Bump to 3.7-beta1

diff --git a/ChangeLog b/ChangeLog
index cf44ac994545f355d59bcaad167fb26d9be115e9..bd0f43bb991f86a196d84dde634edd420adf31fd 100644 (file)
--- a/ChangeLog
+++ b/ChangeLog
@@ -6,6 +6,8 @@
        (AC_OUTPUT): Handle it.
        Reported by Bruno Haible.
 
+       * configure.ac: Version 3.7-beta1.
+
 2008-02-23  François Pinard  <pinard@iro.umontreal.ca>
 
        * configure.ac, Makefile.am: Handle python/.

diff --git a/NEWS b/NEWS
index af16194691c014d759ba550566f2a96ac0183859..34603500c3a7f82e58d11deef88fd3cf0253031d 100644 (file)
--- a/NEWS
+++ b/NEWS
@@ -1,273 +1,338 @@
-Free recode NEWS - User visible changes.       -*- outline -*- (allout)
-Copyright © 1993-1999, 2000, 2001 Free Software Foundation, Inc.
-
-* Version 3.6 - François Pinard, Bruno Haible, 2001-01.
-
-.* General changes
-. + The recode manual is now indexed, by charset, by concept, etc.
-. + Program messages are also available in Greek, Gallicean and Italian.
-. + Bruno Haible's nice portable iconv library has been integrated.
-. + RFC 1345 tables and French character names have been updated.
-. + The Texinfo charset has been refreshed, and made reversible.
-
-.* New charsets (most from libiconv)
-
-. + Japanese
-    EUC-JP (csEUCPkdFmtJapanese, EUC_JP,
-      Extended_UNIX_Code_Packed_Format_for_Japanese);
-    ISO-2022-JP (csISO2022JP); ISO-2022-JP-1; ISO-2022-JP-2 (csISO2022JP2);
-    JIS_C6220-1969-ro (csISO14JISC6220ro, ISO646-JP, iso-ir-14, jp);
-    JIS_X0201 (csHalfWidthKatakana, JIS0201, JISX0201-1976, JISX0201.1976-0,
-       X0201);
-    JIS_X0208 (csISO87JISX0208, ISO-IR-87, JIS0208, JIS_X0208.1983-0,
-       JIS_X0208.1983-1, JIS_X0208-1990-0, JIS_X0208.1983-1, X0208);
-    JIS_X0212 (csISO159JISX02121990, ISO-IR-159, JIS0212, JIS_X0212.1990-0,
-      JIS_X0212-1990, X0212);
-    SJIS (csShiftJIS, MS_KANJI, SHIFT-JIS).
+=======================================
+Free recode NEWS - User visible changes
+=======================================
+
+.. contents::
+.. sectnum::
+
+:Copyright: © 1993-1999, 2000, 2001, 2008 Free Software Foundation, Inc.
+
+Version 3.7-beta1
+=================
+
+:Author: François Pinard, 2008-02.
+
++ Changes are mostly internal, and correct reported bugs.
+
+Version 3.6
+===========
+
+:Author: François Pinard, Bruno Haible, 2001-01.
+
+General changes
+---------------
+
++ The recode manual is now indexed, by charset, by concept, etc.
++ Program messages are also available in Greek, Gallicean and Italian.
++ Bruno Haible's nice portable iconv library has been integrated.
++ RFC 1345 tables and French character names have been updated.
++ The Texinfo charset has been refreshed, and made reversible.
+
+New charsets
+------------
+
+(most from libiconv)
+
++ Japanese
+
+  + EUC-JP (csEUCPkdFmtJapanese, EUC_JP,
+    Extended_UNIX_Code_Packed_Format_for_Japanese);
+  + ISO-2022-JP (csISO2022JP); ISO-2022-JP-1; ISO-2022-JP-2 (csISO2022JP2);
+  + JIS_C6220-1969-ro (csISO14JISC6220ro, ISO646-JP, iso-ir-14, jp);
+  + JIS_X0201 (csHalfWidthKatakana, JIS0201, JISX0201-1976, JISX0201.1976-0,
+    X0201);
+  + JIS_X0208 (csISO87JISX0208, ISO-IR-87, JIS0208, JIS_X0208.1983-0,
+    JIS_X0208.1983-1, JIS_X0208-1990-0, JIS_X0208.1983-1, X0208);
+  + JIS_X0212 (csISO159JISX02121990, ISO-IR-159, JIS0212, JIS_X0212.1990-0,
+    JIS_X0212-1990, X0212);
+  + SJIS (csShiftJIS, MS_KANJI, SHIFT-JIS).
 
 . + Chinese
-    BIG5 (BIG-5, BIG-FIVE, BIGFIVE, CN-BIG5 csBig5); BIG5HKSCS;
-    EUC-CN (CN-GB, csGB2312, EUC_CN, GB2312); EUC-TW (csEUCTW, EUC_TW);
-    GB18030; HZ (HZ-GB-2312); ISO-2022-CN (csISO2022CN); ISO-2022-CN-EXT;
-    GB_1988-80 (cn, csISO57GB1988, ISO646-CN, iso-ir-57);
-    GB_2312-80 (CHINESE, csISO58GB231280, GB2312.1980-0, ISO-IR-58);
-    ISO-IR-165 (CN-GB-ISOIR165).
+
+  + BIG5 (BIG-5, BIG-FIVE, BIGFIVE, CN-BIG5 csBig5); BIG5HKSCS;
+  + EUC-CN (CN-GB, csGB2312, EUC_CN, GB2312); EUC-TW (csEUCTW, EUC_TW);
+  + GB18030; HZ (HZ-GB-2312); ISO-2022-CN (csISO2022CN); ISO-2022-CN-EXT;
+  + GB_1988-80 (cn, csISO57GB1988, ISO646-CN, iso-ir-57);
+  + GB_2312-80 (CHINESE, csISO58GB231280, GB2312.1980-0, ISO-IR-58);
+  + ISO-IR-165 (CN-GB-ISOIR165).
 
