c/libxml2
1
0
Fork 0
mirror of https://gitlab.gnome.org/GNOME/libxml2 synced 2025-03-28 21:33:13 +00:00
Code Issues Packages Projects Releases Wiki Activity

OS400: iconv functions compatibility wrappers and table builder.

Browse Source
This commit is contained in:
Patrick Monnerat 2014-03-04 16:42:19 +01:00 committed by Daniel Veillard
parent ea8c89b9b5
commit 17951ea289
8 changed files with 10165 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

47
os400/iconv/README.iconv Normal file
View File

@ -0,0 +1,47 @@
IBM OS/400 implements iconv in an odd way:
- Type iconv_t is a structure: therefore objects of this type cannot be
compared to (iconv_t) -1.
- Supported character sets names are all of the form IBMCCSIDccsid..., where
ccsid is a decimal 5-digit integer identifying an IBM coded character set.
In addition, character set names have to be given in EBCDIC.
Standard character set names like "UTF-8" are NOT recognized.
- The prototype of iconv_open() does not declare parameters as const, although
they are not altered.
Since libiconv does not support EBCDIC, use of this package here as a
replacement is not a solution.
For these reasons, the code in this directory implements a wrapper to the
OS/400 iconv implementation. The wrapper performs the following transformations:
- Type iconv_t is an pointer. Although OS/400 pointers are odd, comparing
with (iconv_t) -1 is OK.
- All IANA character set names are recognized in a coding- and case-insensitive
way, providing an equivalent CCSID exists. see
http://www.iana.org/assignments/character-sets/character-sets.xhtml
- All CCSIDs from the association file can be expressed as IBMCCSIDxxxxx where
xxxxx is the 5 digit CCSID; no null terminator is required. Alternate codes
are of the form ibm-xxx (null-terminated), where xxx is the integer CCSID with
leading zeroes stripped.
- If a IANA BIBenum is defined for a CCSID, the name iana-xxx can be used,
where xxx is the integer MIBenum without leading zeroes.
- In addition, some aliases are also taken from the association file. Examples
are: ASCII, EBCDIC, UTF8.
- Prototype of iconv_open() has const parameters.
- Character code names can be given in any code.
Character set names to CCSID conversion.
- http://www.iana.org/assignments/character-sets/character-sets.xhtml provides
all IANA registered character set names and aliases associated with a
MIBenum, that is a unique character set identifier.
- A hand-maintained file ccsid_mibenum.xml associates IBM CCSIDs to
IANA MBenums.
- An OS/400 C program (in subdirectory bldcsndfa) generates a deterministic
finite automaton from the files mentioned above into a C file for all
possible character set name and associating each of them with its
corresponding CCSID. This program can only be run on OS/400 since it uses
the native iconv support for EBCDIC.
- Since these operations are tedious and the table generation needs bootstraping
with libxml2, the generated automaton is stored within sources and need not
be rebuilt at each compilation. However, source is provided here to allow
new table generation with conversion tables that were not available at the
time of original generation.

1953
os400/iconv/bldcsndfa/bldcsndfa.c Normal file
View File

File diff suppressed because it is too large Load Diff

15
os400/iconv/bldcsndfa/ccsid_mibenum.dtd Normal file
View File

@ -0,0 +1,15 @@
<?xml version="1.0" encoding="UTF-8"?>
<!--
--- DTD for CCSID/MIBEnum association documents.
---
--- See Copyright for the status of this software.
---
--- Author: Patrick Monnerat <pm@datasphere.ch>, DATASPHERE S.A.
-->
<!ELEMENT ccsid_mibenum (assoc)*>
<!ELEMENT assoc (alias)*>
<!ATTLIST assoc
ccsid CDATA #IMPLIED
mibenum CDATA #IMPLIED
>
<!ELEMENT alias (#PCDATA)>

