diff options
| author | Bruce Momjian | 2005-03-07 04:30:55 +0000 |
|---|---|---|
| committer | Bruce Momjian | 2005-03-07 04:30:55 +0000 |
| commit | deb77a6d58a39e0c39780cb8abd41fd4c7d18c33 (patch) | |
| tree | c441e03beaa982acb147edd825cc71f80d4a16d2 | |
| parent | fb4c2ddece10ed2cab31e8e7ddcfa87d5bc53e8d (diff) | |
Rename canonical encodings, per Peter:
UNICODE => UTF8
ALT => WIN866
WIN => WIN1251
TCVN => WIN1258
The old codes continue to work.
60 files changed, 900 insertions, 965 deletions
diff --git a/doc/README.mb.jp b/doc/README.mb.jp index 6cb15c8883..7cafb2426e 100644 --- a/doc/README.mb.jp +++ b/doc/README.mb.jp @@ -299,7 +299,7 @@ o set client_encoding $B%3%^%s%I$r;H$&J}K!(B PostgreSQL$B$N(BCONVERT$B$H5!G=$O$[$H$s$IF1$8$G$9$,!$8F$S=P$77A<0$,0[$j$^(B $B$9!%(B - SELECT convert(text using euc_jp_to_utf_8) FROM unicode_tbl; + SELECT convert(text using euc_jp_to_utf8) FROM unicode_tbl; "using" $B$N8e$N0z?t$O!V%3%s%P!<%8%g%sL>!W$G$9!%$3$NNc$G$O!$(BEUC_JP $B$+(B $B$i(B UTF-8 $B$KJQ49$9$k%3%s%P!<%8%g%s$r;XDj$7$F$$$^$9!%Dj5A:Q$N%3%s%P!<(B @@ -215,7 +215,7 @@ Multi-Language Support * Optimize locale to have minimal performance impact when not used * Support multiple simultaneous character sets, per SQL92 -* Improve Unicode combined character handling (?) +* Improve UTF8 combined character handling (?) * Add octet_length_server() and octet_length_client() * Make octet_length_client() the same as octet_length()? diff --git a/doc/src/sgml/charset.sgml b/doc/src/sgml/charset.sgml index c6e9694918..2b420a2407 100644 --- a/doc/src/sgml/charset.sgml +++ b/doc/src/sgml/charset.sgml @@ -285,7 +285,7 @@ initdb --locale=sv_SE allows you to store text in a variety of character sets, including single-byte character sets such as the ISO 8859 series and multiple-byte character sets such as <acronym>EUC</> (Extended Unix - Code), Unicode, and Mule internal code. All character sets can be + Code), UTF8, and Mule internal code. All character sets can be used transparently throughout the server. (If you use extension functions from other sources, it depends on whether they wrote their code correctly.) The default character set is selected while @@ -339,8 +339,8 @@ initdb --locale=sv_SE <entry>Taiwan <acronym>EUC</acronym></entry> </row> <row> - <entry><literal>UNICODE</literal></entry> - <entry>Unicode (<acronym>UTF</acronym>-8)</entry> + <entry><literal>UTF8</literal></entry> + <entry>UTF-8 (Unicode, 8-bit)</entry> </row> <row> <entry><literal>MULE_INTERNAL</literal></entry> @@ -407,7 +407,7 @@ initdb --locale=sv_SE <entry><acronym>KOI</acronym>8-R(U)</entry> </row> <row> - <entry><literal>ALT</literal></entry> + <entry><literal>WIN866</literal></entry> <entry>Windows CP866</entry> </row> <row> @@ -419,7 +419,7 @@ initdb --locale=sv_SE <entry>Windows CP1250</entry> </row> <row> - <entry><literal>WIN</literal></entry> + <entry><literal>WIN1251</literal></entry> <entry>Windows CP1251</entry> </row> <row> @@ -427,8 +427,8 @@ initdb --locale=sv_SE <entry>Windows CP1256 (Arabic)</entry> </row> <row> - <entry><literal>TCVN</literal></entry> - <entry><acronym>TCVN</>-5712/Windows CP1258 (Vietnamese)</entry> + <entry><literal>WIN1258</literal></entry> + <entry>Windows CP1258 (Vietnamese)/<acronym>TCVN</>-5712</entry> </row> </tbody> </tgroup> @@ -504,7 +504,7 @@ $ <userinput>psql -l</userinput> regression | t-ishii | SQL_ASCII template1 | t-ishii | EUC_JP test | t-ishii | EUC_JP - unicode | t-ishii | UNICODE + utf8 | t-ishii | UTF8 (9 rows) </screen> </para> @@ -561,126 +561,126 @@ $ <userinput>psql -l</userinput> <tbody> <row> <entry><literal>SQL_ASCII</literal></entry> - <entry><literal>SQL_ASCII</literal>, <literal>UNICODE</literal>, <literal>MULE_INTERNAL</literal> + <entry><literal>SQL_ASCII</literal>, <literal>UTF8</literal>, <literal>MULE_INTERNAL</literal> </entry> </row> <row> <entry><literal>EUC_JP</literal></entry> <entry><literal>EUC_JP</literal>, <literal>SJIS</literal>, - <literal>UNICODE</literal>, <literal>MULE_INTERNAL</literal> + <literal>UTF8</literal>, <literal>MULE_INTERNAL</literal> </entry> </row> <row> <entry><literal>EUC_CN</literal></entry> - <entry><literal>EUC_CN</literal>, <literal>UNICODE</literal>, <literal>MULE_INTERNAL</literal> + <entry><literal>EUC_CN</literal>, <literal>UTF8</literal>, <literal>MULE_INTERNAL</literal> </entry> </row> <row> <entry><literal>EUC_KR</literal></entry> - <entry><literal>EUC_KR</literal>, <literal>UNICODE</literal>, <literal>MULE_INTERNAL</literal> + <entry><literal>EUC_KR</literal>, <literal>UTF8</literal>, <literal>MULE_INTERNAL</literal> </entry> </row> <row> <entry><literal>JOHAB</literal></entry> - <entry><literal>JOHAB</literal>, <literal>UNICODE</literal> + <entry><literal>JOHAB</literal>, <literal>UTF8</literal> </entry> </row> <row> <entry><literal>EUC_TW</literal></entry> <entry><literal>EUC_TW</literal>, <literal>BIG5</literal>, - <literal>UNICODE</literal>, <literal>MULE_INTERNAL</literal> + <literal>UTF8</literal>, <literal>MULE_INTERNAL</literal> </entry> </row> <row> <entry><literal>LATIN1</literal></entry> - <entry><literal>LATIN1</literal>, <literal>UNICODE</literal> + <entry><literal>LATIN1</literal>, <literal>UTF8</literal> <literal>MULE_INTERNAL</literal> </entry> </row> <row> <entry><literal>LATIN2</literal></entry> <entry><literal>LATIN2</literal>, <literal>WIN1250</literal>, - <literal>UNICODE</literal>, + <literal>UTF8</literal>, <literal>MULE_INTERNAL</literal> </entry> </row> <row> <entry><literal>LATIN3</literal></entry> - <entry><literal>LATIN3</literal>, <literal>UNICODE</literal>, + <entry><literal>LATIN3</literal>, <literal>UTF8</literal>, <literal>MULE_INTERNAL</literal> </entry> </row> <row> <entry><literal>LATIN4</literal></entry> - <entry><literal>LATIN4</literal>, <literal>UNICODE</literal>, + <entry><literal>LATIN4</literal>, <literal>UTF8</literal>, <literal>MULE_INTERNAL</literal> </entry> </row> <row> <entry><literal>LATIN5</literal></entry> - <entry><literal>LATIN5</literal>, <literal>UNICODE</literal> + <entry><literal>LATIN5</literal>, <literal>UTF8</literal> </entry> </row> <row> <entry><literal>LATIN6</literal></entry> - <entry><literal>LATIN6</literal>, <literal>UNICODE</literal>, + <entry><literal>LATIN6</literal>, <literal>UTF8</literal>, <literal>MULE_INTERNAL</literal> </entry> </row> <row> <entry><literal>LATIN7</literal></entry> - <entry><literal>LATIN7</literal>, <literal>UNICODE</literal>, + <entry><literal>LATIN7</literal>, <literal>UTF8</literal>, <literal>MULE_INTERNAL</literal> </entry> </row> <row> <entry><literal>LATIN8</literal></entry> - <entry><literal>LATIN8</literal>, <literal>UNICODE</literal>, + <entry><literal>LATIN8</literal>, <literal>UTF8</literal>, <literal>MULE_INTERNAL</literal> </entry> </row> <row> <entry><literal>LATIN9</literal></entry> - <entry><literal>LATIN9</literal>, <literal>UNICODE</literal>, + <entry><literal>LATIN9</literal>, <literal>UTF8</literal>, <literal>MULE_INTERNAL</literal> </entry> </row> <row> <entry><literal>LATIN10</literal></entry> - <entry><literal>LATIN10</literal>, <literal>UNICODE</literal>, + <entry><literal>LATIN10</literal>, <literal>UTF8</literal>, <literal>MULE_INTERNAL</literal> </entry> </row> <row> <entry><literal>ISO_8859_5</literal></entry> <entry><literal>ISO_8859_5</literal>, - <literal>UNICODE</literal>, + <literal>UTF8</literal>, <literal>MULE_INTERNAL</literal>, - <literal>WIN</literal>, - <literal>ALT</literal>, + <literal>WIN1251</literal>, + <literal>WIN866</literal>, <literal>KOI8</literal> </entry> </row> <row> <entry><literal>ISO_8859_6</literal></entry> <entry><literal>ISO_8859_6</literal>, - <literal>UNICODE</literal> + <literal>UTF8</literal> </entry> </row> <row> <entry><literal>ISO_8859_7</literal></entry> <entry><literal>ISO_8859_7</literal>, - <literal>UNICODE</literal> + <literal>UTF8</literal> </entry> </row> <row> <entry><literal>ISO_8859_8</literal></entry> <entry><literal>ISO_8859_8</literal>, - <literal>UNICODE</literal> + <literal>UTF8</literal> </entry> </row> <row> - <entry><literal>UNICODE</literal></entry> + <entry><literal>UTF8</literal></entry> <entry> <literal>EUC_JP</literal>, <literal>SJIS</literal>, <literal>EUC_KR</literal>, <literal>UHC</literal>, <literal>JOHAB</literal>, @@ -691,10 +691,10 @@ $ <userinput>psql -l</userinput> <literal>ISO_8859_6</literal>, <literal>ISO_8859_7</literal>, <literal>ISO_8859_8</literal>, - <literal>WIN</literal>, <literal>ALT</literal>, + <literal>WIN1251</literal>, <literal>WIN866</literal>, <literal>KOI8</literal>, <literal>WIN1256</literal>, - <literal>TCVN</literal>, + <literal>WIN1258</literal>, <literal>WIN874</literal>, <literal>GB18030</literal>, <literal>WIN1250</literal> @@ -704,53 +704,53 @@ $ <userinput>psql -l</userinput> <entry><literal>MULE_INTERNAL</literal></entry> <entry><literal>EUC_JP</literal>, <literal>SJIS</literal>, <literal>EUC_KR</literal>, <literal>EUC_CN</literal>, <literal>EUC_TW</literal>, <literal>BIG5</literal>, <literal>LATIN1</literal> to <literal>LATIN5</literal>, - <literal>WIN</literal>, <literal>ALT</literal>, + <literal>WIN1251</literal>, <literal>WIN866</literal>, <literal>WIN1250</literal>, <literal>BIG5</literal>, <literal>ISO_8859_5</literal>, <literal>KOI8</literal></entry> </row> <row> <entry><literal>KOI8</literal></entry> - <entry><literal>ISO_8859_5</literal>, <literal>WIN</literal>, - <literal>ALT</literal>, <literal>KOI8</literal>, - <literal>UNICODE</literal>, <literal>MULE_INTERNAL</literal> + <entry><literal>ISO_8859_5</literal>, <literal>WIN1251</literal>, + <literal>WIN866</literal>, <literal>KOI8</literal>, + <literal>UTF8</literal>, <literal>MULE_INTERNAL</literal> </entry> </row> <row> - <entry><literal>ALT</literal></entry> - <entry><literal>ISO_8859_5</literal>, <literal>WIN</literal>, - <literal>ALT</literal>, <literal>KOI8</literal>, - <literal>UNICODE</literal>, <literal>MULE_INTERNAL</literal> + <entry><literal>WIN866</literal></entry> + <entry><literal>ISO_8859_5</literal>, <literal>WIN1251</literal>, + <literal>WIN866</literal>, <literal>KOI8</literal>, + <literal>UTF8</literal>, <literal>MULE_INTERNAL</literal> </entry> </row> <row> <entry><literal>WIN874</literal></entry> <entry><literal>WIN874</literal>, - <literal>UNICODE</literal> + <literal>UTF8</literal> </entry> </row> <row> <entry><literal>WIN1250</literal></entry> <entry><literal>LATIN2</literal>, <literal>WIN1250</literal>, - <literal>UNICODE</literal>, <literal>MULE_INTERNAL</literal> + <literal>UTF8</literal>, <literal>MULE_INTERNAL</literal> </entry> </row> <row> - <entry><literal>WIN</literal></entry> - <entry><literal>ISO_8859_5</literal>, <literal>WIN</literal>, - <literal>ALT</literal>, <literal>KOI8</literal>, - <literal>UNICODE</literal>, <literal>MULE_INTERNAL</literal> + <entry><literal>WIN1251</literal></entry> + <entry><literal>ISO_8859_5</literal>, <literal>WIN1251</literal>, + <literal>WIN866</literal>, <literal>KOI8</literal>, + <literal>UTF8</literal>, <literal>MULE_INTERNAL</literal> </entry> </row> <row> <entry><literal>WIN1256</literal></entry> <entry><literal>WIN1256</literal>, - <literal>UNICODE</literal> + <literal>UTF8</literal> </entry> </row> <row> - <entry><literal>TCVN</literal></entry> - <entry><literal>TCVN</literal>, - <literal>UNICODE</literal> + <entry><literal>WIN1258</literal></entry> + <entry><literal>WIN1258</literal>, + <literal>UTF8</literal> </entry> </row> </tbody> diff --git a/doc/src/sgml/func.sgml b/doc/src/sgml/func.sgml index 25c64d6f2a..016d615533 100644 --- a/doc/src/sgml/func.sgml +++ b/doc/src/sgml/func.sgml @@ -933,8 +933,8 @@ PostgreSQL documentation linkend="conversion-names"> for available conversion names. </entry> - <entry><literal>convert('PostgreSQL' using iso_8859_1_to_utf_8)</literal></entry> - <entry><literal>'PostgreSQL'</literal> in Unicode (UTF-8) encoding</entry> + <entry><literal>convert('PostgreSQL' using iso_8859_1_to_utf8)</literal></entry> + <entry><literal>'PostgreSQL'</literal> in UTF8 (Unicode, 8-bit) encoding</entry> </row> <row> @@ -1105,8 +1105,8 @@ PostgreSQL documentation <parameter>src_encoding</parameter> is omitted, database encoding is assumed. </entry> - <entry><literal>convert( 'text_in_unicode', 'UNICODE', 'LATIN1')</literal></entry> - <entry><literal>text_in_unicode</literal> represented in ISO 8859-1 encoding</entry> + <entry><literal>convert( 'text_in_utf8', 'UTF8', 'LATIN1')</literal></entry> + <entry><literal>text_in_utf8</literal> represented in ISO 8859-1 encoding</entry> </row> <row> @@ -1421,9 +1421,9 @@ PostgreSQL documentation </row> <row> - <entry><literal>ascii_to_utf_8</literal></entry> + <entry><literal>ascii_to_utf8</literal></entry> <entry><literal>SQL_ASCII</literal></entry> - <entry><literal>UNICODE</literal></entry> + <entry><literal>UTF8</literal></entry> </row> <row> @@ -1439,9 +1439,9 @@ PostgreSQL documentation </row> <row> - <entry><literal>big5_to_utf_8</literal></entry> + <entry><literal>big5_to_utf8</literal></entry> <entry><literal>BIG5</literal></entry> - <entry><literal>UNICODE</literal></entry> + <entry><literal>UTF8</literal></entry> </row> <row> @@ -1451,9 +1451,9 @@ PostgreSQL documentation </row> <row> - <entry><literal>euc_cn_to_utf_8</literal></entry> + <entry><literal>euc_cn_to_utf8</literal></entry> <entry><literal>EUC_CN</literal></entry> - <entry><literal>UNICODE</literal></entry> + <entry><literal>UTF8</literal></entry> </row> <row> @@ -1469,9 +1469,9 @@ PostgreSQL documentation </row> <row> - <entry><literal>euc_jp_to_utf_8</literal></entry> + <entry><literal>euc_jp_to_utf8</literal></entry> <entry><literal>EUC_JP</literal></entry> - <entry><literal>UNICODE</literal></entry> + <entry><literal>UTF8</literal></entry> </row> <row> @@ -1481,9 +1481,9 @@ PostgreSQL documentation </row> <row> - <entry><literal>euc_kr_to_utf_8</literal></entry> + <entry><literal>euc_kr_to_utf8</literal></entry> <entry><literal>EUC_KR</literal></entry> - <entry><literal>UNICODE</literal></entry> + <entry><literal>UTF8</literal></entry> </row> <row> @@ -1499,51 +1499,51 @@ PostgreSQL documentation </row> <row> - <entry><literal>euc_tw_to_utf_8</literal></entry> + <entry><literal>euc_tw_to_utf8</literal></entry> <entry><literal>EUC_TW</literal></entry> - <entry><literal>UNICODE</literal></entry> + <entry><literal>UTF8</literal></entry> </row> <row> - <entry><literal>gb18030_to_utf_8</literal></entry> + <entry><literal>gb18030_to_utf8</literal></entry> <entry><literal>GB18030</literal></entry> - <entry><literal>UNICODE</literal></entry> + <entry><literal>UTF8</literal></entry> </row> <row> - <entry><literal>gbk_to_utf_8</literal></entry> + <entry><literal>gbk_to_utf8</literal></entry> <entry><literal>GBK</literal></entry> - <entry><literal>UNICODE</literal></entry> + <entry><literal>UTF8</literal></entry> </row> <row> - <entry><literal>iso_8859_10_to_utf_8</literal></entry> + <entry><literal>iso_8859_10_to_utf8</literal></entry> <entry><literal>LATIN6</literal></entry> - <entry><literal>UNICODE</literal></entry> + <entry><literal>UTF8</literal></entry> </row> <row> - <entry><literal>iso_8859_13_to_utf_8</literal></entry> + <entry><literal>iso_8859_13_to_utf8</literal></entry> <entry><literal>LATIN7</literal></entry> - <entry><literal>UNICODE</literal></entry> + <entry><literal>UTF8</literal></entry> </row> <row> - <entry><literal>iso_8859_14_to_utf_8</literal></entry> + <entry><literal>iso_8859_14_to_utf8</literal></entry> <entry><literal>LATIN8</literal></entry> - <entry><literal>UNICODE</literal></entry> + <entry><literal>UTF8</literal></entry> </row> <row> - <entry><literal>iso_8859_15_to_utf_8</literal></entry> + <entry><literal>iso_8859_15_to_utf8</literal></entry> <entry><literal>LATIN9</literal></entry> - <entry><literal>UNICODE</literal></entry> + <entry><literal>UTF8</literal></entry> </row> <row> - <entry><literal>iso_8859_16_to_utf_8</literal></entry> + <entry><literal>iso_8859_16_to_utf8</literal></entry> <entry><literal>LATIN10</literal></entry> - <entry><literal>UNICODE</literal></entry> + <entry><literal>UTF8</literal></entry> </row> <row> @@ -1553,9 +1553,9 @@ PostgreSQL documentation </row> <row> - <entry><literal>iso_8859_1_to_utf_8</literal></entry> + <entry><literal>iso_8859_1_to_utf8</literal></entry> <entry><literal>LATIN1</literal></entry> - <entry><literal>UNICODE</literal></entry> + <entry><literal>UTF8</literal></entry> </row> <row> @@ -1565,9 +1565,9 @@ PostgreSQL documentation </row> <row> - <entry><literal>iso_8859_2_to_utf_8</literal></entry> + <entry><literal>iso_8859_2_to_utf8</literal></entry> <entry><literal>LATIN2</literal></entry> - <entry><literal>UNICODE</literal></entry> + <entry><literal>UTF8</literal></entry> </row> <row> @@ -1583,9 +1583,9 @@ PostgreSQL documentation </row> <row> - <entry><literal>iso_8859_3_to_utf_8</literal></entry> + <entry><literal>iso_8859_3_to_utf8</literal></entry> <entry><literal>LATIN3</literal></entry> - <entry><literal>UNICODE</literal></entry> + <entry><literal>UTF8</literal></entry> </row> <row> @@ -1595,9 +1595,9 @@ PostgreSQL documentation </row> <row> - <entry><literal>iso_8859_4_to_utf_8</literal></entry> + <entry><literal>iso_8859_4_to_utf8</literal></entry> <entry><literal>LATIN4</literal></entry> - <entry><literal>UNICODE</literal></entry> + <entry><literal>UTF8</literal></entry> </row> <row> @@ -1613,51 +1613,51 @@ PostgreSQL documentation </row> <row> - <entry><literal>iso_8859_5_to_utf_8</literal></entry> + <entry><literal>iso_8859_5_to_utf8</literal></entry> <entry><literal>ISO_8859_5</literal></entry> - <entry><literal>UNICODE</literal></entry> + <entry><literal>UTF8</literal></entry> </row> <row> <entry><literal>iso_8859_5_to_windows_1251</literal></entry> <entry><literal>ISO_8859_5</literal></entry> - <entry><literal>WIN</literal></entry> + <entry><literal>WIN1251</literal></entry> </row> <row> <entry><literal>iso_8859_5_to_windows_866</literal></entry> <entry><literal>ISO_8859_5</literal></entry> - <entry><literal>ALT</literal></entry> + <entry><literal>WIN866</literal></entry> </row> <row> - <entry><literal>iso_8859_6_to_utf_8</literal></entry> + <entry><literal>iso_8859_6_to_utf8</literal></entry> <entry><literal>ISO_8859_6</literal></entry> - <entry><literal>UNICODE</literal></entry> + <entry><literal>UTF8</literal></entry> </row> <row> - <entry><literal>iso_8859_7_to_utf_8</literal></entry> + <entry><literal>iso_8859_7_to_utf8</literal></entry> <entry><literal>ISO_8859_7</literal></entry> - <entry><literal>UNICODE</literal></entry> + <entry><literal>UTF8</literal></entry> </row> <row> - <entry><literal>iso_8859_8_to_utf_8</literal></entry> + <entry><literal>iso_8859_8_to_utf8</literal></entry> <entry><literal>ISO_8859_8</literal></entry> - <entry><literal>UNICODE</literal></entry> + <entry><literal>UTF8</literal></entry> </row> <row> - <entry><literal>iso_8859_9_to_utf_8</literal></entry> + <entry><literal>iso_8859_9_to_utf8</literal></entry> <entry><literal>LATIN5</literal></entry> - <entry><literal>UNICODE</literal></entry> + <entry><literal>UTF8</literal></entry> </row> <row> - <entry><literal>johab_to_utf_8</literal></entry> + <entry><literal>johab_to_utf8</literal></entry> <entry><literal>JOHAB</literal></entry> - <entry><literal>UNICODE</literal></entry> + <entry><literal>UTF8</literal></entry> </row> <row> @@ -1673,21 +1673,21 @@ PostgreSQL documentation </row> <row> - <entry><literal>koi8_r_to_utf_8</literal></entry> + <entry><literal>koi8_r_to_utf8</literal></entry> <entry><literal>KOI8</literal></entry> - <entry><literal>UNICODE</literal></entry> + <entry><literal>UTF8</literal></entry> </row> <row> <entry><literal>koi8_r_to_windows_1251</literal></entry> <entry><literal>KOI8</literal></entry> - <entry><literal>WIN</literal></entry> + <entry><literal>WIN1251</literal></entry> </row> <row> <entry><literal>koi8_r_to_windows_866</literal></entry> <entry><literal>KOI8</literal></entry> - <entry><literal>ALT</literal></entry> + <entry><literal>WIN866</literal></entry> </row> <row> @@ -1777,13 +1777,13 @@ PostgreSQL documentation <row> <entry><literal>mic_to_windows_1251</literal></entry> <entry><literal>MULE_INTERNAL</literal></entry> - <entry><literal>WIN</literal></entry> + <entry><literal>WIN1251</literal></entry> </row> <row> <entry><literal>mic_to_windows_866</literal></entry> <entry><literal>MULE_INTERNAL</literal></entry> - <entry><literal>ALT</literal></entry> + <entry><literal>WIN866</literal></entry> </row> <row> @@ -1799,212 +1799,212 @@ PostgreSQL documentation </row> <row> - <entry><literal>sjis_to_utf_8</literal></entry> + <entry><literal>sjis_to_utf8</literal></entry> <entry><literal>SJIS</literal></entry> - <entry><literal>UNICODE</literal></entry> + <entry><literal>UTF8</literal></entry> </row> <row> - <entry><literal>tcvn_to_utf_8</literal></entry> - <entry><literal>TCVN</literal></entry> - <entry><literal>UNICODE</literal></entry> + <entry><literal>tcvn_to_utf8</literal></entry> + <entry><literal>WIN1258</literal></entry> + <entry><literal>UTF8</literal></entry> </row> <row> - <entry><literal>uhc_to_utf_8</literal></entry> + <entry><literal>uhc_to_utf8</literal></entry> <entry><literal>UHC</literal></entry> - <entry><literal>UNICODE</literal></entry> + <entry><literal>UTF8</literal></entry> </row> <row> - <entry><literal>utf_8_to_ascii</literal></entry> - <entry><literal>UNICODE</literal></entry> + <entry><literal>utf8_to_ascii</literal></entry> + <entry><literal>UTF8</literal></entry> <entry><literal>SQL_ASCII</literal></entry> </row> <row> - <entry><literal>utf_8_to_big5</literal></entry> - <entry><literal>UNICODE</literal></entry> + <entry><literal>utf8_to_big5</literal></entry> + <entry><literal>UTF8</literal></entry> <entry><literal>BIG5</literal></entry> </row> <row> - <entry><literal>utf_8_to_euc_cn</literal></entry> - <entry><literal>UNICODE</literal></entry> + <entry><literal>utf8_to_euc_cn</literal></entry> + <entry><literal>UTF8</literal></entry> <entry><literal>EUC_CN</literal></entry> </row> <row> - <entry><literal>utf_8_to_euc_jp</literal></entry> - <entry><literal>UNICODE</literal></entry> + <entry><literal>utf8_to_euc_jp</literal></entry> + <entry><literal>UTF8</literal></entry> <entry><literal>EUC_JP</literal></entry> </row> <row> - <entry><literal>utf_8_to_euc_kr</literal></entry> - <entry><literal>UNICODE</literal></entry> + <entry><literal>utf8_to_euc_kr</literal></entry> + <entry><literal>UTF8</literal></entry> <entry><literal>EUC_KR</literal></entry> </row> <row> - <entry><literal>utf_8_to_euc_tw</literal></entry> - <entry><literal>UNICODE</literal></entry> + <entry><literal>utf8_to_euc_tw</literal></entry> + <entry><literal>UTF8</literal></entry> <entry><literal>EUC_TW</literal></entry> </row> <row> - <entry><literal>utf_8_to_gb18030</literal></entry> - <entry><literal>UNICODE</literal></entry> + <entry><literal>utf8_to_gb18030</literal></entry> + <entry><literal>UTF8</literal></entry> <entry><literal>GB18030</literal></entry> </row> <row> - <entry><literal>utf_8_to_gbk</literal></entry> - <entry><literal>UNICODE</literal></entry> + <entry><literal>utf8_to_gbk</literal></entry> + <entry><literal>UTF8</literal></entry> <entry><literal>GBK</literal></entry> </row> <row> - <entry><literal>utf_8_to_iso_8859_1</literal></entry> - <entry><literal>UNICODE</literal></entry> + <entry><literal>utf8_to_iso_8859_1</literal></entry> + <entry><literal>UTF8</literal></entry> <entry><literal>LATIN1</literal></entry> </row> <row> - <entry><literal>utf_8_to_iso_8859_10</literal></entry> - <entry><literal>UNICODE</literal></entry> + <entry><literal>utf8_to_iso_8859_10</literal></entry> + <entry><literal>UTF8</literal></entry> <entry><literal>LATIN6</literal></entry> </row> <row> - <entry><literal>utf_8_to_iso_8859_13</literal></entry> - <entry><literal>UNICODE</literal></entry> + <entry><literal>utf8_to_iso_8859_13</literal></entry> + <entry><literal>UTF8</literal></entry> <entry><literal>LATIN7</literal></entry> </row> <row> - <entry><literal>utf_8_to_iso_8859_14</literal></entry> - <entry><literal>UNICODE</literal></entry> + <entry><literal>utf8_to_iso_8859_14</literal></entry> + <entry><literal>UTF8</literal></entry> <entry><literal>LATIN8</literal></entry> </row> <row> - <entry><literal>utf_8_to_iso_8859_15</literal></entry> - <entry><literal>UNICODE</literal></entry> + <entry><literal>utf8_to_iso_8859_15</literal></entry> + <entry><literal>UTF8</literal></entry> <entry><literal>LATIN9</literal></entry> </row> <row> - <entry><literal>utf_8_to_iso_8859_16</literal></entry> - <entry><literal>UNICODE</literal></entry> + <entry><literal>utf8_to_iso_8859_16</literal></entry> + <entry><literal>UTF8</literal></entry> <entry><literal>LATIN10</literal></entry> </row> <row> - <entry><literal>utf_8_to_iso_8859_2</literal></entry> - <entry><literal>UNICODE</literal></entry> + <entry><literal>utf8_to_iso_8859_2</literal></entry> + <entry><literal>UTF8</literal></entry> <entry><literal>LATIN2</literal></entry> </row> <row> - <entry><literal>utf_8_to_iso_8859_3</literal></entry> - <entry><literal>UNICODE</literal></entry> + <entry><literal>utf8_to_iso_8859_3</literal></entry> + <entry><literal>UTF8</literal></entry> <entry><literal>LATIN3</literal></entry> </row> <row> - <entry><literal>utf_8_to_iso_8859_4</literal></entry> - <entry><literal>UNICODE</literal></entry> + <entry><literal>utf8_to_iso_8859_4</literal></entry> + <entry><literal>UTF8</literal></entry> <entry><literal>LATIN4</literal></entry> </row> <row> - <entry><literal>utf_8_to_iso_8859_5</literal></entry> - <entry><literal>UNICODE</literal></entry> + <entry><literal>utf8_to_iso_8859_5</literal></entry> + <entry><literal>UTF8</literal></entry> <entry><literal>ISO_8859_5</literal></entry> </row> <row> - <entry><literal>utf_8_to_iso_8859_6</literal></entry> - <entry><literal>UNICODE</literal></entry> + <entry><literal>utf8_to_iso_8859_6</literal></entry> + <entry><literal>UTF8</literal></entry> <entry><literal>ISO_8859_6</literal></entry> </row> <row> - <entry><literal>utf_8_to_iso_8859_7</literal></entry> - <entry><literal>UNICODE</literal></entry> + <entry><literal>utf8_to_iso_8859_7</literal></entry> + <entry><literal>UTF8</literal></entry> <entry><literal>ISO_8859_7</literal></entry> </row> <row> - <entry><literal>utf_8_to_iso_8859_8</literal></entry> - <entry><literal>UNICODE</literal></entry> + <entry><literal>utf8_to_iso_8859_8</literal></entry> + <entry><literal>UTF8</literal></entry> <entry><literal>ISO_8859_8</literal></entry> </row> <row> - <entry><literal>utf_8_to_iso_8859_9</literal></entry> - <entry><literal>UNICODE</literal></entry> + <entry><literal>utf8_to_iso_8859_9</literal></entry> + <entry><literal>UTF8</literal></entry> <entry><literal>LATIN5</literal></entry> </row> <row> - <entry><literal>utf_8_to_johab</literal></entry> - <entry><literal>UNICODE</