 . + Korean
-    JOHAB (CP1361); EUC-KR (csEUCKR, EUC_KR); GBK (CP936);
-    ISO-2022-KR (csISO2022KR);
-    KSC_5601 (CP949, csKSC56011987, ISO-IR-149, KOREAN, KSC5601.1987-0,
-      KS_C_5601-1987, KS_C_5601-1989, KSX1001:1992).
+
+  + JOHAB (CP1361); EUC-KR (csEUCKR, EUC_KR); GBK (CP936);
+  + ISO-2022-KR (csISO2022KR);
+  + KSC_5601 (CP949, csKSC56011987, ISO-IR-149, KOREAN, KSC5601.1987-0,
+    KS_C_5601-1987, KS_C_5601-1989, KSX1001:1992).
 
 . + Vietnamese (independently of libiconv)
-    TCVN; VIQR; VISCII; VNI; VPS.
+
+  + TCVN; VIQR; VISCII; VNI; VPS.
 
 . + Other languages
-    ARMSCII-8; Georgian-Academy; Georgian-PS; WINDOWS-874 (CP874);
-    MuleLao-1; CP1133 (IBM-CP1133); CP1258 (WINDOWS-1258);
-    TIS-620 (ISO-IR-166, TIS620, TIS620.2529-1, TIS620-0, TIS620.2533-0,
-      TIS620.2533-1).
+
+  + ARMSCII-8; Georgian-Academy; Georgian-PS; WINDOWS-874 (CP874);
+  + MuleLao-1; CP1133 (IBM-CP1133); CP1258 (WINDOWS-1258);
+  + TIS-620 (ISO-IR-166, TIS620, TIS620.2529-1, TIS620-0, TIS620.2533-0,
+    TIS620.2533-1).
 
 . + Apple specifics
-    MacArabic; MacCentralEurope; MacCroatian; MacCyrillic; MacGreek;
-    MacHebrew; MacIceland; MacRomania; MacThai; MacTurkish; MacUkraine
+
+  + MacArabic; MacCentralEurope; MacCroatian; MacCyrillic; MacGreek;
+  + MacHebrew; MacIceland; MacRomania; MacThai; MacTurkish; MacUkraine
 
 . + Unicode
-    JAVA; UCS-2-INTERNAL; UCS-2LE (UnicodeLITTLE); UCS-2-SWAPPED; UCS-4BE;
-    UCS-4-INTERNAL; UCS-4LE; UCS-4-SWAPPED; UTF-16BE; UTF-16LE.
+
+  + JAVA; UCS-2-INTERNAL; UCS-2LE (UnicodeLITTLE); UCS-2-SWAPPED; UCS-4BE;
+  + UCS-4-INTERNAL; UCS-4LE; UCS-4-SWAPPED; UTF-16BE; UTF-16LE.
 
 . + Others
-    CP932; CP949 (UHC); CP950; CP866 (866, csIBM866, IBM866).
-    ISO-8859-16 (ISO-IR-226, ISO_8859-16:2000).
+
+  + CP932; CP949 (UHC); CP950; CP866 (866, csIBM866, IBM866).
+  + ISO-8859-16 (ISO-IR-226, ISO_8859-16:2000).
 