270
os400/iconv/bldcsndfa/ccsid_mibenum.xml Normal file
View File

@ -0,0 +1,270 @@
<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE ccsid_mibenum SYSTEM "ccsid_mibenum.dtd">
<!--
--- CCSID/MIBEnum associations.
---
--- See Copyright for the status of this software.
---
--- Author: Patrick Monnerat <pm@datasphere.ch>, DATASPHERE S.A.
-->
<ccsid_mibenum>
<assoc ccsid="0"><!-- Curent job's CCSID. --></assoc>
<assoc ccsid="37" mibenum="2028"><!-- EBCDIC-US -->
<alias>EBCDIC</alias>
</assoc>
<assoc ccsid="256"><!-- Netherlands ? --></assoc>
<assoc ccsid="273" mibenum="2030"><!-- EBCDIC-DE --></assoc>
<assoc ccsid="277" mibenum="2033"><!-- EBCDIC-DK/NO --></assoc>
<assoc ccsid="278" mibenum="2034"><!-- EBCDIC-FI/SE --></assoc>
<assoc ccsid="280" mibenum="2035"><!-- EBCDIC-IT --></assoc>
<assoc ccsid="284" mibenum="2037"><!-- EBCDIC-ES --></assoc>
<assoc ccsid="285" mibenum="2038"><!-- EBCDIC-GB --></assoc>
<assoc ccsid="290" mibenum="2039"><!-- EBCDIC-JP-Kana --></assoc>
<assoc ccsid="297" mibenum="2040"><!-- EBCDIC-FR --></assoc>
<assoc ccsid="300"><!-- Japan English ? --></assoc>
<assoc ccsid="301"><!-- PC DATA Japanese --></assoc>
<assoc ccsid="367" mibenum="3"><!-- ANSI X3.4 ASCII -->
<alias>ASCII</alias>
</assoc>
<assoc ccsid="420" mibenum="2041"><!-- EBCDIC-Arab --></assoc>
<assoc ccsid="423" mibenum="2042"><!-- EBCDIC-GR --></assoc>
<assoc ccsid="424" mibenum="2043"><!-- EBCDIC-Hebrew --></assoc>
<assoc ccsid="437" mibenum="2011"><!-- 8-bit PC ASCII --></assoc>
<assoc ccsid="500" mibenum="2044"><!-- EBCDIC-BE/CH international latin 1 --></assoc>
<assoc ccsid="720"><!-- MSDOS Arabic ? --></assoc>
<assoc ccsid="737"><!-- MSDOS Greek PC DATA ? --></assoc>
<assoc ccsid="775" mibenum="2087"><!-- MSDOS Baltic PC DATA --></assoc>
<assoc ccsid="813" mibenum="10"><!-- ISO-8859-7 --></assoc>
<assoc ccsid="819" mibenum="4"><!-- ISO-8859-1 --></assoc>
<assoc ccsid="833"><!-- Korea (extended range) --></assoc>
<assoc ccsid="835"><!-- Korea host double byte --></assoc>
<assoc ccsid="836"><!-- Simplified chinese (extended range) --></assoc>
<assoc ccsid="837"><!-- Simplified chinese --></assoc>
<assoc ccsid="838" mibenum="2016"><!-- IBM-Thai --></assoc>
<assoc ccsid="850" mibenum="2009"><!-- PC DATA international latin 1 --></assoc>
<assoc ccsid="851" mibenum="2045"><!-- PC DATA greek --></assoc>
<assoc ccsid="852" mibenum="2010"><!-- PC DATA latin-2 multilingual --></assoc>
<assoc ccsid="855" mibenum="2046"><!-- PC DATA ROECE cyrillic --></assoc>
<assoc ccsid="857" mibenum="2047"><!-- PC DATA Turkey latin-5 --></assoc>
<assoc ccsid="858" mibenum="2089"><!-- PC-Multilingual-850+Euro --></assoc>
<assoc ccsid="860" mibenum="2048"><!-- PC DATA Portugal --></assoc>
<assoc ccsid="861" mibenum="2049"><!-- PC DATA Iceland --></assoc>
<assoc ccsid="862" mibenum="2013"><!-- PC DATA Hebrew --></assoc>
<assoc ccsid="863" mibenum="2050"><!-- PC DATA Canada --></assoc>
<assoc ccsid="864" mibenum="2051"><!-- PC DATA Arabic --></assoc>
