
a634e3b7acc8 [xemacs-hg @ 2002-04-14 12:41:59 by ben]
ben
parents: 802
diff changeset
970 default) */
a634e3b7acc8 [xemacs-hg @ 2002-04-14 12:41:59 by ben]
ben
parents: 802
diff changeset
971 unsigned int set_char_mode_on_us_when_reading:1;
800
a5954632b187 [xemacs-hg @ 2002-03-31 08:27:14 by ben]
ben
parents: 793
diff changeset
972
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
973 /* #### Temporary test */
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
974 unsigned int finalized:1;
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
975 };
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
976
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
977 #define CODING_STREAM_DATA(stream) LSTREAM_TYPE_DATA (stream, coding)
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
978
800
a5954632b187 [xemacs-hg @ 2002-03-31 08:27:14 by ben]
ben
parents: 793
diff changeset
979 #ifdef ERROR_CHECK_TYPES
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
980 # define CODING_STREAM_TYPE_DATA(s, type) \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
981 error_check_##type##_coding_stream_data (s)
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
982 #else
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
983 # define CODING_STREAM_TYPE_DATA(s, type) \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
984 ((struct type##_coding_stream *) (s)->data)
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
985 #endif
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
986
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
987 /* C should be a binary character in the range 0 - 255; convert
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
988 to internal format and add to Dynarr DST. */
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
989
428
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
990 #ifdef MULE
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
991
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
992 #define DECODE_ADD_BINARY_CHAR(c, dst) \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
993 do { \
826
6728e641994e [xemacs-hg @ 2002-05-05 11:30:15 by ben]
ben
parents: 814
diff changeset
994 if (byte_ascii_p (c)) \
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
995 Dynarr_add (dst, c); \
826
6728e641994e [xemacs-hg @ 2002-05-05 11:30:15 by ben]
ben
parents: 814
diff changeset
996 else if (byte_c1_p (c)) \
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
997 { \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
998 Dynarr_add (dst, LEADING_BYTE_CONTROL_1); \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
999 Dynarr_add (dst, c + 0x20); \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
1000 } \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
1001 else \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
1002 { \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
1003 Dynarr_add (dst, LEADING_BYTE_LATIN_ISO8859_1); \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
1004 Dynarr_add (dst, c); \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
1005 } \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
1006 } while (0)
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
1007
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
1008 #else /* not MULE */
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
1009
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
1010 #define DECODE_ADD_BINARY_CHAR(c, dst) \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
1011 do { \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
1012 Dynarr_add (dst, c); \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
1013 } while (0)
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
1014
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
1015 #endif /* MULE */
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
1016
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
1017 #define DECODE_OUTPUT_PARTIAL_CHAR(ch, dst) \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
1018 do { \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
1019 if (ch) \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
1020 { \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
1021 DECODE_ADD_BINARY_CHAR (ch, dst); \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
1022 ch = 0; \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
1023 } \
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
1024 } while (0)
428
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
1025
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
1026 #ifdef MULE
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
1027 /* Convert shift-JIS code (sj1, sj2) into internal string
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
1028 representation (c1, c2). (The leading byte is assumed.) */
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
1029
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
1030 #define DECODE_SHIFT_JIS(sj1, sj2, c1, c2) \
428
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
1031 do { \
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
1032 int I1 = sj1, I2 = sj2; \
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
1033 if (I2 >= 0x9f) \
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
1034 c1 = (I1 << 1) - ((I1 >= 0xe0) ? 0xe0 : 0x60), \
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
1035 c2 = I2 + 2; \
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
1036 else \
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
1037 c1 = (I1 << 1) - ((I1 >= 0xe0) ? 0xe1 : 0x61), \
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
1038 c2 = I2 + ((I2 >= 0x7f) ? 0x60 : 0x61); \
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
1039 } while (0)
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
1040
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
1041 /* Convert the internal string representation of a Shift-JIS character
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
1042 (c1, c2) into Shift-JIS code (sj1, sj2). The leading byte is
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
1043 assumed. */
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
1044
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
1045 #define ENCODE_SHIFT_JIS(c1, c2, sj1, sj2) \
428
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
1046 do { \
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
1047 int I1 = c1, I2 = c2; \
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
1048 if (I1 & 1) \
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
1049 sj1 = (I1 >> 1) + ((I1 < 0xdf) ? 0x31 : 0x71), \
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
1050 sj2 = I2 - ((I2 >= 0xe0) ? 0x60 : 0x61); \
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
1051 else \
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
1052 sj1 = (I1 >> 1) + ((I1 < 0xdf) ? 0x30 : 0x70), \
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
1053 sj2 = I2 - 2; \
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
1054 } while (0)
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
1055 #endif /* MULE */
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
1056
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
1057 DECLARE_CODING_SYSTEM_TYPE (no_conversion);
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
1058 DECLARE_CODING_SYSTEM_TYPE (convert_eol);
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
1059 #if 0
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
1060 DECLARE_CODING_SYSTEM_TYPE (text_file_wrapper);
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
1061 #endif /* 0 */
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
1062 DECLARE_CODING_SYSTEM_TYPE (undecided);
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
1063 DECLARE_CODING_SYSTEM_TYPE (chain);
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
1064
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
1065 #ifdef DEBUG_XEMACS
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
1066 DECLARE_CODING_SYSTEM_TYPE (internal);
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
1067 #endif
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
1068
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
1069 #ifdef MULE
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
1070 DECLARE_CODING_SYSTEM_TYPE (iso2022);
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
1071 DECLARE_CODING_SYSTEM_TYPE (ccl);
4690
257b468bf2ca Move the #'query-coding-region implementation to C.