 . + Recode internal
-    :libiconv: (:)   [so option -x: avoids going through libiconv]
-
-.* New aliases (from libiconv) [list to be revised]
-   csASCII (for ANSI_X3.4-1968); csHPRoman8 (for hp-roman8);
-   csISOLatin1 (for ISO-8859-1); csISOLatin2 (for ISO-8859-2);
-   csISOLatin3 (for ISO-8859-3); csISOLatin4 (for ISO-8859-4);
-   csISOLatin5 (for ISO-8859-9);
-   csISOLatin6 and ISO_8859-10:1992 (for ISO-8859-10);
-   csISOLatinArabic (for ISO-8859-6); csISOLatinCyrillic (for ISO-8859-5);
-   csISOLatinGreek (for ISO-8859-7); csISOLatinHebrew (for ISO-8859-8);
-   csKOI8R (for KOI8-R); csPC850Multilingual (for IBM850);
-   csUCS4 (for ISO-10646-UCS-4);
-   csUnicode, csUnicode11, UCS-2BE, UnicodeBIG (for ISO-10646-UCS-2);
-   csUnicode11UTF7 (for UNICODE-1-1-UTF-7);
-   csVISCII and VISCII1.1-1 (for VISCII);
-   ISO-IR-179 (for ISO-8859-13); csMacintosh and MacRoman (for macintosh);
-   TCVN5712-1, TCVN5712-1:1993 and TCVN-5712 (for TCVN).
-
-.* New surfaces
-   tree (experimental).
-
-* Version 3.5 - François Pinard, 1999-05.
-
-.* Incompatible changes
-. + A double dot `..' should now be used instead of a colon `:'.
-. + Option --force (-f) is needed to pursue recoding despite errors.
-. + There is no more quoting for special characters within charsets names.
-. + Auto check (`-a') and popen (`-o') options have been withdrawn.
-. + Some charsets and aliases were deleted, see `Charsets & aliases' below.
-
-.* Extended features
-. + Program messages are available in localised form for many languages.
-. + Long character names are available in French, if LANGUAGE is set to `fr'.
-. + A new request syntax allows for recode chaining, and for surfaces.
-. + Option --header-file (-h) accepts a language parameter, and Perl is new.
-. + Full charset listings now show the UCS-2 value for characters.
-. + Option --known=PAIRS (-k) also accepts octal and hexadecimal numbers.
-. + Option --list (-l) better sorts charsets and aliases, also fully written.
-. + Charset `RFC1345' implements mnemonic+ascii+38, and is now reversible.
-. + HTML is not limited anymore to Latin-1, HTML 4.0 entities are supported.
-
-.* New features
-. + Euro support.
-. + Updated RFC 1345 set of tables, from Keld Simonsen.
-. + Some African charsets and transliterated forms.
-. + Conversions for ISO 10646 and Unicode.
-. + Combining or explosion of UCS-2 diacriticized characters and ligatures.
-. + Implementation of surfaces, see `Surfaces & aliases' below.
-. + Mixed mode for recoding only comments and strings in C sources or PO files.
-. + A stand-alone recoding library gets installed, often as a shared library.
-. + Option --find-subsets (-T) lists charsets which are subsets of another.
-. + The library may generate testing data, and study character frequencies.
-
-.* Charsets & aliases
-
-. + New ISO 10646 and Unicode charsets
-.  - combined-UCS-2: pseudo-charset.
-.  - count-characters: pseudo-charset.
-.  - dump-with-names: pseudo-charset.
-.  - ISO-10646-UCS-2 (UNICODE-1-1, BMP, rune, u2).
-.  - ISO-10646-UCS-4 (10646, ISO-10646, UCS-4, u4).
-.  - UNICODE-1-1-UTF-7 (TF-7, u7).
-.  - UTF-8 (UTF-2, UTF-FSS, FSS_UTF, TF-8, u8).
-.  - UTF-16 (Unicode, TF-16, u6).
-
-. + RFC 1345.bis matters
-.  - Deleted charsets
-     dk-us, us-dk (because of &duplicate which `recode' does not handle yet).
-.  - New charsets
-     baltic (alias is iso-ir-179); CP1250 (1250, ms-ee, windows-1250);
-     CP1251 (1251, ms-cyrl, windows-1251);
-     CP1252 (1252, ms-ansi, windows-1252);
-     CP1253 (1253, ms-greek, windows-1253);
-     CP1254 (1254, ms-turk, windows-1254);
-     CP1255 (1255, ms-hebr, windows-1255);
-     CP1256 (1256, ms-arab, windows-1256);
-     CP1257 (1257, WinBaltRim, windows-1257);
-     CWI (CWI-2, cp-hu); EBCDIC-IS-FRISS (friss);
-     GOST_19768-87 with aliases of previous GOST_19768-74;
-     IBM256 (256, CP256, EBCDIC-INT1); IBM875 (875, CP875, EBCDIC-Greek);
-     IBM1004 (1004, CP1004, os2latin1); IBM1047 (1047, CP1047);
-     ISO-8859-13 (ISO_8859-13:1998, iso-baltic, iso-ir-179a, l7, latin7);
-     ISO-8859-14 (ISO_8859-14:1998, iso-celtic, iso-ir-199, l8, latin8);
-     ISO-8859-15 (ISO_8859-15:1998, iso-ir-203, l9, latin9);
-     KOI-7; KOI-8 (GOST_19768-74); KOI8-R; KOI8-RU; KOI8-U;
-     macintosh_ce (macce); mac-is;
-     NeXTSTEP (next) yet previous `recode' had it outside RFC 1345.
-.  - Alias promoted to charset (with previous charset becoming alias)
-     ISO-646.basic (with ISO-646.basic:1983); ISO-646.irv (ISO-646.irv:1983);
-     ISO_5427-ext (ISO_5427:1981); ISO_5428 (ISO_5428:1980);
-     ISO-8859-1 (ISO_8859-1:1987); ISO-8859-2 (ISO_8859-2:1987);
-     ISO-8859-3 (ISO_8859-3:1988); ISO-8859-4 (ISO_8859-4:1988);
-     ISO-8859-5 (ISO_8859-5:1988); ISO-8859-6 (ISO_8859-6:1987);
-     ISO-8859-7 (ISO_8859-7:1987); ISO-8859-8 (ISO_8859-8:1988);
-     ISO-8859-9 (ISO_8859-9:1989); ISO-8859-10 (latin6);
-     NC_NC00-10 (NC_NC00-10:81); sami (latin-lap).
-.  - New aliases
-     037 (for charset IBM037); 038 (IBM038); 273 (IBM273); 274 (IBM274);
-     275 (IBM275); 278 (IBM278); 280 (IBM280); 281 (IBM281); 284 (IBM284);
-     285 (IBM285); 290 (IBM290); 297 (IBM297); 367 (ANSI_X3.4-1968);
-     420 (IBM420); 423 (IBM423); 424 (IBM424); 500, 500V1 (IBM500);
-     819 (ISO-8859-1); 864 (IBM864); 868 (IBM868); 870 (IBM870);
-     871 (IBM871); 880 (IBM880); 891 (IBM891); 903 (IBM903); 905 (IBM905);
-     912, CP912, IBM912 (ISO-8859-2); 918 (IBM918); 1026 (IBM1026);
-     ECMA-113, ECMA-113:1986 (ECMA-Cyrillic); GOST_19768-74 (KOI8);
-     ISO_8859-N (ISO-8859-N) for N = 1 through 10 and 13 through 15;
-     ISO_8859-10:1993 (ISO-8869-10); iso-ir-170 (INVARIANT);
-     KOI8_L2 (CSN_369103); pclatin2, pcl2 (IBM852); SS636127 (SEN_850200_B).
-
-. + New African charsets
-    AFRL1-101-BPI_OCIL (t-francais, t-fra);
-    AFRFUL-102-BPI_OCIL (bambara, bra, ewondo, fulfulde);
-    AFRFUL-103-BPI_OCIL (t-bambara, t-bra, t-ewondo, t-fulfulde);
-    AFRLIN-104-BPI_OCIL (lingala, lin, sango, wolof);
-    AFRLIN-105-BPI_OCIL (t-lingala, t-lin, t-sango, t-wolof).
-
-. + Extra miscellaneous charsets
-     KEYBCS2 (Kamenicky); CORK (T1); KOI-8_CS2.
-
-. + New HTML pseudo-charsets
-    HTML_1.1 (h1);  HTML_2.0 (RFC 1866, 1866, h2); HTML-i18n (RFC 2070);
-    HTML_3.2 (h3) reimplemented; HTML_4.0 (h4, HTML, h);
-    deleted aliases HTF, 8859, ISO 8859, Entities, SGML, WWW, w3.
-
-.* Surfaces & aliases
-   Base64 (64, b64); Quoted-Printable (qp, Quote-Printable);
-   21-Permutation (swabytes); 4321-Permutation; CR; CR-LF (cl);
-   Decimal-1 (d, d1); Decimal-2 (d2), Decimal-4 (d4);
-   Hexadecimal-1 (x, x1); Hexadecimal-2 (x2); Hexadecimal-4 (x4);
-   Octal-1 (o, o1); Octal-2 (o2); Octal-4 (o4).
-   data; test7; test8; test15; test16.
-
-* Version 3.4 - François Pinard, 1994-11.
-
-.* Charset HTML is new, it handles `&...;' sequences for Latin-1.
-.* Charset AtariST handling is more general, --list may be used with it.