<assoc ccsid="865" mibenum="2052"><!-- PC DATA DK/NO --></assoc>
<assoc ccsid="866" mibenum="2086"><!-- PC DATA cyrillic 2 --></assoc>
<assoc ccsid="868" mibenum="2053"><!-- PC DATA Urdu --></assoc>
<assoc ccsid="869" mibenum="2054"><!-- PC DATA greek (2?) --></assoc>
<assoc ccsid="870" mibenum="2055"><!-- EBCDIC-Latin2-Multilingual --></assoc>
<assoc ccsid="871" mibenum="2056"><!-- EBCDIC-IS --></assoc>
<assoc ccsid="874" mibenum="2259"><!-- TIS-620 -->
<alias>EUC-TH></alias>
<alias>eucTH</alias>
<alias>csEUCTH</alias>
</assoc>
<assoc ccsid="875"><!-- Greece --></assoc>
<assoc ccsid="878" mibenum="2084"><!-- KOI8-R --></assoc>
<assoc ccsid="880" mibenum="2057"><!-- EBCDIC-Cyrillic --></assoc>
<assoc ccsid="891" mibenum="2058"><!-- PC DATA corean (non-extended) --></assoc>
<assoc ccsid="896"><!-- Japan 7-bit Katakana --></assoc>
<assoc ccsid="897" mibenum="15"><!-- JIS_X0201 --></assoc>
<assoc ccsid="903" mibenum="2059"><!-- PC DATA simplified chinese (non-extended) --></assoc>
<assoc ccsid="904" mibenum="2060"><!-- PC DATA traditional chinese --></assoc>
<assoc ccsid="905" mibenum="2061"><!-- EBCDIC-TR latin 3 --></assoc>
<assoc ccsid="912" mibenum="5"><!-- ISO-8859-2 --></assoc>
<assoc ccsid="913" mibenum="6"><!-- ISO-8859-3 --></assoc>
<assoc ccsid="914" mibenum="7"><!-- ISO-8859-4 --></assoc>
<assoc ccsid="915" mibenum="8"><!-- ISO-8859-5 --></assoc>
<assoc ccsid="916" mibenum="11"><!-- ISO-8859-8 --></assoc>
<assoc ccsid="918" mibenum="2062"><!-- IBM918 --></assoc>
<assoc ccsid="920" mibenum="12"><!-- ISO-8859-9 --></assoc>
<assoc ccsid="921" mibenum="109"><!-- ISO-8859-13 --></assoc>
<assoc ccsid="922"><!-- Estonia, 8-bit --></assoc>
<assoc ccsid="923" mibenum="111"><!-- ISO-8859-15 --></assoc>
<assoc ccsid="924" mibenum="2090"><!-- EBCDIC-Latin9+Euro --></assoc>
<assoc ccsid="926"><!-- Korean PC DATA DBCS, UDC 1880 --></assoc>
<assoc ccsid="927"><!-- Traditional chinese PC DATA DBCS, UDC 6204 --></assoc>
<assoc ccsid="928"><!-- Simplified chinese PC DATA DBCS, UDC 1880 --></assoc>
<assoc ccsid="930"><!-- Japan Katakana (extended range) 4370 UDC (User Defined Characters) --></assoc>
<assoc ccsid="932"><!-- Japan PC DATA Mixed --></assoc>
<assoc ccsid="933"><!-- Korea (extended range), 1880 UDC --></assoc>
<assoc ccsid="934"><!-- Korean PC DATA --></assoc>
<assoc ccsid="935"><!-- Simplified Chinese (extended range) --></assoc>
<assoc ccsid="936"><!-- Simplified Chinese (non-extended) --></assoc>
<assoc ccsid="937"><!-- Traditional Chinese (extended range) --></assoc>
<assoc ccsid="938"><!-- Traditional Chinese (non-extended) --></assoc>
<assoc ccsid="939"><!-- Japan English (extended range) 4370 UDC --></assoc>
<assoc ccsid="942"><!-- Japanese PC DATA Mixed --></assoc>
<assoc ccsid="943" mibenum="17"><!-- Shift_JIS --></assoc>
<assoc ccsid="944"><!-- Korean PC DATA Mixed --></assoc>
<assoc ccsid="946"><!-- Simplified Chinese PC DATA Mixed --></assoc>