literal></entry> + <entry><literal>utf8_to_johab</literal></entry> + <entry><literal>UTF8</literal></entry> <entry><literal>JOHAB</literal></entry> </row> <row> - <entry><literal>utf_8_to_koi8_r</literal></entry> - <entry><literal>UNICODE</literal></entry> + <entry><literal>utf8_to_koi8_r</literal></entry> + <entry><literal>UTF8</literal></entry> <entry><literal>KOI8</literal></entry> </row> <row> - <entry><literal>utf_8_to_sjis</literal></entry> - <entry><literal>UNICODE</literal></entry> + <entry><literal>utf8_to_sjis</literal></entry> + <entry><literal>UTF8</literal></entry> <entry><literal>SJIS</literal></entry> </row> <row> - <entry><literal>utf_8_to_tcvn</literal></entry> - <entry><literal>UNICODE</literal></entry> - <entry><literal>TCVN</literal></entry> + <entry><literal>utf8_to_tcvn</literal></entry> + <entry><literal>UTF8</literal></entry> + <entry><literal>WIN1258</literal></entry> </row> <row> - <entry><literal>utf_8_to_uhc</literal></entry> - <entry><literal>UNICODE</literal></entry> + <entry><literal>utf8_to_uhc</literal></entry> + <entry><literal>UTF8</literal></entry> <entry><literal>UHC</literal></entry> </row> <row> - <entry><literal>utf_8_to_windows_1250</literal></entry> - <entry><literal>UNICODE</literal></entry> + <entry><literal>utf8_to_windows_1250</literal></entry> + <entry><literal>UTF8</literal></entry> <entry><literal>WIN1250</literal></entry> </row> <row> - <entry><literal>utf_8_to_windows_1251</literal></entry> - <entry><literal>UNICODE</literal></entry> - <entry><literal>WIN</literal></entry> + <entry><literal>utf8_to_windows_1251</literal></entry> + <entry><literal>UTF8</literal></entry> + <entry><literal>WIN1251</literal></entry> </row> <row> - <entry><literal>utf_8_to_windows_1256</literal></entry> - <entry><literal>UNICODE</literal></entry> + <entry><literal>utf8_to_windows_1256</literal></entry> + <entry><literal>UTF8</literal></entry> <entry><literal>WIN1256</literal></entry> </row> <row> - <entry><literal>utf_8_to_windows_866</literal></entry> - <entry><literal>UNICODE</literal></entry> - <entry><literal>ALT</literal></entry> + <entry><literal>utf8_to_windows_866</literal></entry> + <entry><literal>UTF8</literal></entry> + <entry><literal>WIN866</literal></entry> </row> <row> - <entry><literal>utf_8_to_windows_874</literal></entry> - <entry><literal>UNICODE</literal></entry> + <entry><literal>utf8_to_windows_874</literal></entry> + <entry><literal>UTF8</literal></entry> <entry><literal>WIN874</literal></entry> </row> @@ -2021,81 +2021,81 @@ PostgreSQL documentation </row> <row> - <entry><literal>windows_1250_to_utf_8</literal></entry> + <entry><literal>windows_1250_to_utf8</literal></entry> <entry><literal>WIN1250</literal></entry> - <entry><literal>UNICODE</literal></entry> + <entry><literal>UTF8</literal></entry> </row> <row> <entry><literal>windows_1251_to_iso_8859_5</literal></entry> - <entry><literal>WIN</literal></entry> + <entry><literal>WIN1251</literal></entry> <entry><literal>ISO_8859_5</literal></entry> </row> <row> <entry><literal>windows_1251_to_koi8_r</literal></entry> - <entry><literal>WIN</literal></entry> + <entry><literal>WIN1251</literal></entry> <entry><literal>KOI8</literal></entry> </row> <row> <entry><literal>windows_1251_to_mic</literal></entry> - <entry><literal>WIN</literal></entry> + <entry><literal>WIN1251</literal></entry> <entry><literal>MULE_INTERNAL</literal></entry> </row> <row> - <entry><literal>windows_1251_to_utf_8</literal></entry> - <entry><literal>WIN</literal></entry> - <entry><literal>UNICODE</literal></entry> + <entry><literal>windows_1251_to_utf8</literal></entry> + <entry><literal>WIN1251</literal></entry> + <entry><literal>UTF8</literal></entry> </row> <row> <entry><literal>windows_1251_to_windows_866</literal></entry> - <entry><literal>WIN</literal></entry> - <entry><literal>ALT</literal></entry> + <entry><literal>WIN1251</literal></entry> + <entry><literal>WIN866</literal></entry> </row> <row> - <entry><literal>windows_1256_to_utf_8</literal></entry> + <entry><literal>windows_1256_to_utf8</literal></entry> <entry><literal>WIN1256</literal></entry> - <entry><literal>UNICODE</literal></entry> + <entry><literal>UTF8</literal></entry> </row> <row> <entry><literal>windows_866_to_iso_8859_5</literal></entry> - <entry><literal>ALT</literal></entry> + <entry><literal>WIN866</literal></entry> <entry><literal>ISO_8859_5</literal></entry> </row> <row> <entry><literal>windows_866_to_koi8_r</literal></entry> - <entry><literal>ALT</literal></entry> + <entry><literal>WIN866</literal></entry> <entry><literal>KOI8</literal></entry> </row> <row> <entry><literal>windows_866_to_mic</literal></entry> - <entry><literal>ALT</literal></entry> + <entry><literal>WIN866</literal></entry> <entry><literal>MULE_INTERNAL</literal></entry> </row> <row> - <entry><literal>windows_866_to_utf_8</literal></entry> - <entry><literal>ALT</literal></entry> - <entry><literal>UNICODE</literal></entry> + <entry><literal>windows_866_to_utf8</literal></entry> + <entry><literal>WIN866</literal></entry> + <entry><literal>UTF8</literal></entry> </row> <row> <entry><literal>windows_866_to_windows_1251</literal></entry> - <entry><literal>ALT</literal></entry> + <entry><literal>WIN866</literal></entry> <entry><literal>WIN</literal></entry> </row> <row> - <entry><literal>windows_874_to_utf_8</literal></entry> + <entry><literal>windows_874_to_utf8</literal></entry> <entry><literal>WIN874</literal></entry> - <entry><literal>UNICODE</literal></entry> + <entry><literal>UTF8</literal></entry> </row> </tbody> @@ -3372,7 +3372,7 @@ substring('foobar' from 'o(.)b') <lineannotation>o</lineannotation> <row> <entry> <literal>\u</><replaceable>wxyz</> </entry> <entry> (where <replaceable>wxyz</> is exactly four hexadecimal digits) - the Unicode character <literal>U+</><replaceable>wxyz</> + the UTF16 (Unicode, 16-bit) character <literal>U+</><replaceable>wxyz</> in the local byte ordering </entry> </row> diff --git a/doc/src/sgml/ref/alter_conversion.sgml b/doc/src/sgml/ref/alter_conversion.sgml index edfe2f8851..39d826274d 100644 --- a/doc/src/sgml/ref/alter_conversion.sgml +++ b/doc/src/sgml/ref/alter_conversion.sgml @@ -72,18 +72,18 @@ ALTER CONVERSION <replaceable>name</replaceable> OWNER TO <replaceable>newowner< <title>Examples</title> <para> - To rename the conversion <literal>iso_8859_1_to_utf_8</literal> to + To rename the conversion <literal>iso_8859_1_to_utf8</literal> to <literal>latin1_to_unicode</literal>: <programlisting> -ALTER CONVERSION iso_8859_1_to_utf_8 RENAME TO latin1_to_unicode; +ALTER CONVERSION iso_8859_1_to_utf8 RENAME TO latin1_to_unicode; </programlisting> </para> <para> - To change the owner of the conversion <literal>iso_8859_1_to_utf_8</literal> to + To change the owner of the conversion <literal>iso_8859_1_to_utf8</literal> to <literal>joe</literal>: <programlisting> -ALTER CONVERSION iso_8859_1_to_utf_8 OWNER TO joe; +ALTER CONVERSION iso_8859_1_to_utf8 OWNER TO joe; </programlisting> </para> </refsect1> diff --git a/doc/src/sgml/ref/comment.sgml b/doc/src/sgml/ref/comment.sgml index 3b626c201c..d37c445d49 100644 --- a/doc/src/sgml/ref/comment.sgml +++ b/doc/src/sgml/ref/comment.sgml @@ -195,7 +195,7 @@ COMMENT ON TABLE mytable IS NULL; COMMENT ON AGGREGATE my_aggregate (double precision) IS 'Computes sample variance'; COMMENT ON CAST (text AS int4) IS 'Allow casts from text to int4'; COMMENT ON COLUMN my_table.my_column IS 'Employee ID number'; -COMMENT ON CONVERSION my_conv IS 'Conversion to Unicode'; +COMMENT ON CONVERSION my_conv IS 'Conversion to UTF8'; COMMENT ON DATABASE my_database IS 'Development Database'; COMMENT ON DOMAIN my_domain IS 'Email Address Domain'; COMMENT ON FUNCTION my_function (timestamp) IS 'Returns Roman Numeral'; diff --git a/doc/src/sgml/ref/create_conversion.sgml b/doc/src/sgml/ref/create_conversion.sgml index eacd0d5950..9136f896e8 100644 --- a/doc/src/sgml/ref/create_conversion.sgml +++ b/doc/src/sgml/ref/create_conversion.sgml @@ -136,10 +136,10 @@ conv_proc( <title>Examples</title> <para> - To create a conversion from encoding <literal>UNICODE</literal> to + To create a conversion from encoding <literal>UTF8</literal> to <literal>LATIN1</literal> using <function>myfunc</>: <programlisting> -CREATE CONVERSION myconv FOR 'UNICODE' TO 'LATIN1' FROM myfunc; +CREATE CONVERSION myconv FOR 'UTF8' TO 'LATIN1' FROM myfunc; </programlisting> </para> </refsect1> diff --git a/src/backend/utils/adt/selfuncs.c b/src/backend/utils/adt/selfuncs.c index fa63880470..1a38c1f8d3 100644 --- a/src/backend/utils/adt/selfuncs.c +++ b/src/backend/utils/adt/selfuncs.c @@ -4035,7 +4035,7 @@ pattern_selectivity(Const *patt, Pattern_Type ptype) * * NOTE: at present this assumes we are in the C locale, so that simple * bytewise comparison applies. However, we might be in a multibyte - * encoding such as UTF-8, so we do have to watch out for generating + * encoding such as