-.* Charset ASCII-BS overstriking has been extended, mainly for German.
-.* Charset RFC1345 may be a goal, to debug or study RFC 1345 short names.
-.* Charset names have been revised.  Note that nextstep is now NeXT.
-.* Option --force (-f) is accepted, but does not yet protect reversibility.
-.* Option --quiet or --silent (-q) silences irreversible recoding messages.
-.* Option --known=PAIRS (-k) helps searching through recodings.
-.* Option --sequence=pipe (-p) does not fall back on -o anymore.
-.* Option --auto-check may narrow its study around one particular charset.
-.* An MSDOS port is available, check ftp.iro.umontreal.ca in pub/gnuish.
-.* Compilation should now succeed on OS/2 EMX.  Thanks to Kai Uwe Rommel.
-.* Program initialization is almost three times faster on average.
-.* Corrected reported bugs, added small improvements, some aesthetic.
-
-* Version 3.3 - François Pinard, 1993-12.
-
-.* Charsets atarist, ebcdic-ccc, ebcdic-ibm and nextstep have been added.
-.* Also, most RFC 1345 charsets and aliases are handled.  That's a bunch!
-.* Old ascii disappears because of RFC 1345's ascii, use ascii-bs instead.
-.* Old maci disappears because of RFC 1345's macintosh, use applemac instead.
-.* Charsets cccascii and cdcascii disappear, use ebcdic-ccc and ebcdic instead.
-.* Recoding between latin1, ibmpc and applemac is (almost) reversible.
-.* The texinfo documentation has been reorganized, this to be continued.
-.* Long options are accepted, charset names may be abbreviated.
-.* Option --list (-l) displays charsets, aliases and contents in many formats.
-.* Option --strict (-s) asks for stricter, non-reversible recodings.
-.* Option --graphics (-g) approximates ibmpc rulers with ASCII graphics.
-.* Option --header (-h) produces C source for many recoding tables.
-.* Option --auto-check (-a) reports about all possible recodings.
-.* Option --ignore (-x) prevents a charset from being selected.
-.* Execution has been sped up through step merging, hashing for charset names.
-.* Many various buglets have been eradicated, portability increased.
-.* Charsets may be edited out by modifying the Makefile only.
-.* Configuration is made through the use of an external config.h file.
-
-* Version 3.2.4 - François Pinard, 1992-10.
-
-.* None.
-
-* Version 3.2.3 - François Pinard, 1992-09.
-
-.* New -d `diacritics_only' option for LaTeX.
-.* A few bugs have been corrected.
-.* Documentation reorganization and improvements.
-.* Increased portability, now uses Autoconf.
-.* A few bugs solved.
-
-* Version 3.2 - François Pinard, 1991-10.
-
-.* MSDOS port redone.
-.* New check goal at installation time.
-.* Add -v option for verbose processing, remove old -q.
-.* Add -i, -o and -p for letting the user control the strategy.
-.* A few bugs corrected.
-.* Embedded NULs should now be transmitted.
-
-* Version 3.1 - François Pinard, 1990-03.
-
-.* Rename -V to -C for showing Copyright.
-.* Calling sequence changed, said files now recoded on themselves.
-.* Add -t option for touching files.
-.* Better on-line help.
-
-* Version 3.0.1 - François Pinard, 1990-02.
-
-.* Add -q option for quiet processing.
-.* Executable file now considerably smaller, also speedier.
-.* A few bugs corrected.
-
-* Version 3.0 - François Pinard, 1989-10.
-
-.* New Text to Latin1 processing, should be faster.
-.* A few bugs corrected.
-
-* For prior history down to 1980, see at the end of the ChangeLog.
+
+  + :libiconv: (:)   [so option -x: avoids going through libiconv]
+
+New aliases
+-----------
+
+(from libiconv) [list to be revised]
+
++ csASCII (for ANSI_X3.4-1968); csHPRoman8 (for hp-roman8);
++ csISOLatin1 (for ISO-8859-1); csISOLatin2 (for ISO-8859-2);
++ csISOLatin3 (for ISO-8859-3); csISOLatin4 (for ISO-8859-4);
++ csISOLatin5 (for ISO-8859-9);
++ csISOLatin6 and ISO_8859-10:1992 (for ISO-8859-10);
++ csISOLatinArabic (for ISO-8859-6); csISOLatinCyrillic (for ISO-8859-5);
++ csISOLatinGreek (for ISO-8859-7); csISOLatinHebrew (for ISO-8859-8);
++ csKOI8R (for KOI8-R); csPC850Multilingual (for IBM850);
++ csUCS4 (for ISO-10646-UCS-4);
++ csUnicode, csUnicode11, UCS-2BE, UnicodeBIG (for ISO-10646-UCS-2);
++ csUnicode11UTF7 (for UNICODE-1-1-UTF-7);
++ csVISCII and VISCII1.1-1 (for VISCII);
++ ISO-IR-179 (for ISO-8859-13); csMacintosh and MacRoman (for macintosh);
++ TCVN5712-1, TCVN5712-1:1993 and TCVN-5712 (for TCVN).
+
+New surfaces
+------------
+
++ tree (experimental).
+
+Version 3.5
+===========
+
+:Author: François Pinard, 1999-05.
+
+Incompatible changes
+--------------------
+
++ A double dot `..' should now be used instead of a colon `:'.
++ Option --force (-f) is needed to pursue recoding despite errors.
++ There is no more quoting for special characters within charsets names.
++ Auto check (`-a') and popen (`-o') options have been withdrawn.
++ Some charsets and aliases were deleted, see `Charsets & aliases' below.
+
+Extended features
+-----------------
+
++ Program messages are available in localised form for many languages.
++ Long character names are available in French, if LANGUAGE is set to `fr'.
++ A new request syntax allows for recode chaining, and for surfaces.
++ Option --header-file (-h) accepts a language parameter, and Perl is new.
++ Full charset listings now show the UCS-2 value for characters.
++ Option --known=PAIRS (-k) also accepts octal and hexadecimal numbers.
++ Option --list (-l) better sorts charsets and aliases, also fully written.
++ Charset `RFC1345' implements mnemonic+ascii+38, and is now reversible.
++ HTML is not limited anymore to Latin-1, HTML 4.0 entities are supported.
+
+New features
+------------
+
++ Euro support.
++ Updated RFC 1345 set of tables, from Keld Simonsen.
++ Some African charsets and transliterated forms.
++ Conversions for ISO 10646 and Unicode.
++ Combining or explosion of UCS-2 diacriticized characters and ligatures.
++ Implementation of surfaces, see `Surfaces & aliases' below.
++ Mixed mode for recoding only comments and strings in C sources or PO files.
++ A stand-alone recoding library gets installed, often as a shared library.
++ Option --find-subsets (-T) lists charsets which are subsets of another.
++ The library may generate testing data, and study character frequencies.
+
+Charsets & aliases
+------------------
+
++ New ISO 10646 and Unicode charsets
+
+  + combined-UCS-2: pseudo-charset.
+  + count-characters: pseudo-charset.
+  + dump-with-names: pseudo-charset.
+  + ISO-10646-UCS-2 (UNICODE-1-1, BMP, rune, u2).
+  + ISO-10646-UCS-4 (10646, ISO-10646, UCS-4, u4).
+  + UNICODE-1-1-UTF-7 (TF-7, u7).
+  + UTF-8 (UTF-2, UTF-FSS, FSS_UTF, TF-8, u8).
+  + UTF-16 (Unicode, TF-16, u6).
+
++ RFC 1345.bis matters
+
+  + Deleted charsets
+
+    + dk-us, us-dk (because of &duplicate which `recode' does not handle yet).
+
+  + New charsets
+
+    + baltic (alias is iso-ir-179); CP1250 (1250, ms-ee, windows-1250);