<assoc ccsid="947"><!-- Traditional Chinese PC DATA Mixed 6204 UDC (User Defined Characters) --></assoc>
<assoc ccsid="949"><!-- Republic of Korea National Standard Graphic Character Set (KS). PC DATA mixed-byte including 1800 UDC --></assoc>
<assoc ccsid="950"><!-- Traditional Chinese PC DATA Mixed for Big5 --></assoc>
<assoc ccsid="951"><!-- Republic of Korea National Standard Graphic Character Set (KS). PC DATA double-byte including 1800 UDC --></assoc>
<assoc ccsid="956"><!-- JIS X201 Roman for CP 00895; JIS X208-1983 for CP 00952 --></assoc>
<assoc ccsid="957"><!-- JIS X201 Roman for CP 00895; JIS X208-1978 for CP 00955 --></assoc>
<assoc ccsid="958"><!-- ASCII for CP 00367; JIS X208-1983 for CP 00952 --></assoc>
<assoc ccsid="959"><!-- ASCII for CP 00367; JIS X208-1978 for CP 00955 --></assoc>
<assoc ccsid="964"><!-- G0 - ASCII for CP 00367; G1-CNS 11643 plane 1 for CP 960 --></assoc>
<assoc ccsid="965"><!-- ASCII for CP 00367; CNS 11643 plane 1 for CP 960 --></assoc>
<assoc ccsid="970" mibenum="38"><!-- EUC-KR --></assoc>
<assoc ccsid="1008"><!-- Arabic 8-bit ISO/ASCII --></assoc>
<assoc ccsid="1009"><!-- IRV --></assoc>
<assoc ccsid="1010"><!-- France --></assoc>
<assoc ccsid="1011"><!-- Germany --></assoc>
<assoc ccsid="1012"><!-- Italy --></assoc>
<assoc ccsid="1013"><!-- United Kingdom --></assoc>
<assoc ccsid="1014"><!-- Spain --></assoc>
<assoc ccsid="1015"><!-- Portugal --></assoc>
<assoc ccsid="1016"><!-- Norway --></assoc>
<assoc ccsid="1017"><!-- Denmark --></assoc>
<assoc ccsid="1018"><!-- Finland and Sweden --></assoc>
<assoc ccsid="1019"><!-- Belgium and Netherlands --></assoc>
<assoc ccsid="1025"><!-- Cyrillic Multilingual --></assoc>
<assoc ccsid="1026" mibenum="2063"><!-- Turkey latin 5 CECP --></assoc>
<assoc ccsid="1027"><!-- Japan english (extended range) --></assoc>
<assoc ccsid="1040"><!-- Korean Latin PC DATA extended --></assoc>
<assoc ccsid="1041"><!-- Japanese PC DATA extended --></assoc>
<assoc ccsid="1042"><!-- Simplified Chinese PC DATA extended --></assoc>
<assoc ccsid="1043"><!-- Traditional Chinese PC DATA extended --></assoc>
<assoc ccsid="1046"><!-- PC DATA - Arabic Extended --></assoc>
<assoc ccsid="1047" mibenum="2102"><!-- Latin open sys EBCDIC --></assoc>
<assoc ccsid="1051" mibenum="2004"><!-- hp-roman8 --></assoc>
<assoc ccsid="1088"><!-- Korean PC DATA single-byte --></assoc>
<assoc ccsid="1089" mibenum="9"><!-- ISO 8859-6: Arabic --></assoc>
<assoc ccsid="1097"><!-- Farsi --></assoc>
<assoc ccsid="1098"><!-- Farsi (IBM-PC) --></assoc>
<assoc ccsid="1112"><!-- Baltic, Multilingual --></assoc>
<assoc ccsid="1114"><!-- Traditional Chinese, Taiwan Industry Graphic Character Set (Big5) --></assoc>
<assoc ccsid="1115"><!-- Simplified Chinese, People&#x27;s Republic of China National. Standard (GB), personal computer SBCS --></assoc>
<assoc ccsid="1122"><!-- Estonia --></assoc>
<assoc ccsid="1123"/>
<assoc ccsid="1129"><!-- ISO-8 Vietnamese --></assoc>
<assoc ccsid="1130"><!-- EBCDIC Vietnamese --></assoc>