Aidan Kehoe <kehoea@parhasard.net>
parents: 4569
diff changeset
1072 DECLARE_CODING_SYSTEM_TYPE (fixed_width);
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
1073 DECLARE_CODING_SYSTEM_TYPE (shift_jis);
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
1074 DECLARE_CODING_SYSTEM_TYPE (big5);
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
1075 #endif
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
1076
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
1077 #ifdef HAVE_ZLIB
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
1078 DECLARE_CODING_SYSTEM_TYPE (gzip);
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
1079 #endif
428
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
1080
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
1081 DECLARE_CODING_SYSTEM_TYPE (unicode);
428
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
1082
1315
70921960b980 [xemacs-hg @ 2003-02-20 08:19:28 by ben]
ben
parents: 1204
diff changeset
1083 #ifdef WIN32_ANY
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
1084 DECLARE_CODING_SYSTEM_TYPE (mswindows_multibyte_to_unicode);
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
1085 DECLARE_CODING_SYSTEM_TYPE (mswindows_multibyte);
428
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
1086 #endif
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
1087
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
1088 Lisp_Object coding_stream_detected_coding_system (Lstream *stream);
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
1089 Lisp_Object coding_stream_coding_system (Lstream *stream);
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
1090 void set_coding_stream_coding_system (Lstream *stream,
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
1091 Lisp_Object codesys);
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
1092 Lisp_Object detect_coding_stream (Lisp_Object stream);
867
804517e16990 [xemacs-hg @ 2002-06-05 09:54:39 by ben]
ben
parents: 826
diff changeset
1093 Ichar decode_big5_char (int o1, int o2);
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
1094 void add_entry_to_coding_system_type_list (struct coding_system_methods *m);
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
1095 Lisp_Object make_internal_coding_system (Lisp_Object existing,
4528
726060ee587c First draft of g++ 4.3 warning removal patch. Builds. *Needs ChangeLogs.*
Stephen J. Turnbull <stephen@xemacs.org>
parents: 4522
diff changeset
1096 const Ascbyte *prefix,
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
1097 Lisp_Object type,
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
1098 Lisp_Object description,
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
1099 Lisp_Object props);
802
19dfb459d51a [xemacs-hg @ 2002-04-03 10:47:37 by ben]
ben
parents: 800
diff changeset
1100
814
a634e3b7acc8 [xemacs-hg @ 2002-04-14 12:41:59 by ben]
ben
parents: 802
diff changeset
1101 #define LSTREAM_FL_NO_CLOSE_OTHER (1 << 16)
a634e3b7acc8 [xemacs-hg @ 2002-04-14 12:41:59 by ben]
ben
parents: 802
diff changeset
1102 #define LSTREAM_FL_READ_ONE_BYTE_AT_A_TIME (1 << 17)
a634e3b7acc8 [xemacs-hg @ 2002-04-14 12:41:59 by ben]
ben
parents: 802
diff changeset
1103 #define LSTREAM_FL_NO_INIT_CHAR_MODE_WHEN_READING (1 << 18)
a634e3b7acc8 [xemacs-hg @ 2002-04-14 12:41:59 by ben]
ben
parents: 802
diff changeset
1104
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
1105 Lisp_Object make_coding_input_stream (Lstream *stream, Lisp_Object codesys,
800
a5954632b187 [xemacs-hg @ 2002-03-31 08:27:14 by ben]
ben
parents: 793
diff changeset
1106 enum encode_decode direction,
802
19dfb459d51a [xemacs-hg @ 2002-04-03 10:47:37 by ben]
ben
parents: 800
diff changeset
1107 int flags);
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
1108 Lisp_Object make_coding_output_stream (Lstream *stream, Lisp_Object codesys,
800
a5954632b187 [xemacs-hg @ 2002-03-31 08:27:14 by ben]
ben
parents: 793
diff changeset
1109 enum encode_decode direction,
802
19dfb459d51a [xemacs-hg @ 2002-04-03 10:47:37 by ben]
ben
parents: 800
diff changeset
1110 int flags);
771
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
1111 void set_detection_results (struct detection_state *st, int detector,
943eaba38521 [xemacs-hg @ 2002-03-13 08:51:24 by ben]
ben
parents: 665
diff changeset
1112 int given);
428
3ecd8885ac67 Import from CVS: tag r21-2-22
cvs
parents:
diff changeset
1113
440
8de8e3f6228a Import from CVS: tag r21-2-28
cvs
parents: 438
diff changeset
1114 #endif /* INCLUDED_file_coding_h_ */
8de8e3f6228a Import from CVS: tag r21-2-28
cvs
parents: 438
diff changeset
1115