+    + CP1251 (1251, ms-cyrl, windows-1251);
+    + CP1252 (1252, ms-ansi, windows-1252);
+    + CP1253 (1253, ms-greek, windows-1253);
+    + CP1254 (1254, ms-turk, windows-1254);
+    + CP1255 (1255, ms-hebr, windows-1255);
+    + CP1256 (1256, ms-arab, windows-1256);
+    + CP1257 (1257, WinBaltRim, windows-1257);
+    + CWI (CWI-2, cp-hu); EBCDIC-IS-FRISS (friss);
+    + GOST_19768-87 with aliases of previous GOST_19768-74;
+    + IBM256 (256, CP256, EBCDIC-INT1); IBM875 (875, CP875, EBCDIC-Greek);
+    + IBM1004 (1004, CP1004, os2latin1); IBM1047 (1047, CP1047);
+    + ISO-8859-13 (ISO_8859-13:1998, iso-baltic, iso-ir-179a, l7, latin7);
+    + ISO-8859-14 (ISO_8859-14:1998, iso-celtic, iso-ir-199, l8, latin8);
+    + ISO-8859-15 (ISO_8859-15:1998, iso-ir-203, l9, latin9);
+    + KOI-7; KOI-8 (GOST_19768-74); KOI8-R; KOI8-RU; KOI8-U;
+    + macintosh_ce (macce); mac-is;
+    + NeXTSTEP (next) yet previous `recode' had it outside RFC 1345.
+
+  + Alias promoted to charset (with previous charset becoming alias)
+
+    + ISO-646.basic (with ISO-646.basic:1983); ISO-646.irv (ISO-646.irv:1983);
+    + ISO_5427-ext (ISO_5427:1981); ISO_5428 (ISO_5428:1980);
+    + ISO-8859-1 (ISO_8859-1:1987); ISO-8859-2 (ISO_8859-2:1987);
+    + ISO-8859-3 (ISO_8859-3:1988); ISO-8859-4 (ISO_8859-4:1988);
+    + ISO-8859-5 (ISO_8859-5:1988); ISO-8859-6 (ISO_8859-6:1987);
+    + ISO-8859-7 (ISO_8859-7:1987); ISO-8859-8 (ISO_8859-8:1988);
+    + ISO-8859-9 (ISO_8859-9:1989); ISO-8859-10 (latin6);
+    + NC_NC00-10 (NC_NC00-10:81); sami (latin-lap).
+
+  + New aliases
+
+    + 037 (for charset IBM037); 038 (IBM038); 273 (IBM273); 274 (IBM274);
+    + 275 (IBM275); 278 (IBM278); 280 (IBM280); 281 (IBM281); 284 (IBM284);
+    + 285 (IBM285); 290 (IBM290); 297 (IBM297); 367 (ANSI_X3.4-1968);
+    + 420 (IBM420); 423 (IBM423); 424 (IBM424); 500, 500V1 (IBM500);
+    + 819 (ISO-8859-1); 864 (IBM864); 868 (IBM868); 870 (IBM870);
+    + 871 (IBM871); 880 (IBM880); 891 (IBM891); 903 (IBM903); 905 (IBM905);
+    + 912, CP912, IBM912 (ISO-8859-2); 918 (IBM918); 1026 (IBM1026);
+    + ECMA-113, ECMA-113:1986 (ECMA-Cyrillic); GOST_19768-74 (KOI8);
+    + ISO_8859-N (ISO-8859-N) for N = 1 through 10 and 13 through 15;
+    + ISO_8859-10:1993 (ISO-8869-10); iso-ir-170 (INVARIANT);
+    + KOI8_L2 (CSN_369103); pclatin2, pcl2 (IBM852); SS636127 (SEN_850200_B).
+
++ New African charsets
+
+  + AFRL1-101-BPI_OCIL (t-francais, t-fra);
+  + AFRFUL-102-BPI_OCIL (bambara, bra, ewondo, fulfulde);
+  + AFRFUL-103-BPI_OCIL (t-bambara, t-bra, t-ewondo, t-fulfulde);
+  + AFRLIN-104-BPI_OCIL (lingala, lin, sango, wolof);
+  + AFRLIN-105-BPI_OCIL (t-lingala, t-lin, t-sango, t-wolof).
+
++ Extra miscellaneous charsets
+
+  + KEYBCS2 (Kamenicky); CORK (T1); KOI-8_CS2.
+
++ New HTML pseudo-charsets
+
+  + HTML_1.1 (h1);  HTML_2.0 (RFC 1866, 1866, h2); HTML-i18n (RFC 2070);
+  + HTML_3.2 (h3) reimplemented; HTML_4.0 (h4, HTML, h);
+  + deleted aliases HTF, 8859, ISO 8859, Entities, SGML, WWW, w3.
+
+Surfaces & aliases
+------------------
+
++ Base64 (64, b64); Quoted-Printable (qp, Quote-Printable);
++ 21-Permutation (swabytes); 4321-Permutation; CR; CR-LF (cl);
++ Decimal-1 (d, d1); Decimal-2 (d2), Decimal-4 (d4);
++ Hexadecimal-1 (x, x1); Hexadecimal-2 (x2); Hexadecimal-4 (x4);
++ Octal-1 (o, o1); Octal-2 (o2); Octal-4 (o4).
++ data; test7; test8; test15; test16.
+
+Version 3.4
+===========
+
+:Author: François Pinard, 1994-11.
+
++ Charset HTML is new, it handles `&...;' sequences for Latin-1.
++ Charset AtariST handling is more general, --list may be used with it.
++ Charset ASCII-BS overstriking has been extended, mainly for German.
++ Charset RFC1345 may be a goal, to debug or study RFC 1345 short names.
++ Charset names have been revised.  Note that nextstep is now NeXT.
++ Option --force (-f) is accepted, but does not yet protect reversibility.
++ Option --quiet or --silent (-q) silences irreversible recoding messages.
++ Option --known=PAIRS (-k) helps searching through recodings.
++ Option --sequence=pipe (-p) does not fall back on -o anymore.
++ Option --auto-check may narrow its study around one particular charset.
++ An MSDOS port is available, check ftp.iro.umontreal.ca in pub/gnuish.
++ Compilation should now succeed on OS/2 EMX.  Thanks to Kai Uwe Rommel.
++ Program initialization is almost three times faster on average.
++ Corrected reported bugs, added small improvements, some aesthetic.
+
+Version 3.3
+===========
+
+:Author: François Pinard, 1993-12.
+
++ Charsets atarist, ebcdic-ccc, ebcdic-ibm and nextstep have been added.
++ Also, most RFC 1345 charsets and aliases are handled.  That's a bunch!
++ Old ascii disappears because of RFC 1345's ascii, use ascii-bs instead.
++ Old maci disappears because of RFC 1345's macintosh, use applemac instead.
++ Charsets cccascii and cdcascii disappear, use ebcdic-ccc and ebcdic instead.
++ Recoding between latin1, ibmpc and applemac is (almost) reversible.
++ The texinfo documentation has been reorganized, this to be continued.
++ Long options are accepted, charset names may be abbreviated.
++ Option --list (-l) displays charsets, aliases and contents in many formats.
++ Option --strict (-s) asks for stricter, non-reversible recodings.
++ Option --graphics (-g) approximates ibmpc rulers with ASCII graphics.
++ Option --header (-h) produces C source for many recoding tables.
++ Option --auto-check (-a) reports about all possible recodings.
++ Option --ignore (-x) prevents a charset from being selected.
++ Execution has been sped up through step merging, hashing for charset names.
++ Many various buglets have been eradicated, portability increased.
++ Charsets may be edited out by modifying the Makefile only.
++ Configuration is made through the use of an external config.h file.
++ New -d `diacritics_only' option for LaTeX.
++ A few bugs have been corrected.
++ Documentation reorganization and improvements.
++ Increased portability, now uses Autoconf.
++ A few bugs solved.
+
+Version 3.2
+===========
+
+:Author: François Pinard, 1991-10.
+
++ MSDOS port redone.
++ New check goal at installation time.
++ Add -v option for verbose processing, remove old -q.
++ Add -i, -o and -p for letting the user control the strategy.
++ A few bugs corrected.
++ Embedded NULs should now be transmitted.
+
+Version 3.1
+===========
+
+:Author: François Pinard, 1990-03.
+
++ Rename -V to -C for showing Copyright.
++ Calling sequence changed, said files now recoded on themselves.
++ Add -t option for touching files.
++ Better on-line help.
++ Add -q option for quiet processing.
++ Executable file now considerably smaller, also speedier.
++ A few bugs corrected.
+
+Version 3.0
+===========
+
+:Author: François Pinard, 1989-10.
+
++ New Text to Latin1 processing, should be faster.
++ A few bugs corrected.
+
+For prior history down to 1980, see at the end of the ChangeLog.