<assoc ccsid="1132"><!-- EBCDIC Lao --></assoc>
<assoc ccsid="1133"><!-- ISO-8 Lao --></assoc>
<assoc ccsid="1137"/>
<assoc ccsid="1140" mibenum="2091"><!-- EBCDIC-US-37+Euro --></assoc>
<assoc ccsid="1141" mibenum="2092"><!-- EBCDIC-DE-273+Euro --></assoc>
<assoc ccsid="1142" mibenum="2093"><!-- EBCDIC-DK/NO-277+Euro --></assoc>
<assoc ccsid="1143" mibenum="2094"><!-- EBCDIC-FI/SE-278+Euro --></assoc>
<assoc ccsid="1144" mibenum="2095"><!-- EBCDIC-IT-280+Euro --></assoc>
<assoc ccsid="1145" mibenum="2096"><!-- EBCDIC-ES-284+Euro --></assoc>
<assoc ccsid="1146" mibenum="2097"><!-- EBCDIC-GB-285+Euro --></assoc>
<assoc ccsid="1147" mibenum="2098"><!-- EBCDIC-FR-297+Euro --></assoc>
<assoc ccsid="1148" mibenum="2099"><!-- EBCDIC-INT-500+Euro --></assoc>
<assoc ccsid="1149" mibenum="2100"><!-- EBCDIC-IS-871+Euro --></assoc>
<assoc ccsid="1153"/>
<assoc ccsid="1154"/>
<assoc ccsid="1155"/>
<assoc ccsid="1156"/>
<assoc ccsid="1157"/>
<assoc ccsid="1158"/>
<assoc ccsid="1160"/>
<assoc ccsid="1164"/>
<assoc ccsid="1201" mibenum="1013"><!-- UTF-16BE -->
<alias>UTF16-BE</alias>
<alias>UTF16BE</alias>
<alias>UTF-16-BE</alias>
</assoc>
<assoc ccsid="1203" mibenum="1014"><!-- UTF-16LE -->
<alias>UTF16-LE</alias>
<alias>UTF16LE</alias>
<alias>UTF-16-LE</alias>
</assoc>
<assoc ccsid="1208" mibenum="106"><!-- UTF-8 -->
<alias>UTF8</alias>
</assoc>
<assoc ccsid="1233" mibenum="1018"><!-- UTF-32BE -->
<alias>UTF32-BE</alias>
<alias>UTF32BE</alias>
<alias>UTF-32-BE</alias>
</assoc>
<assoc ccsid="1235" mibenum="1019"><!-- UTF-32LE -->
<alias>UTF32-LE</alias>
<alias>UTF32LE</alias>
<alias>UTF-32-LE</alias>
</assoc>
<assoc ccsid="1250" mibenum="2002"><!-- Windows Latin 2 --></assoc>
<assoc ccsid="1251"><!-- Windows Cyrillic --></assoc>
<assoc ccsid="1252" mibenum="2001"><!-- Windows Latin 1 --></assoc>
<assoc ccsid="1253"><!-- Windows Greek --></assoc>
<assoc ccsid="1254"><!-- Windows Turkish --></assoc>
<assoc ccsid="1255"><!-- Windows Hebrew --></assoc>
<assoc ccsid="1256"><!-- Windows Arabic --></assoc>
<assoc ccsid="1257"><!-- Windows Baltic Rim --></assoc>
<assoc ccsid="1258"><!-- Windows Vietnamese --></assoc>
<assoc ccsid="1275"><!-- Apple, Latin-1 --></assoc>
<assoc ccsid="1276" mibenum="2005"><!-- Adobe-Standard-Encoding --></assoc>
<assoc ccsid="1280"><!-- Apple, Greek --></assoc>
<assoc ccsid="1281"><!-- Apple, Turkey --></assoc>
<assoc ccsid="1282"><!-- Apple, Central European (Latin-2) --></assoc>
<assoc ccsid="1283"><!-- Apple, Cyrillic --></assoc>
<assoc ccsid="1363" mibenum="36"><!-- KS_C_5601-1987 -->
<alias>korean</alias>
</assoc>
<assoc ccsid="1364"/>
<assoc ccsid="1373"><!-- Windows-950 --></assoc>
<assoc ccsid="1375" mibenum="2101"><!-- Big5-HKSCS --></assoc>
<assoc ccsid="1380"><!-- Simplified Chinese DBCS PC --></assoc>
<assoc ccsid="1381"><!-- Simplified Chinese PC DATA Mixed --></assoc>
<assoc ccsid="1383" mibenum="2025"><!-- GB2312 -->
<alias>EUC-CN</alias>
</assoc>
<assoc ccsid="1386" mibenum="113"><!-- GBK --></assoc>