diff --git a/README b/README
index f2685512601af1c036f6b4857ebc2629796ebba8..46214c4f6448517e0f31a1e33d78d98f4a55601c 100644 (file)
--- a/README
+++ b/README
@@ -113,6 +113,37 @@ least, new features go to Recodec only.
 
 __ http://recodec.progiciels-bpi.ca
 
+Notes for version 3.7-beta1
+---------------------------
+
+The beta 1 pre-test release for the incoming Recode 3.7 has been made
+available for those needing it right away.  While it solves some serious
+bugs and portability problems, others are meant to be addressed only in
+later pre-tests.  In particular, none of charset or surface issues, user
+requests, and various suggestions appear in this pre-test, and will not
+either in later pretests, until all real show-stoppers are solved first.
+So this is in no way a candidate for a Recode 3.7 release.
+
+The test suite is worth more comments:
+
++ The suite is very partial, and may not be thought as a validation
+  suite.  Before it could be used to ascertain confidence, it would need,
+  much more tests than it has already.
+
++ Testing is notably more speedy than it used to be.  For example, the
+  previous :code:`bigauto` test, which was not run by default because it
+  ran for too long, is now executed within the standard test suite, once
+  in non-strict mode, and a second time in strict mode.
+
++ It does not use Autotest anymore, but rather a home grown test driver
+  much inspired from the Codespeak project.  The link between the test and
+  the Recode library is established through a Pyrex interface, so you need
+  to have :code:`python` and :code:`python-devel` installed first.
+
++ Beware that the Pyrex interface to the Recode library is only meant
+  for testing. for now at least.  While you may play with it, it would not
+  be wise relying on it, as the specifications might change at any time.
+
 Installation
 ============
 

diff --git a/configure b/configure
index f2d07c89bf8e61b6c56104a8614eddad8f1b13a3..806bdf6c29f161ac25125747c7b21af9a0d8bf52 100755 (executable)
--- a/configure
+++ b/configure
@@ -2290,7 +2290,7 @@ fi
 
 # Define the identity of the package.
  PACKAGE=recode
- VERSION=3.6
+ VERSION=3.7-beta1
 
 
 cat >>confdefs.h <<_ACEOF

diff --git a/configure.ac b/configure.ac
index 4095f20b742a36ca4023a6c969ae4348bdc60047..ebfba51e8ffa64f1d21c0dc1da9f6d5e1f36625b 100644 (file)
--- a/configure.ac
+++ b/configure.ac
@@ -5,7 +5,7 @@
 AC_INIT(src/recode.c)
 AC_PREREQ(2.12)
 AM_CONFIG_HEADER(config.h)
-AM_INIT_AUTOMAKE(recode, 3.6)
+AM_INIT_AUTOMAKE(recode, 3.7-beta1)
 
 AC_PROG_CC
 AC_AIX

diff --git a/doc/recode.info b/doc/recode.info
index e85caa37bd9810ecd9b37c225bfa9d0de5dc4ece..3c6e031575e3330b911c5f61da1104e621b02a7e 100644 (file)
--- a/doc/recode.info
+++ b/doc/recode.info
@@ -29,100 +29,100 @@ translation approved by the Foundation.
 \1f
 Indirect:
 recode.info-1: 1138
-recode.info-2: 244435
+recode.info-2: 244441
 \1f
 Tag Table:
 (Indirect)
 Node: Top\7f1138
-Node: Tutorial\7f5541
-Node: Introduction\7f9778
-Node: Charset overview\7f14017
-Node: Surface overview\7f15812
-Node: Contributing\7f17284
-Ref: Contributing-Footnote-1\7f19530
-Node: Invoking recode\7f19664
-Node: Synopsis\7f20621
-Ref: Synopsis-Footnote-1\7f23063
-Node: Requests\7f23362
-Ref: Requests-Footnote-1\7f29276
-Ref: Requests-Footnote-2\7f29343
-Ref: Requests-Footnote-3\7f29521
-Node: Listings\7f29980
-Ref: Listings-Footnote-1\7f40398
-Node: Recoding\7f40725
-Node: Reversibility\7f43550
-Ref: Reversibility-Footnote-1\7f52053
-Node: Sequencing\7f52190
-Node: Mixed\7f54636
-Node: Emacs\7f58029
-Node: Debugging\7f59008
-Node: Library\7f63275
-Node: Outer level\7f64629
-Node: Request level\7f70115
-Node: Task level\7f80584
-Node: Charset level\7f91006
-Node: Errors\7f91848
-Ref: Errors-Footnote-1\7f96702
-Ref: Errors-Footnote-2\7f96816
-Node: Universal\7f97177
-Ref: Universal-Footnote-1\7f100305
-Ref: Universal-Footnote-2\7f100373
-Node: UCS-2\7f100586
-Node: UCS-4\7f103120
-Node: UTF-7\7f103662
-Node: UTF-8\7f104259
-Node: UTF-16\7f108566
-Node: count-characters\7f109716
-Node: dump-with-names\7f110389
-Node: libiconv\7f112942
-Node: Tabular\7f124499
-Node: ASCII misc\7f146765
-Node: ASCII\7f147131
-Node: ISO 8859\7f147951
-Node: ASCII-BS\7f150249
-Node: flat\7f152088
-Node: IBM and MS\7f152761
-Node: EBCDIC\7f153334
-Node: IBM-PC\7f155448
-Ref: IBM-PC-Footnote-1\7f157570
-Node: Icon-QNX\7f157729
-Node: CDC\7f158156
-Node: Display Code\7f159860
-Ref: Display Code-Footnote-1\7f162144
-Node: CDC-NOS\7f162349
-Node: Bang-Bang\7f164313
-Node: Micros\7f166244
-Node: Apple-Mac\7f166629
-Node: AtariST\7f168685
-Node: Miscellaneous\7f169675
-Node: HTML\7f170412
-Node: LaTeX\7f176440
-Node: Texinfo\7f177216
-Node: Vietnamese\7f177996
-Node: African\7f178976
-Node: Others\7f180332
-Node: Texte\7f181790
-Ref: Texte-Footnote-1\7f186345
-Ref: Texte-Footnote-2\7f186425
-Ref: Texte-Footnote-3\7f186900
-Node: Mule\7f186997
-Ref: Mule-Footnote-1\7f188784
-Node: Surfaces\7f189303
-Ref: Surfaces-Footnote-1\7f192291
-Node: Permutations\7f192397
-Node: End lines\7f193242
-Node: MIME\7f195449
-Node: Dump\7f196640
-Node: Test\7f200834
-Node: Internals\7f203314
-Node: Main flow\7f204552
-Node: New charsets\7f207672
-Node: New surfaces\7f212215
-Node: Design\7f212943
-Ref: Design-Footnote-1\7f222158
-Node: Concept Index\7f222262
-Node: Option Index\7f237005
-Node: Library Index\7f239858
-Node: Charset and Surface Index\7f244435
+Node: Tutorial\7f5547
+Node: Introduction\7f9784
+Node: Charset overview\7f14023
+Node: Surface overview\7f15818
+Node: Contributing\7f17290
+Ref: Contributing-Footnote-1\7f19536
+Node: Invoking recode\7f19670
+Node: Synopsis\7f20627
+Ref: Synopsis-Footnote-1\7f23069
+Node: Requests\7f23368
+Ref: Requests-Footnote-1\7f29282
+Ref: Requests-Footnote-2\7f29349
+Ref: Requests-Footnote-3\7f29527
+Node: Listings\7f29986
+Ref: Listings-Footnote-1\7f40404
+Node: Recoding\7f40731
+Node: Reversibility\7f43556
+Ref: Reversibility-Footnote-1\7f52059
+Node: Sequencing\7f52196
+Node: Mixed\7f54642
+Node: Emacs\7f58035
+Node: Debugging\7f59014
+Node: Library\7f63281
+Node: Outer level\7f64635
+Node: Request level\7f70121
+Node: Task level\7f80590
+Node: Charset level\7f91012
+Node: Errors\7f91854
+Ref: Errors-Footnote-1\7f96708
+Ref: Errors-Footnote-2\7f96822
+Node: Universal\7f97183
+Ref: Universal-Footnote-1\7f100311
+Ref: Universal-Footnote-2\7f100379
+Node: UCS-2\7f100592
+Node: UCS-4\7f103126
+Node: UTF-7\7f103668
+Node: UTF-8\7f104265
+Node: UTF-16\7f108572
+Node: count-characters\7f109722
+Node: dump-with-names\7f110395
+Node: libiconv\7f112948
+Node: Tabular\7f124505
+Node: ASCII misc\7f146771
+Node: ASCII\7f147137
+Node: ISO 8859\7f147957
+Node: ASCII-BS\7f150255
+Node: flat\7f152094
+Node: IBM and MS\7f152767
+Node: EBCDIC\7f153340
+Node: IBM-PC\7f155454
+Ref: IBM-PC-Footnote-1\7f157576
+Node: Icon-QNX\7f157735
+Node: CDC\7f158162
+Node: Display Code\7f159866
+Ref: Display Code-Footnote-1\7f162150
+Node: CDC-NOS\7f162355
+Node: Bang-Bang\7f164319
+Node: Micros\7f166250
+Node: Apple-Mac\7f166635
+Node: AtariST\7f168691
+Node: Miscellaneous\7f169681
+Node: HTML\7f170418
+Node: LaTeX\7f176446
+Node: Texinfo\7f177222
+Node: Vietnamese\7f178002
+Node: African\7f178982
+Node: Others\7f180338
+Node: Texte\7f181796
+Ref: Texte-Footnote-1\7f186351
+Ref: Texte-Footnote-2\7f186431
+Ref: Texte-Footnote-3\7f186906
+Node: Mule\7f187003
+Ref: Mule-Footnote-1\7f188790
+Node: Surfaces\7f189309
+Ref: Surfaces-Footnote-1\7f192297
+Node: Permutations\7f192403
+Node: End lines\7f193248
+Node: MIME\7f195455
+Node: Dump\7f196646
+Node: Test\7f200840
+Node: Internals\7f203320
+Node: Main flow\7f204558
+Node: New charsets\7f207678
+Node: New surfaces\7f212221
+Node: Design\7f212949
+Ref: Design-Footnote-1\7f222164
+Node: Concept Index\7f222268
+Node: Option Index\7f237011
+Node: Library Index\7f239864
+Node: Charset and Surface Index\7f244441
 \1f
 End Tag Table