<assoc ccsid="1388"><!-- Simplified Chinese DBCS-Host DATA GBK mixed --></assoc>
<assoc ccsid="1392"><!-- S-ch PC Dara mixed GB18030 --></assoc>
<assoc ccsid="1399" />
<assoc ccsid="4396"><!-- Japanese Host DB including 1880 --></assoc>
<assoc ccsid="4948"><!-- Latin 2 PC DATA Multilingual --></assoc>
<assoc ccsid="4951"><!-- Cyrillic PC DATA Multilingual --></assoc>
<assoc ccsid="4952"><!-- Hebrew PC DATA --></assoc>
<assoc ccsid="4953"><!-- Turkey PC DATA Latin 5 --></assoc>
<assoc ccsid="4960"><!-- Arabic PC DATA --></assoc>
<assoc ccsid="4965"><!-- Greek PC DATA --></assoc>
<assoc ccsid="4971"/>
<assoc ccsid="5026"><!-- Japan Katakana (extended range) 1880 UDC --></assoc>
<assoc ccsid="5035"><!-- Japan English (extended range) 1880 UDC --></assoc>
<assoc ccsid="5050"><!-- G0 - JIS X201 Roman for CP 895; G1 JIS X208-1990 for CP 952 --></assoc>
<assoc ccsid="5052"><!-- JIS X201 Roman for CP 895; JIS X208-1983 for CP 952 --></assoc>
<assoc ccsid="5053"><!-- JIS X201 Roman for CP 895; JIS X208-1978 for CP 955 --></assoc>
<assoc ccsid="5054"><!-- ASCII for CP 367; JIS X208-1983 for CP 952 --></assoc>
<assoc ccsid="5055"><!-- ASCII for CP 367; JIS X208-1978 for CP 955 --></assoc>
<assoc ccsid="5354" mibenum="2258"><!-- windows-1258 --></assoc>
<assoc ccsid="5346" mibenum="2250"><!-- windows-1250 --></assoc>
<assoc ccsid="5347" mibenum="2251"><!-- windows-1251 --></assoc>
<assoc ccsid="5348" mibenum="2252"><!-- windows-1252 --></assoc>
<assoc ccsid="5349" mibenum="2253"><!-- windows-1253 --></assoc>
<assoc ccsid="5350" mibenum="2254"><!-- windows-1254 --></assoc>
<assoc ccsid="5123"/>
<assoc ccsid="5478" mibenum="57"><!-- GB_2312-80 -->
<alias>chinese</alias>
</assoc>
<assoc ccsid="8612"><!-- Arabic (base shapes only) --></assoc>
<assoc ccsid="9030"><!-- Thai Host Extended SBCS --></assoc>
<assoc ccsid="9056"><!-- PC DATA: Arabic PC Storage/Interchange --></assoc>
<assoc ccsid="9066"><!-- Thai PC DATA Extended SBCS --></assoc>
<assoc ccsid="9447" mibenum="2255"><!-- windows-1255 --></assoc>
<assoc ccsid="9448" mibenum="2256"><!-- windows-1256 --></assoc>
<assoc ccsid="9449" mibenum="2257"><!-- windows-1257 --></assoc>
<assoc ccsid="12708"/>
<assoc ccsid="13121"/>
<assoc ccsid="13124"/>
<assoc ccsid="13488" mibenum="1000"><!-- ISO-10646-UCS-2 -->
<alias>UCS-2</alias>
<alias>UCS2</alias>
</assoc>
<assoc ccsid="17354"><!-- G0 - ASCII for CP 00367; G1 -KSC X5601-1989 (including 188 UDCs) for --></assoc>
<assoc ccsid="25546"><!-- Korean 2022-KR TCP ASCII --></assoc>
<assoc ccsid="28709"><!-- Traditional Chinese (extended range) --></assoc>
<assoc ccsid="33722" mibenum="18"><!-- EUC-JP --></assoc>
<assoc ccsid="57345"><!-- All Japanese 2022 characters --></assoc>
<assoc ccsid="61952"><!-- AS/400 specific UCS level 2. --></assoc>
<assoc ccsid="62211"/>
<assoc ccsid="62224"/>
<assoc ccsid="62235"/>
<assoc ccsid="62245"/>
<assoc mibenum="27"><!-- ISO-10646-UTF-1 --></assoc>
</ccsid_mibenum>

3077
os400/iconv/bldcsndfa/character-sets.xhtml Normal file
View File

File diff suppressed because it is too large Load Diff

4609
os400/iconv/ianatables.c Normal file
View File

File diff suppressed because it is too large Load Diff

154
os400/iconv/iconv.c Normal file
View File

@ -0,0 +1,154 @@
/**
*** iconv_open(), iconv(), iconv_close() wrappers for the OS/400.
***
*** See Copyright for the status of this software.
***
*** Author: Patrick Monnerat <pm@datasphere.ch>, DATASPHERE S.A.
**/
#include <errno.h>
#include <stdio.h>
#include <stdlib.h>
#include "/QIBM/include/iconv.h" /* Force system definition. */
#define USE_SYSTEM_ICONV
#include "iconv.h" /* Use local definitions. */
/**
*** Bring-in the name-->CCSID mapping DFA tables.
**/
#include "ianatables.c"
static int
findEncoding(const unsigned char * * namep)
{
t_staterange curstate;
t_ccsid ccsid;
t_ccsid final;
t_transrange l;
t_transrange h;
const unsigned char * name;
/**
*** Get the CCSID correspong to the name at *`namep'.
*** If success, update pointer at `namep' to 1st byte after matched
*** name and return the CCSID.
*** If failure, set errno and return -1.
**/
if (!namep || !(name = *namep)) {
errno = EINVAL;
return -1;
}
curstate = 0;
final = 0;
for (;;) {
if (curstate < sizeof final_array / sizeof final_array[0])
if (final_array[curstate]) {
final = final_array[curstate];
*namep = name;
}
l = trans_array[curstate] - 1;
h = trans_array[curstate + 1];
do {
if (++l >= h) {
if (!final) {
errno = EINVAL;
return -1;
}
return final - 1;
}
} while (label_array[l] != *name);
curstate = goto_array[l];
name++;
}
/* NOTREACHED. */
}
static void
makeos400codename(char * buf, unsigned int ccsid)
{
ccsid &= 0xFFFF;
memset(buf, 0, 32);
sprintf(buf, "IBMCCSID%05u0000000", ccsid);
}
Iconv_t
IconvOpen(const char * tocode, const char * fromcode)
{
int toccsid = findEncoding(&tocode);
int fromccsid = findEncoding(&fromcode);
char fromibmccsid[33];
char toibmccsid[33];
iconv_t * cd;
if (toccsid < 0 || fromccsid < 0)
return (Iconv_t) -1;
makeos400codename(fromibmccsid, fromccsid);
makeos400codename(toibmccsid, toccsid);
memset(toibmccsid + 13, 0, sizeof toibmccsid - 13);
cd = (iconv_t *) malloc(sizeof *cd);
if (!cd)
return (Iconv_t) -1;
*cd = iconv_open(toibmccsid, fromibmccsid);
if (cd->return_value) {
free((char *) cd);
return (Iconv_t) -1;
}
return (Iconv_t) cd;
}
size_t
Iconv(Iconv_t cd, char * * inbuf, size_t * inbytesleft,
char * * outbuf, size_t * outbytesleft)
{
if (!cd || cd == (Iconv_t) -1) {
errno = EINVAL;
return (size_t) -1;
}
return iconv(*(iconv_t *) cd, inbuf, inbytesleft, outbuf, outbytesleft);
}
int
IconvClose(Iconv_t cd)
{
if (!cd || cd == (Iconv_t) -1) {
errno = EINVAL;
return -1;
}
if (iconv_close(*(iconv_t *) cd))
return -1;
free((char *) cd);
return 0;
}

40
os400/iconv/iconv.h Normal file
View File

@ -0,0 +1,40 @@
/**
*** Declarations for the iconv wrappers.
***
*** See Copyright for the status of this software.
***
*** Author: Patrick Monnerat <pm@datasphere.ch>, DATASPHERE S.A.
**/
#ifndef __ICONV_H_
#define __ICONV_H_
#ifdef __cplusplus
extern "C" {
#endif
#include <stddef.h> /* For size_t. */
typedef void * Iconv_t;
Iconv_t IconvOpen(const char * tocode, const char * fromcode);
size_t Iconv(Iconv_t cd, char * * inbuf, size_t * inbytesleft,
char * * outbuf, size_t * outbytesleft);
int IconvClose(Iconv_t cd);
#ifndef USE_SYSTEM_ICONV
#define iconv_t Iconv_t
#define iconv_open IconvOpen
#define iconv Iconv
#define iconv_close IconvClose
#endif
#ifdef __cplusplus
}
#endif
#endif