diff --git a/doc/recode.info-1 b/doc/recode.info-1
index 3e8c5549525e723b2c1a02c078af782bb974baef..2119663ce4ceffdd6c9c3c3a0d462c928ea0c43e 100644 (file)
--- a/doc/recode.info-1
+++ b/doc/recode.info-1
@@ -40,7 +40,7 @@ sets and is able to convert files between almost any pair.  Most
 RFC 1345 character sets, and all `libiconv' character sets, are
 supported.  The `recode' program is a handy front-end to the library.
 
-   The current `recode' release is 3.6.
+   The current `recode' release is 3.7-beta1.
 
 * Menu:
 

diff --git a/doc/stamp-vti b/doc/stamp-vti
index ed841a5946f3136632f6809033ab4ac7cd458d2e..f6293d8a67b76a5857901c769a980086c03ec850 100644 (file)
--- a/doc/stamp-vti
+++ b/doc/stamp-vti
@@ -1,4 +1,4 @@
 @set UPDATED 27 February 2008
 @set UPDATED-MONTH February 2008
-@set EDITION 3.6
-@set VERSION 3.6
+@set EDITION 3.7-beta1
+@set VERSION 3.7-beta1

diff --git a/doc/version.texi b/doc/version.texi
index ed841a5946f3136632f6809033ab4ac7cd458d2e..f6293d8a67b76a5857901c769a980086c03ec850 100644 (file)
--- a/doc/version.texi
+++ b/doc/version.texi
@@ -1,4 +1,4 @@
 @set UPDATED 27 February 2008
 @set UPDATED-MONTH February 2008
-@set EDITION 3.6
-@set VERSION 3.6
+@set EDITION 3.7-beta1
+@set VERSION 3.7-beta1

diff --git a/src/main.c b/src/main.c
index adfa6d59589925b79609feed2ead9c325ada64e2..e167921d1972aeb7b2312d4d7ab69c9a5e8aae83 100644 (file)
--- a/src/main.c
+++ b/src/main.c
@@ -622,7 +622,7 @@ Written by Franc,ois Pinard <pinard@iro.umontreal.ca>.\n"),
             stdout);
       fputs (_("\
 \n\
-Copyright (C) 1990, 92, 93, 94, 96, 97, 99 Free Software Foundation, Inc.\n"),
+Copyright (C) 1990, 92-94, 96, 97, 99, 08 Free Software Foundation, Inc.\n"),
             stdout);
       fputs (_("\
 This is free software; see the source for copying conditions.  There is NO\n\

diff --git a/src/recode.1 b/src/recode.1
index 43fea6cf61677ae941a9651a4f66a5136ee84d52..bbcebbffcb7ad37f1439d2f29c5616d200e7731e 100644 (file)
--- a/src/recode.1
+++ b/src/recode.1
@@ -1,5 +1,5 @@
 .\" DO NOT MODIFY THIS FILE!  It was generated by help2man 1.35.
-.TH RECODE "1" "February 2008" "recode 3.6" "User Commands"
+.TH RECODE "1" "February 2008" "recode 3.7-beta1" "User Commands"
 .SH NAME
 recode \- converts files between character sets
 .SH SYNOPSIS
@@ -100,7 +100,7 @@ Written by Franc,ois Pinard <pinard@iro.umontreal.ca>.
 .SH "REPORTING BUGS"
 Report bugs to <recode\-bugs@iro.umontreal.ca>.
 .SH COPYRIGHT
-Copyright \(co 1990, 92, 93, 94, 96, 97, 99 Free Software Foundation, Inc.
+Copyright \(co 1990, 92-94, 96, 97, 99, 08 Free Software Foundation, Inc.
 .br
 This is free software; see the source for copying conditions.  There is NO
 warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.