UTF8, so we do have to watch out for generating * invalid encoding sequences. */ Const * diff --git a/src/backend/utils/mb/Unicode/Makefile b/src/backend/utils/mb/Unicode/Makefile index 96844276d8..36b22db5a2 100644 --- a/src/backend/utils/mb/Unicode/Makefile +++ b/src/backend/utils/mb/Unicode/Makefile @@ -18,8 +18,8 @@ ISO8859MAPS=iso8859_2_to_utf8.map iso8859_3_to_utf8.map \ utf8_to_iso8859_4.map utf8_to_iso8859_5.map -CYRILLICMAPS=koi8r_to_utf8.map win1251_to_utf8.map alt_to_utf8.map\ - utf8_to_koi8r.map utf8_to_win1251.map utf8_to_alt.map +CYRILLICMAPS=koi8r_to_utf8.map win1251_to_utf8.map win866_to_utf8.map\ + utf8_to_koi8r.map utf8_to_win1251.map utf8_to_win866.map MAPS= $(ISO8859MAPS) $(CYRILLICMAPS)\ big5_to_utf8.map euc_cn_to_utf8.map euc_jp_to_utf8.map \ diff --git a/src/backend/utils/mb/Unicode/UCS_to_8859.pl b/src/backend/utils/mb/Unicode/UCS_to_8859.pl index 4cba090e36..2258b6fd84 100755 --- a/src/backend/utils/mb/Unicode/UCS_to_8859.pl +++ b/src/backend/utils/mb/Unicode/UCS_to_8859.pl @@ -39,7 +39,7 @@ foreach $charset (@charsets) { if( $code >= 0x80){ $utf = &ucs2utf($ucs); if( $array{ $utf } ne "" ){ - printf STDERR "Warning: duplicate unicode: %04x\n",$ucs; + printf STDERR "Warning: duplicate UTF8: %04x\n",$ucs; next; } $count++; @@ -83,7 +83,7 @@ foreach $charset (@charsets) { if($code >= 0x80){ $utf = &ucs2utf($ucs); if( $array{ $utf } ne "" ){ - printf STDERR "Warning: duplicate unicode: %04x\n",$ucs; + printf STDERR "Warning: duplicate UTF8: %04x\n",$ucs; next; } $count++; diff --git a/src/backend/utils/mb/Unicode/UCS_to_BIG5.pl b/src/backend/utils/mb/Unicode/UCS_to_BIG5.pl index 86d31d0c0e..016ed82c6b 100755 --- a/src/backend/utils/mb/Unicode/UCS_to_BIG5.pl +++ b/src/backend/utils/mb/Unicode/UCS_to_BIG5.pl @@ -35,7 +35,7 @@ while( <FILE> ){ if( $code >= 0x80 && $ucs >= 0x0080 ){ $utf = &ucs2utf($ucs); if( $array{ $utf } ne "" ){ - printf STDERR "Warning: duplicate unicode: %04x\n",$ucs; + printf STDERR "Warning: duplicate UTF8: %04x\n",$ucs; next; } $count++; diff --git a/src/backend/utils/mb/Unicode/UCS_to_EUC_CN.pl b/src/backend/utils/mb/Unicode/UCS_to_EUC_CN.pl index a16564a99c..4a3d78c1ed 100755 --- a/src/backend/utils/mb/Unicode/UCS_to_EUC_CN.pl +++ b/src/backend/utils/mb/Unicode/UCS_to_EUC_CN.pl @@ -35,7 +35,7 @@ while( <FILE> ){ if( $code >= 0x80 && $ucs >= 0x0080 ){ $utf = &ucs2utf($ucs); if( $array{ $utf } ne "" ){ - printf STDERR "Warning: duplicate unicode: %04x\n",$ucs; + printf STDERR "Warning: duplicate UTF8: %04x\n",$ucs; next; } $count++; diff --git a/src/backend/utils/mb/Unicode/UCS_to_EUC_JP.pl b/src/backend/utils/mb/Unicode/UCS_to_EUC_JP.pl index 7d8efc868d..4c2ddd2548 100755 --- a/src/backend/utils/mb/Unicode/UCS_to_EUC_JP.pl +++ b/src/backend/utils/mb/Unicode/UCS_to_EUC_JP.pl @@ -51,7 +51,7 @@ while( <FILE> ){ if( $code >= 0x80 && $ucs >= 0x0080 ){ $utf = &ucs2utf($ucs); if( $array{ $utf } ne "" ){ - printf STDERR "Warning: duplicate unicode: %04x\n",$ucs; + printf STDERR "Warning: duplicate UTF8: %04x\n",$ucs; next; } $count++; @@ -80,7 +80,7 @@ while( <FILE> ){ if( $code >= 0x80 && $ucs >= 0x0080 ){ $utf = &ucs2utf($ucs); if( $array{ $utf } ne "" ){ - printf STDERR "Warning: duplicate unicode: %04x\n",$ucs; + printf STDERR "Warning: duplicate UTF8: %04x\n",$ucs; next; } $count++; @@ -108,7 +108,7 @@ while( <FILE> ){ if( $code >= 0x80 && $ucs >= 0x0080 ){ $utf = &ucs2utf($ucs); if( $array{ $utf } ne "" ){ - printf STDERR "Warning: duplicate unicode: %04x\n",$ucs; + printf STDERR "Warning: duplicate UTF8: %04x\n",$ucs; next; } $count++; diff --git a/src/backend/utils/mb/Unicode/UCS_to_EUC_KR.pl b/src/backend/utils/mb/Unicode/UCS_to_EUC_KR.pl index 66ec1ebd61..c93ea19003 100755 --- a/src/backend/utils/mb/Unicode/UCS_to_EUC_KR.pl +++ b/src/backend/utils/mb/Unicode/UCS_to_EUC_KR.pl @@ -35,7 +35,7 @@ while( <FILE> ){ if( $code >= 0x80 && $ucs >= 0x0080 ){ $utf = &ucs2utf($ucs); if( $array{ $utf } ne "" ){ - printf STDERR "Warning: duplicate unicode: %04x\n",$ucs; + printf STDERR "Warning: duplicate UTF8: %04x\n",$ucs; next; } $count++; diff --git a/src/backend/utils/mb/Unicode/UCS_to_EUC_TW.pl b/src/backend/utils/mb/Unicode/UCS_to_EUC_TW.pl index c24eefb0a4..6b978c8a67 100755 --- a/src/backend/utils/mb/Unicode/UCS_to_EUC_TW.pl +++ b/src/backend/utils/mb/Unicode/UCS_to_EUC_TW.pl @@ -36,7 +36,7 @@ while( <FILE> ){ if( $code >= 0x80 && $ucs >= 0x0080 ){ $utf = &ucs2utf($ucs); if( $array{ $utf } ne "" ){ - printf STDERR "Warning: duplicate unicode: %04x\n",$ucs; + printf STDERR "Warning: duplicate UTF8: %04x\n",$ucs; next; } $count++; diff --git a/src/backend/utils/mb/Unicode/UCS_to_GB18030.pl b/src/backend/utils/mb/Unicode/UCS_to_GB18030.pl index e924f64680..369532009d 100755 --- a/src/backend/utils/mb/Unicode/UCS_to_GB18030.pl +++ b/src/backend/utils/mb/Unicode/UCS_to_GB18030.pl @@ -35,7 +35,7 @@ while( <FILE> ){ if( $code >= 0x80 && $ucs >= 0x0080 ){ $utf = &ucs2utf($ucs); if( $array{ $utf } ne "" ){ - printf STDERR "Warning: duplicate unicode: %04x\n",$ucs; + printf STDERR "Warning: duplicate UTF8: %04x\n",$ucs; next; } $count++; diff --git a/src/backend/utils/mb/Unicode/UCS_to_GBK.pl b/src/backend/utils/mb/Unicode/UCS_to_GBK.pl index 69201c685a..ed9d91acf3 100644 --- a/src/backend/utils/mb/Unicode/UCS_to_GBK.pl +++ b/src/backend/utils/mb/Unicode/UCS_to_GBK.pl @@ -36,7 +36,7 @@ while( <FILE> ){ if( $code >= 0x80 && $ucs >= 0x0080 ){ $utf = &ucs2utf($ucs); if( $array{ $utf } ne "" ){ - printf STDERR "Warning: duplicate unicode: %04x\n",$ucs; + printf STDERR "Warning: duplicate UTF8: %04x\n",$ucs; next; } $count++; diff --git a/src/backend/utils/mb/Unicode/UCS_to_JOHAB.pl b/src/backend/utils/mb/Unicode/UCS_to_JOHAB.pl index ed832e71d6..e622fbd28a 100644 --- a/src/backend/utils/mb/Unicode/UCS_to_JOHAB.pl +++ b/src/backend/utils/mb/Unicode/UCS_to_JOHAB.pl @@ -35,7 +35,7 @@ while( <FILE> ){ if( $code >= 0x80 && $ucs >= 0x0080 ){ $utf = &ucs2utf($ucs); if( $array{ $utf } ne "" ){ - printf STDERR "Warning: duplicate unicode: %04x\n",$ucs; + printf STDERR "Warning: duplicate UTF8: %04x\n",$ucs; next; } $count++; diff --git a/src/backend/utils/mb/Unicode/UCS_to_SJIS.pl b/src/backend/utils/mb/Unicode/UCS_to_SJIS.pl index 09fdba25b6..36fdd7f5eb 100755 --- a/src/backend/utils/mb/Unicode/UCS_to_SJIS.pl +++ b/src/backend/utils/mb/Unicode/UCS_to_SJIS.pl @@ -52,7 +52,7 @@ while( <FILE> ){ || (( $code >= 0x879a ) && ( $code <= 0x879c ))) { - printf STDERR "Warning: duplicate unicode : UCS=0x%04x SJIS=0x%04x\n",$ucs,$code; + printf STDERR "Warning: duplicate UTF8 : UCS=0x%04x SJIS=0x%04x\n",$ucs,$code; next; } $count++; diff --git a/src/backend/utils/mb/Unicode/UCS_to_UHC.pl b/src/backend/utils/mb/Unicode/UCS_to_UHC.pl index fd598af60b..b76c8ce5ce 100644 --- a/src/backend/utils/mb/Unicode/UCS_to_UHC.pl +++ b/src/backend/utils/mb/Unicode/UCS_to_UHC.pl @@ -35,7 +35,7 @@ while( <FILE> ){ if( $code >= 0x80 && $ucs >= 0x0080 ){ $utf = &ucs2utf($ucs); if( $array{ $utf } ne "" ){ - printf STDERR "Warning: duplicate unicode: %04x\n",$ucs; + printf STDERR "Warning: duplicate UTF8: %04x\n",$ucs; next; } $count++; diff --git a/src/backend/utils/mb/Unicode/UCS_to_WIN874.pl b/src/backend/utils/mb/Unicode/UCS_to_WIN874.pl index 94d851c55d..33c8937d4d 100644 --- a/src/backend/utils/mb/Unicode/UCS_to_WIN874.pl +++ b/src/backend/utils/mb/Unicode/UCS_to_WIN874.pl @@ -35,7 +35,7 @@ while( <FILE> ){ if( $code >= 0x80 && $ucs >= 0x0080 ){ $utf = &ucs2utf($ucs); if( $array{ $utf } ne "" ){ - printf STDERR "Warning: duplicate unicode: %04x\n",$ucs; + printf STDERR "Warning: duplicate UTF8: %04x\n",$ucs; next; } $count++; diff --git a/src/backend/utils/mb/Unicode/UCS_to_WINX.pl b/src/backend/utils/mb/Unicode/UCS_to_WINX.pl index 1e2fb41aad..2291c61424 100644 --- a/src/backend/utils/mb/Unicode/UCS_to_WINX.pl +++ b/src/backend/utils/mb/Unicode/UCS_to_WINX.pl @@ -42,7 +42,7 @@ foreach $charset (@charsets) { if( $code >= 0x80){ $utf = &ucs2utf($ucs); if( $array{ $utf } ne "" ){ - printf STDERR "Warning: duplicate unicode: %04x\n",$ucs; + printf STDERR "Warning: duplicate UTF8: %04x\n",$ucs; next; } $count++; @@ -86,7 +86,7 @@ foreach $charset (@charsets) { if($code >= 0x80){ $utf = &ucs2utf($ucs); if( $array{ $utf } ne "" ){ - printf STDERR "Warning: duplicate unicode: %04x\n",$ucs; + printf STDERR "Warning: duplicate UTF8: %04x\n",$ucs; next; } $count++; diff --git a/src/backend/utils/mb/Unicode/UCS_to_cyrillic.pl b/src/backend/utils/mb/Unicode/UCS_to_cyrillic.pl index 9e1b49aea2..400089bd19 100644 --- a/src/backend/utils/mb/Unicode/UCS_to_cyrillic.pl +++ b/src/backend/utils/mb/Unicode/UCS_to_cyrillic.pl @@ -17,8 +17,8 @@ require "ucs2utf.pl"; %filename = ('KOI8R'=>'koi8-r.txt', 'WIN1251'=>'cp1251.txt', - 'ALT'=>'cp866.txt'); -@charsets = ('KOI8R','ALT','WIN1251'); + 'WIN866'=>'cp866.txt'); +@charsets = ('KOI8R','WIN866','WIN1251'); foreach $charset (@charsets) { # @@ -41,7 +41,7 @@ foreach $charset (@charsets) { if( $code >= 0x80){ $utf = &ucs2utf($ucs); if( $array{ $utf } ne "" ){ - printf STDERR "Warning: duplicate unicode: %04x\n",$ucs; + printf STDERR "Warning: duplicate UTF8: %04x\n",$ucs; next; } $count++; @@ -85,7 +85,7 @@ foreach $charset (@charsets) { if($code >= 0x80){ $utf = &ucs2utf($ucs); if( $array{ $utf } ne "" ){ - printf STDERR "Warning: duplicate unicode: %04x\n",$ucs; + printf STDERR "Warning: duplicate UTF8: %04x\n",$ucs; next; } $count++; diff --git a/src/backend/utils/mb/Unicode/utf8_to_tcvn.map b/src/backend/utils/mb/Unicode/utf8_to_win1258.map index c7e3b0f258..84cefd91f3 100644 --- a/src/backend/utils/mb/Unicode/utf8_to_tcvn.map +++ b/src/backend/utils/mb/Unicode/utf8_to_win1258.map @@ -1,4 +1,4 @@ -static pg_utf_to_local ULmapTCVN[ 120 ] = { +static pg_utf_to_local ULmapWIN1258[ 120 ] = { {0x0000, 0x0081}, {0xc2a0, 0x00a0}, {0xc2a1, 0x00a1}, diff --git a/src/backend/utils/mb/Unicode/utf8_to_alt.map b/src/backend/utils/mb/Unicode/utf8_to_win866.map index 2aba0c5a9b..cac06a82ed 100644 --- a/src/backend/utils/mb/Unicode/utf8_to_alt.map +++ b/src/backend/utils/mb/Unicode/utf8_to_win866.map @@ -1,4 +1,4 @@ -static pg_utf_to_local ULmap_ALT[ 128 ] = { +static pg_utf_to_local ULmap_WIN866[ 128 ] = { {0xc2a0, 0x00ff}, {0xc2a4, 0x00fd}, {0xc2b0, 0x00f8}, diff --git a/src/backend/utils/mb/Unicode/tcvn_to_utf8.map b/src/backend/utils/mb/Unicode/win1258_to_utf8.map index 5e680c0f21..0596d8ba4f 100644 --- a/src/backend/utils/mb/Unicode/tcvn_to_utf8.map +++ b/src/backend/utils/mb/Unicode/win1258_to_utf8.map @@ -1,4 +1,4 @@ -static pg_local_to_utf LUmapTCVN[ 128 ] = { +static pg_local_to_utf LUmapWIN1258[ 128 ] = { {0x0080, 0xe282ac}, {0x0081, 0x0000}, {0x0082, 0xe2809a}, diff --git a/src/backend/utils/mb/Unicode/alt_to_utf8.map b/src/backend/utils/mb/Unicode/win866_to_utf8.map index 7bc6982224..d2a377a537 100644 --- a/src/backend/utils/mb/Unicode/alt_to_utf8.map +++ b/src/backend/utils/mb/Unicode/win866_to_utf8.map @@ -1,4 +1,4 @@ -static pg_local_to_utf LUmapALT[ 128 ] = { +static pg_local_to_utf LUmapWIN866[ 128 ] = { {0x0080, 0xd090}, {0x0081, 0xd091}, {0x0082, 0xd092}, diff --git a/src/backend/utils/mb/conv.c b/src/backend/utils/mb/conv.c index 4062fa26b9..bad1c2116f 100644 --- a/src/backend/utils/mb/conv.c +++ b/src/backend/utils/mb/conv.c @@ -303,7 +303,7 @@ mic2latin_with_table( /* * comparison routine for bsearch() - * this routine is intended for UTF-8 -> local code + * this routine is intended for UTF8 -> local code */ static int compare1(const void *p1, const void *p2) @@ -318,7 +318,7 @@ compare1(const void *p1, const void *p2) /* * comparison routine for bsearch() - * this routine is intended for local code -> UTF-8 + * this routine is intended for local code -> UTF8 */ static int compare2(const void *p1, const void *p2) @@ -332,9 +332,9 @@ compare2(const void *p1, const void *p2) } /* - * UTF-8 ---> local code + * UTF8 ---> local code * - * utf: input UTF-8 string. Its length is limited by "len" parameter + * utf: input UTF8 string. Its length is limited by "len" parameter * or a null terminator. * iso: pointer to the output. * map: the conversion map. @@ -373,7 +373,7 @@ UtfToLocal(unsigned char *utf, unsigned char *iso, { ereport(WARNING, (errcode(ERRCODE_UNTRANSLATABLE_CHARACTER), - errmsg("ignoring unconvertible UTF-8 character 0x%04x", + errmsg("ignoring unconvertible UTF8 character 0x%04x", iutf))); continue; } @@ -390,7 +390,7 @@ UtfToLocal(unsigned char *utf, unsigned char *iso, } /* - * local code ---> UTF-8 + * local code ---> UTF8 */ void LocalToUtf(unsigned char *iso, unsigned char *utf, diff --git a/src/backend/utils/mb/conversion_procs/Makefile b/src/backend/utils/mb/conversion_procs/Makefile index fb69fe715c..9a53770237 100644 --- a/src/backend/utils/mb/conversion_procs/Makefile +++ b/src/backend/utils/mb/conversion_procs/Makefile @@ -23,7 +23,7 @@ DIRS = \ utf8_and_ascii utf8_and_big5 utf8_and_cyrillic utf8_and_euc_cn \ utf8_and_euc_jp utf8_and_euc_kr utf8_and_euc_tw utf8_and_gb18030 \ utf8_and_gbk utf8_and_iso8859 utf8_and_iso8859_1 utf8_and_johab \ - utf8_and_sjis utf8_and_tcvn utf8_and_uhc utf8_and_win1250 \ + utf8_and_sjis utf8_and_win1258 utf8_and_uhc utf8_and_win1250 \ utf8_and_win1256 utf8_and_win874 # conversion_name source_encoding destination_encoding function object @@ -36,20 +36,20 @@ CONVERSIONS = \ mic_to_iso_8859_5 MULE_INTERNAL ISO-8859-5 mic_to_iso cyrillic_and_mic \ windows_1251_to_mic WIN1251 MULE_INTERNAL win1251_to_mic cyrillic_and_mic \ mic_to_windows_1251 MULE_INTERNAL WIN1251 mic_to_win1251 cyrillic_and_mic \ - windows_866_to_mic ALT MULE_INTERNAL alt_to_mic cyrillic_and_mic \ - mic_to_windows_866 MULE_INTERNAL ALT mic_to_alt cyrillic_and_mic \ + windows_866_to_mic WIN866 MULE_INTERNAL win866_to_mic cyrillic_and_mic \ + mic_to_windows_866 MULE_INTERNAL WIN866 mic_to_win866 cyrillic_and_mic \ koi8_r_to_windows_1251 KOI8R WIN1251 koi8r_to_win1251 cyrillic_and_mic \ windows_1251_to_koi8_r WIN1251 KOI8R win1251_to_koi8r cyrillic_and_mic \ - koi8_r_to_windows_866 KOI8R ALT koi8r_to_alt cyrillic_and_mic \ - windows_866_to_koi8_r ALT KOI8R alt_to_koi8r cyrillic_and_mic \ - windows_866_to_windows_1251 ALT WIN1251 alt_to_win1251 cyrillic_and_mic \ - windows_1251_to_windows_866 WIN1251 ALT win1251_to_alt cyrillic_and_mic \ + koi8_r_to_windows_866 KOI8R WIN866 koi8r_to_win866 cyrillic_and_mic \ + windows_866_to_koi8_r WIN866 KOI8R win866_to_koi8r cyrillic_and_mic \ + windows_866_to_windows_1251 WIN866 WIN1251 win866_to_win1251 cyrillic_and_mic \ + windows_1251_to_windows_866 WIN1251 WIN866 win1251_to_win866 cyrillic_and_mic \ iso_8859_5_to_koi8_r ISO-8859-5 KOI8R iso_to_koi8r cyrillic_and_mic \ koi8_r_to_iso_8859_5 KOI8R ISO-8859-5 koi8r_to_iso cyrillic_and_mic \ iso_8859_5_to_windows_1251 ISO-8859-5 WIN1251 iso_to_win1251 cyrillic_and_mic \ windows_1251_to_iso_8859_5 WIN1251 ISO-8859-5 win1251_to_iso cyrillic_and_mic \ - iso_8859_5_to_windows_866 ISO-8859-5 ALT iso_to_alt cyrillic_and_mic \ - windows_866_to_iso_8859_5 ALT ISO-8859-5 alt_to_iso cyrillic_and_mic \ + iso_8859_5_to_windows_866 ISO-8859-5 WIN866 iso_to_win866 cyrillic_and_mic \ + windows_866_to_iso_8859_5 WIN866 ISO-8859-5 win866_to_iso cyrillic_and_mic \ euc_cn_to_mic EUC_CN MULE_INTERNAL euc_cn_to_mic euc_cn_and_mic \ mic_to_euc_cn MULE_INTERNAL EUC_CN mic_to_euc_cn euc_cn_and_mic \ euc_jp_to_sjis EUC_JP SJIS euc_jp_to_sjis euc_jp_and_sjis \ @@ -78,70 +78,70 @@ CONVERSIONS = \ mic_to_iso_8859_3 MULE_INTERNAL LATIN3 mic_to_latin3 latin_and_mic \ iso_8859_4_to_mic LATIN4 MULE_INTERNAL latin4_to_mic latin_and_mic \ mic_to_iso_8859_4 MULE_INTERNAL LATIN4 mic_to_latin4 latin_and_mic \ - ascii_to_utf_8 SQL_ASCII UNICODE ascii_to_utf8 utf8_and_ascii \ - utf_8_to_ascii UNICODE SQL_ASCII utf8_to_ascii utf8_and_ascii \ - big5_to_utf_8 BIG5 UNICODE big5_to_utf8 utf8_and_big5 \ - utf_8_to_big5 UNICODE BIG5 utf8_to_big5 utf8_and_big5 \ - utf_8_to_koi8_r UNICODE KOI8R utf8_to_koi8r utf8_and_cyrillic \ - koi8_r_to_utf_8 KOI8R UNICODE koi8r_to_utf8 utf8_and_cyrillic \ - utf_8_to_windows_1251 UNICODE WIN1251 utf8_to_win1251 utf8_and_cyrillic \ - windows_1251_to_utf_8 WIN1251 UNICODE win1251_to_utf8 utf8_and_cyrillic \ - utf_8_to_windows_866 UNICODE ALT utf8_to_alt utf8_and_cyrillic \ - windows_866_to_utf_8 ALT UNICODE alt_to_utf8 utf8_and_cyrillic \ - euc_cn_to_utf_8 EUC_CN UNICODE euc_cn_to_utf8 utf8_and_euc_cn \ - utf_8_to_euc_cn UNICODE EUC_CN utf8_to_euc_cn utf8_and_euc_cn \ - euc_jp_to_utf_8 EUC_JP UNICODE euc_jp_to_utf8 utf8_and_euc_jp \ - utf_8_to_euc_jp UNICODE EUC_JP utf8_to_euc_jp utf8_and_euc_jp \ - euc_kr_to_utf_8 EUC_KR UNICODE euc_kr_to_utf8 utf8_and_euc_kr \ - utf_8_to_euc_kr UNICODE EUC_KR utf8_to_euc_kr utf8_and_euc_kr \ - euc_tw_to_utf_8 EUC_TW UNICODE euc_tw_to_utf8 utf8_and_euc_tw \ - utf_8_to_euc_tw UNICODE EUC_TW utf8_to_euc_tw utf8_and_euc_tw \ - gb18030_to_utf_8 GB18030 UNICODE gb18030_to_utf8 utf8_and_gb18030 \ - utf_8_to_gb18030 UNICODE GB18030 utf8_to_gb18030 utf8_and_gb18030 \ - gbk_to_utf_8 GBK UNICODE gbk_to_utf8 utf8_and_gbk \ - utf_8_to_gbk UNICODE GBK utf8_to_gbk utf8_and_gbk \ - utf_8_to_iso_8859_2 UNICODE LATIN2 utf8_to_iso8859 utf8_and_iso8859 \ - iso_8859_2_to_utf_8 LATIN2 UNICODE iso8859_to_utf8 utf8_and_iso8859 \ - utf_8_to_iso_8859_3 UNICODE LATIN3 utf8_to_iso8859 utf8_and_iso8859 \ - iso_8859_3_to_utf_8 LATIN3 UNICODE iso8859_to_utf8 utf8_and_iso8859 \ - utf_8_to_iso_8859_4 UNICODE LATIN4 utf8_to_iso8859 utf8_and_iso8859 \ - iso_8859_4_to_utf_8 LATIN4 UNICODE iso8859_to_utf8 utf8_and_iso8859 \ - utf_8_to_iso_8859_9 UNICODE LATIN5 utf8_to_iso8859 utf8_and_iso8859 \ - iso_8859_9_to_utf_8 LATIN5 UNICODE iso8859_to_utf8 utf8_and_iso8859 \ - utf_8_to_iso_8859_10 UNICODE LATIN6 utf8_to_iso8859 utf8_and_iso8859 \ - iso_8859_10_to_utf_8 LATIN6 UNICODE iso8859_to_utf8 utf8_and_iso8859 \ - utf_8_to_iso_8859_13 UNICODE LATIN7 utf8_to_iso8859 utf8_and_iso8859 \ - iso_8859_13_to_utf_8 LATIN7 UNICODE iso8859_to_utf8 utf8_and_iso8859 \ - utf_8_to_iso_8859_14 UNICODE LATIN8 utf8_to_iso8859 utf8_and_iso8859 \ - iso_8859_14_to_utf_8 LATIN8 UNICODE iso8859_to_utf8 utf8_and_iso8859 \ - utf_8_to_iso_8859_15 UNICODE LATIN9 utf8_to_iso8859 utf8_and_iso8859 \ - iso_8859_15_to_utf_8 LATIN9 UNICODE iso8859_to_utf8 utf8_and_iso8859 \ - utf_8_to_iso_8859_16 UNICODE LATIN10 utf8_to_iso8859 utf8_and_iso8859 \ - iso_8859_16_to_utf_8 LATIN10 UNICODE iso8859_to_utf8 utf8_and_iso8859 \ - utf_8_to_iso_8859_5 UNICODE ISO-8859-5 utf8_to_iso8859 utf8_and_iso8859 \ - iso_8859_5_to_utf_8 ISO-8859-5 UNICODE iso8859_to_utf8 utf8_and_iso8859 \ - utf_8_to_iso_8859_6 UNICODE ISO-8859-6 utf8_to_iso8859 utf8_and_iso8859 \ - iso_8859_6_to_utf_8 ISO-8859-6 UNICODE iso8859_to_utf8 utf8_and_iso8859 \ - utf_8_to_iso_8859_7 UNICODE ISO-8859-7 utf8_to_iso8859 utf8_and_iso8859 \ - iso_8859_7_to_utf_8 ISO-8859-7 UNICODE iso8859_to_utf8 utf8_and_iso8859 \ - utf_8_to_iso_8859_8 UNICODE ISO-8859-8 utf8_to_iso8859 utf8_and_iso8859 \ - iso_8859_8_to_utf_8 ISO-8859-8 UNICODE iso8859_to_utf8 utf8_and_iso8859 \ - iso_8859_1_to_utf_8 LATIN1 UNICODE iso8859_1_to_utf8 utf8_and_iso8859_1 \ - utf_8_to_iso_8859_1 UNICODE LATIN1 utf8_to_iso8859_1 utf8_and_iso8859_1 \ - johab_to_utf_8 JOHAB UNICODE johab_to_utf8 utf8_and_johab \ - utf_8_to_johab UNICODE JOHAB utf8_to_johab utf8_and_johab \ - sjis_to_utf_8 SJIS UNICODE sjis_to_utf8 utf8_and_sjis \ - utf_8_to_sjis UNICODE SJIS utf8_to_sjis utf8_and_sjis \ - tcvn_to_utf_8 TCVN UNICODE tcvn_to_utf8 utf8_and_tcvn \ - utf_8_to_tcvn UNICODE TCVN utf8_to_tcvn utf8_and_tcvn \ - uhc_to_utf_8 UHC UNICODE uhc_to_utf8 utf8_and_uhc \ - utf_8_to_uhc UNICODE UHC utf8_to_uhc utf8_and_uhc \ - utf_8_to_windows_1250 UNICODE WIN1250 utf_to_win1250 utf8_and_win1250 \ - windows_1250_to_utf_8 WIN1250 UNICODE win1250_to_utf utf8_and_win1250 \ - utf_8_to_windows_1256 UNICODE WIN1256 utf_to_win1256 utf8_and_win1256 \ - windows_1256_to_utf_8 WIN1256 UNICODE win1256_to_utf utf8_and_win1256 \ - utf_8_to_windows_874 UNICODE WIN874 utf_to_win874 utf8_and_win874 \ - windows_874_to_utf_8 WIN874 UNICODE win874_to_utf utf8_and_win874 + ascii_to_utf8 SQL_ASCII UTF8 ascii_to_utf8 utf8_and_ascii \ + utf8_to_ascii UTF8 SQL_ASCII utf8_to_ascii utf8_and_ascii \ + big5_to_utf8 BIG5 UTF8 big5_to_utf8 utf8_and_big5 \ + utf8_to_big5 UTF8 BIG5 utf8_to_big5 utf8_and_big5 \ + utf8_to_koi8_r UTF8 KOI8R utf8_to_koi8r utf8_and_cyrillic \ + koi8_r_to_utf8 KOI8R UTF8 koi8r_to_utf8 utf8_and_cyrillic \ + utf8_to_windows_1251 UTF8 WIN1251 utf8_to_win1251 utf8_and_cyrillic \ + windows_1251_to_utf8 WIN1251 UTF8 win1251_to_utf8 utf8_and_cyrillic \ + utf8_to_windows_866 UTF8 WIN866 utf8_to_win866 utf8_and_cyrillic \ + windows_866_to_utf8 WIN866 UTF8 win866_to_utf8 utf8_and_cyrillic \ + euc_cn_to_utf8 EUC_CN UTF8 euc_cn_to_utf8 utf8_and_euc_cn \ + utf8_to_euc_cn UTF8 EUC_CN utf8_to_euc_cn utf8_and_euc_cn \ + euc_jp_to_utf8 EUC_JP UTF8 euc_jp_to_utf8 utf8_and_euc_jp \ + utf8_to_euc_jp UTF8 EUC_JP utf8_to_euc_jp utf8_and_euc_jp \ + euc_kr_to_utf8 EUC_KR UTF8 euc_kr_to_utf8 utf8_and_euc_kr \ + utf8_to_euc_kr UTF8 EUC_KR utf8_to_euc_kr utf8_and_euc_kr \ + euc_tw_to_utf8 EUC_TW UTF8 euc_tw_to_utf8 utf8_and_euc_tw \ + utf8_to_euc_tw UTF8 EUC_TW utf8_to_euc_tw utf8_and_euc_tw \ + gb18030_to_utf8 GB18030 UTF8 gb18030_to_utf8 utf8_and_gb18030 \ + utf8_to_gb18030 UTF8 GB18030 utf8_to_gb18030 utf8_and_gb18030 \ + gbk_to_utf8 GBK UTF8 gbk_to_utf8 utf8_and_gbk \ + utf8_to_gbk UTF8 GBK utf8_to_gbk utf8_and_gbk \ + utf8_to_iso_8859_2 UTF8 LATIN2 utf8_to_iso8859 utf8_and_iso8859 \ + iso_8859_2_to_utf8 LATIN2 UTF8 iso8859_to_utf8 utf8_and_iso8859 \ + utf8_to_iso_8859_3 UTF8 LATIN3 utf8_to_iso8859 utf8_and_iso8859 \ + iso_8859_3_to_utf8 LATIN3 UTF8 iso8859_to_utf8 utf8_and_iso8859 \ + utf8_to_iso_8859_4 UTF8 LATIN4 utf8_to_iso8859 utf8_and_iso8859 \ + iso_8859_4_to_utf8 LATIN4 UTF8 iso8859_to_utf8 utf8_and_iso8859 \ + utf8_to_iso_8859_9 UTF8 LATIN5 utf8_to_iso8859 utf8_and_iso8859 \ + iso_8859_9_to_utf8 LATIN5 UTF8 iso8859_to_utf8 utf8_and_iso8859 \ + utf8_to_iso_8859_10 UTF8 LATIN6 utf8_to_iso8859 utf8_and_iso8859 \ + iso_8859_10_to_utf8 LATIN6 UTF8 iso8859_to_utf8 utf8_and_iso8859 \ + utf8_to_iso_8859_13 UTF8 LATIN7 utf8_to_iso8859 utf8_and_iso8859 \ + iso_8859_13_to_utf8 LATIN7 UTF8 iso8859_to_utf8 utf8_and_iso8859 \ + utf8_to_iso_8859_14 UTF8 LATIN8 utf8_to_iso8859 utf8_and_iso8859 \ + iso_8859_14_to_utf8 LATIN8 UTF8 iso8859_to_utf8 utf8_and_iso8859 \ + utf8_to_iso_8859_15 UTF8 LATIN9 utf8_to_iso8859 utf8_and_iso8859 \ + iso_8859_15_to_utf8 LATIN9 UTF8 iso8859_to_utf8 utf8_and_iso8859 \ + utf8_to_iso_8859_16 UTF8 LATIN10 utf8_to_iso8859 utf8_and_iso8859 \ + iso_8859_16_to_utf8 LATIN10 UTF8 iso8859_to_utf8 utf8_and_iso8859 \ + utf8_to_iso_8859_5 UTF8 ISO-8859-5 utf8_to_iso8859 utf8_and_iso8859 \ + iso_8859_5_to_utf8 ISO-8859-5 UTF8 iso8859_to_utf8 utf8_and_iso8859 \ + utf8_to_iso_8859_6 UTF8 ISO-8859-6 utf8_to_iso8859 utf8_and_iso8859 \ + iso_8859_6_to_utf8 ISO-8859-6 UTF8 iso8859_to_utf8 utf8_and_iso8859 \ + utf8_to_iso_8859_7 UTF8 ISO-8859-7 utf8_to_iso8859 utf8_and_iso8859 \ + iso_8859_7_to_utf8 ISO-8859-7 UTF8 iso8859_to_utf8 utf8_and_iso8859 \ + utf8_to_iso_8859_8 UTF8 ISO-8859-8 utf8_to_iso8859 utf8_and_iso8859 \ + iso_8859_8_to_utf8 ISO-8859-8 UTF8 iso8859_to_utf8 utf8_and_iso8859 \ + iso_8859_1_to_utf8 LATIN1 UTF8 iso8859_1_to_utf8 utf8_and_iso8859_1 \ + utf8_to_iso_8859_1 UTF8 LATIN1 utf8_to_iso8859_1 utf8_and_iso8859_1 \ + johab_to_utf8 JOHAB UTF8 johab_to_utf8 utf8_and_johab \ + utf8_to_johab UTF8 JOHAB utf8_to_johab utf8_and_johab \ + sjis_to_utf8 SJIS UTF8 sjis_to_utf8 utf8_and_sjis \ + utf8_to_sjis UTF8 SJIS utf8_to_sjis utf8_and_sjis \ + win1258_to_utf8 WIN1258 UTF8 win1258_to_utf8 utf8_and_win1258 \ + utf8_to_win1258 UTF8 WIN1258 utf8_to_win1258 utf8_and_win1258 \ + uhc_to_utf8 UHC UTF8 uhc_to_utf8 utf8_and_uhc \ + utf8_to_uhc UTF8 UHC utf8_to_uhc utf8_and_uhc \ + utf8_to_windows_1250 UTF8 WIN1250 utf_to_win1250 utf8_and_win1250 \ + windows_1250_to_utf8 WIN1250 UTF8 win1250_to_utf utf8_and_win1250 \ + utf8_to_windows_1256 UTF8 WIN1256 utf_to_win1256 utf8_and_win1256 \ + windows_1256_to_utf8 WIN1256 UTF8 win1256_to_utf utf8_and_win1256 \ + utf8_to_windows_874 UTF8 WIN874 utf_to_win874 utf8_and_win874 \ + windows_874_to_utf8 WIN874 UTF8 win874_to_utf utf8_and_win874 all: $(SQLSCRIPT) @for dir in $(DIRS); do $(MAKE) -C $$dir $@ || exit; done diff --git a/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c b/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c index e0eb3f5206..b82a61f12e 100644 --- a/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c @@ -23,20 +23,20 @@ PG_FUNCTION_INFO_V1(iso_to_mic); PG_FUNCTION_INFO_V1(mic_to_iso); PG_FUNCTION_INFO_V1(win1251_to_mic); PG_FUNCTION_INFO_V1(mic_to_win1251); -PG_FUNCTION_INFO_V1(alt_to_mic); -PG_FUNCTION_INFO_V1(mic_to_alt); +PG_FUNCTION_INFO_V1(win866_to_mic); +PG_FUNCTION_INFO_V1(mic_to_win866); PG_FUNCTION_INFO_V1(koi8r_to_win1251); PG_FUNCTION_INFO_V1(win1251_to_koi8r); -PG_FUNCTION_INFO_V1(koi8r_to_alt); -PG_FUNCTION_INFO_V1(alt_to_koi8r); -PG_FUNCTION_INFO_V1(alt_to_win1251); -PG_FUNCTION_INFO_V1(win1251_to_alt); +PG_FUNCTION_INFO_V1(koi8r_to_win866); +PG_FUNCTION_INFO_V1(win866_to_koi8r); +PG_FUNCTION_INFO_V1(win866_to_win1251); +PG_FUNCTION_INFO_V1(win1251_to_win866); PG_FUNCTION_INFO_V1(iso_to_koi8r); PG_FUNCTION_INFO_V1(koi8r_to_iso); PG_FUNCTION_INFO_V1(iso_to_win1251); PG_FUNCTION_INFO_V1(win1251_to_iso); -PG_FUNCTION_INFO_V1(iso_to_alt); -PG_FUNCTION_INFO_V1(alt_to_iso); +PG_FUNCTION_INFO_V1(iso_to_win866); +PG_FUNCTION_INFO_V1(win866_to_iso); extern Datum koi8r_to_mic(PG_FUNCTION_ARGS); extern Datum mic_to_koi8r(PG_FUNCTION_ARGS); @@ -44,20 +44,20 @@ extern Datum iso_to_mic(PG_FUNCTION_ARGS); extern Datum mic_to_iso(PG_FUNCTION_ARGS); extern Datum win1251_to_mic(PG_FUNCTION_ARGS); extern Datum mic_to_win1251(PG_FUNCTION_ARGS); -extern Datum alt_to_mic(PG_FUNCTION_ARGS); -extern Datum mic_to_alt(PG_FUNCTION_ARGS); +extern Datum win866_to_mic(PG_FUNCTION_ARGS); +extern Datum mic_to_win866(PG_FUNCTION_ARGS); extern Datum koi8r_to_win1251(PG_FUNCTION_ARGS); extern Datum win1251_to_koi8r(PG_FUNCTION_ARGS); -extern Datum koi8r_to_alt(PG_FUNCTION_ARGS); -extern Datum alt_to_koi8r(PG_FUNCTION_ARGS); -extern Datum alt_to_win1251(PG_FUNCTION_ARGS); -extern Datum win1251_to_alt(PG_FUNCTION_ARGS); +extern Datum koi8r_to_win866(PG_FUNCTION_ARGS); +extern Datum win866_to_koi8r(PG_FUNCTION_ARGS); +extern Datum win866_to_win1251(PG_FUNCTION_ARGS); +extern Datum win1251_to_win866(PG_FUNCTION_ARGS); extern Datum iso_to_koi8r(PG_FUNCTION_ARGS); extern Datum koi8r_to_iso(PG_FUNCTION_ARGS); extern Datum iso_to_win1251(PG_FUNCTION_ARGS); extern Datum win1251_to_iso(PG_FUNCTION_ARGS); -extern Datum iso_to_alt(PG_FUNCTION_ARGS); -extern Datum alt_to_iso(PG_FUNCTION_ARGS); +extern Datum iso_to_win866(PG_FUNCTION_ARGS); +extern Datum win866_to_iso(PG_FUNCTION_ARGS); /* ---------- * conv_proc( @@ -76,8 +76,8 @@ static void iso2mic(unsigned char *l, unsigned char *p, int len); static void mic2iso(unsigned char *mic, unsigned char *p, int len); static void win12512mic(unsigned char *l, unsigned char *p, int len); static void mic2win1251(unsigned char *mic, unsigned char *p, int len); -static void alt2mic(unsigned char *l, unsigned char *p, int len); -static void mic2alt(unsigned char *mic, unsigned char *p, int len); +static void win8662mic(unsigned char *l, unsigned char *p, int len); +static void mic2win866(unsigned char *mic, unsigned char *p, int len); Datum koi8r_to_mic(PG_FUNCTION_ARGS) @@ -176,33 +176,33 @@ mic_to_win1251(PG_FUNCTION_ARGS) } Datum -alt_to_mic(PG_FUNCTION_ARGS) +win866_to_mic(PG_FUNCTION_ARGS) { unsigned char *src = PG_GETARG_CSTRING(2); unsigned char *dest = PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); - Assert(PG_GETARG_INT32(0) == PG_ALT); + Assert(PG_GETARG_INT32(0) == PG_WIN866); Assert(PG_GETARG_INT32(1) == PG_MULE_INTERNAL); Assert(len >= 0); - alt2mic(src, dest, len); + win8662mic(src, dest, len); PG_RETURN_VOID(); } Datum -mic_to_alt(PG_FUNCTION_ARGS) +mic_to_win866(PG_FUNCTION_ARGS) { unsigned char *src = PG_GETARG_CSTRING(2); unsigned char *dest = PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); Assert(PG_GETARG_INT32(0) == PG_MULE_INTERNAL); - Assert(PG_GETARG_INT32(1) == PG_ALT); + Assert(PG_GETARG_INT32(1) == PG_WIN866); Assert(len >= 0); - mic2alt(src, dest, len); + mic2win866(src, dest, len); PG_RETURN_VOID(); } @@ -248,7 +248,7 @@ win1251_to_koi8r(PG_FUNCTION_ARGS) } Datum -koi8r_to_alt(PG_FUNCTION_ARGS) +koi8r_to_win866(PG_FUNCTION_ARGS) { unsigned char *src = PG_GETARG_CSTRING(2); unsigned char *dest = PG_GETARG_CSTRING(3); @@ -256,31 +256,31 @@ koi8r_to_alt(PG_FUNCTION_ARGS) unsigned char *buf; Assert(PG_GETARG_INT32(0) == PG_KOI8R); - Assert(PG_GETARG_INT32(1) == PG_ALT); + Assert(PG_GETARG_INT32(1) == PG_WIN866); Assert(len >= 0); buf = palloc(len * ENCODING_GROWTH_RATE); koi8r2mic(src, buf, len); - mic2alt(buf, dest, strlen(buf)); + mic2win866(buf, dest, strlen(buf)); pfree(buf); PG_RETURN_VOID(); } Datum -alt_to_koi8r(PG_FUNCTION_ARGS) +win866_to_koi8r(PG_FUNCTION_ARGS) { unsigned char *src = PG_GETARG_CSTRING(2); unsigned char *dest = PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); unsigned char *buf; - Assert(PG_GETARG_INT32(0) == PG_ALT); + Assert(PG_GETARG_INT32(0) == PG_WIN866); Assert(PG_GETARG_INT32(1) == PG_KOI8R); Assert(len >= 0); buf = palloc(len * ENCODING_GROWTH_RATE); - alt2mic(src, buf, len); + win8662mic(src, buf, len); mic2koi8r(buf, dest, strlen(buf)); pfree(buf); @@ -288,19 +288,19 @@ alt_to_koi8r(PG_FUNCTION_ARGS) } Datum -alt_to_win1251(PG_FUNCTION_ARGS) +win866_to_win1251(PG_FUNCTION_ARGS) { unsigned char *src = PG_GETARG_CSTRING(2); unsigned char *dest = PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); unsigned char *buf; - Assert(PG_GETARG_INT32(0) == PG_ALT); + Assert(PG_GETARG_INT32(0) == PG_WIN866); Assert(PG_GETARG_INT32(1) == PG_WIN1251); Assert(len >= 0); buf = palloc(len * ENCODING_GROWTH_RATE); - alt2mic(src, buf, len); + win8662mic(src, buf, len); mic2win1251(buf, dest, strlen(buf)); pfree(buf); @@ -308,7 +308,7 @@ alt_to_win1251(PG_FUNCTION_ARGS) } Datum -win1251_to_alt(PG_FUNCTION_ARGS) +win1251_to_win866(PG_FUNCTION_ARGS) { unsigned char *src = PG_GETARG_CSTRING(2); unsigned char *dest = PG_GETARG_CSTRING(3); @@ -316,12 +316,12 @@ win1251_to_alt(PG_FUNCTION_ARGS) unsigned char *buf; Assert(PG_GETARG_INT32(0) == PG_WIN1251); - Assert(PG_GETARG_INT32(1) == PG_ALT); + Assert(PG_GETARG_INT32(1) == PG_WIN866); Assert(len >= 0); buf = palloc(len * ENCODING_GROWTH_RATE); win12512mic(src, buf, len); - mic2alt(buf, dest, strlen(buf)); + mic2win866(buf, dest, strlen(buf)); pfree(buf); PG_RETURN_VOID(); @@ -408,7 +408,7 @@ win1251_to_iso(PG_FUNCTION_ARGS) } Datum -iso_to_alt(PG_FUNCTION_ARGS) +iso_to_win866(PG_FUNCTION_ARGS) { unsigned char *src = PG_GETARG_CSTRING(2); unsigned char *dest = PG_GETARG_CSTRING(3); @@ -416,32 +416,32 @@ iso_to_alt(PG_FUNCTION_ARGS) unsigned char *buf; Assert(PG_GETARG_INT32(0) == PG_ISO_8859_5); - Assert(PG_GETARG_INT32(1) == PG_ALT); + Assert(PG_GETARG_INT32(1) == PG_WIN866); Assert(len >= 0); buf = palloc(len * ENCODING_GROWTH_RATE); iso2mic(src, buf, len); - mic2alt(buf, dest, strlen(buf)); + mic2win866(buf, dest, strlen(buf)); pfree(buf); PG_RETURN_VOID(); } Datum -alt_to_iso(PG_FUNCTION_ARGS) +win866_to_iso(PG_FUNCTION_ARGS) { unsigned char *src = PG_GETARG_CSTRING(2); unsigned char *dest = PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); unsigned char *buf; - Assert(PG_GETARG_INT32(0) == PG_ALT); + Assert(PG_GETARG_INT32(0) == PG_WIN866); Assert(PG_GETARG_INT32(1) == PG_ISO_8859_5); Assert(len >= 0); buf = palloc(len * ENCODING_GROWTH_RATE); - alt2mic(src, buf, len); - mic2alt(buf, dest, strlen(buf)); + win8662mic(src, buf, len); + mic2win866(buf, dest, strlen(buf)); pfree(buf); PG_RETURN_VOID(); @@ -576,11 +576,11 @@ mic2win1251(unsigned char *mic, unsigned char *p, int len) mic2latin_with_table(mic, p, len, LC_KOI8_R, koi2win); } -/* alt2mic: CP866 to Mule internal code */ +/* win8662mic: CP866 to Mule internal code */ static void -alt2mic(unsigned char *l, unsigned char *p, int len) +win8662mic(unsigned char *l, unsigned char *p, int len) { - static unsigned char alt2koi[] = { + static unsigned char win8662koi[] = { 0xe1, 0xe2, 0xf7, 0xe7, 0xe4, 0xe5, 0xf6, 0xfa, 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef, 0xf0, 0xf2, 0xf3, 0xf4, 0xf5, 0xe6, 0xe8, 0xe3, 0xfe, @@ -599,14 +599,14 @@ alt2mic(unsigned char *l, unsigned char *p, int len) 0xb6, 0xa6, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 }; - latin2mic_with_table(l, p, len, LC_KOI8_R, alt2koi); + latin2mic_with_table(l, p, len, LC_KOI8_R, win8662koi); } -/* mic2alt: Mule internal code to CP866 */ +/* mic2win866: Mule internal code to CP866 */ static void -mic2alt(unsigned char *mic, unsigned char *p, int len) +mic2win866(unsigned char *mic, unsigned char *p, int len) { - static unsigned char koi2alt[] = { + static unsigned char koi2win866[] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, @@ -625,5 +625,5 @@ mic2alt(unsigned char *mic, unsigned char *p, int len) 0x9c, 0x9b, 0x87, 0x98, 0x9d, 0x99, 0x97, 0x9a }; - mic2latin_with_table(mic, p, len, LC_KOI8_R, koi2alt); + mic2latin_with_table(mic, p, len, LC_KOI8_R, koi2win866); } diff --git a/src/backend/utils/mb/conversion_procs/regress_prolog b/src/backend/utils/mb/conversion_procs/regress_prolog index 5136019d62..f5c71790cf 100644 --- a/src/backend/utils/mb/conversion_procs/regress_prolog +++ b/src/backend/utils/mb/conversion_procs/regress_prolog @@ -3,19 +3,19 @@ -- CREATE USER conversion_test_user WITH NOCREATEDB NOCREATEUSER; SET SESSION AUTHORIZATION conversion_test_user; -CREATE CONVERSION myconv FOR 'LATIN1' TO 'UNICODE' FROM iso8859_1_to_utf8; +CREATE CONVERSION myconv FOR 'LATIN1' TO 'UTF8' FROM iso8859_1_to_utf8; -- -- cannot make same name conversion in same schema -- -CREATE CONVERSION myconv FOR 'LATIN1' TO 'UNICODE' FROM iso8859_1_to_utf8; +CREATE CONVERSION myconv FOR 'LATIN1' TO 'UTF8' FROM iso8859_1_to_utf8; -- -- create default conversion with qualified name -- -CREATE DEFAULT CONVERSION public.mydef FOR 'LATIN1' TO 'UNICODE' FROM iso8859_1_to_utf8; +CREATE DEFAULT CONVERSION public.mydef FOR 'LATIN1' TO 'UTF8' FROM iso8859_1_to_utf8; -- -- cannot make default conversion with same shcema/for_encoding/to_encoding -- -CREATE DEFAULT CONVERSION public.mydef2 FOR 'LATIN1' TO 'UNICODE' FROM iso8859_1_to_utf8; +CREATE DEFAULT CONVERSION public.mydef2 FOR 'LATIN1' TO 'UTF8' FROM iso8859_1_to_utf8; -- -- drop user defined conversion -- diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_ascii/utf8_and_ascii.c b/src/backend/utils/mb/conversion_procs/utf8_and_ascii/utf8_and_ascii.c index 446277fc2d..786c8a6719 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_ascii/utf8_and_ascii.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_ascii/utf8_and_ascii.c @@ -1,6 +1,6 @@ /*------------------------------------------------------------------------- * - * ASCII <--> UTF-8 + * ASCII <--> UTF8 * * Portions Copyright (c) 1996-2005, PostgreSQL Global Development Group * Portions Copyright (c) 1994, Regents of the University of California diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c b/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c index c8382a314e..1df624da9b 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c @@ -1,6 +1,6 @@ /*------------------------------------------------------------------------- * - * BIG5 <--> UTF-8 + * BIG5 <--> UTF8 * * Portions Copyright (c) 1996-2005, PostgreSQL Global Development Group * Portions Copyright (c) 1994, Regents of the University of California diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c b/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c index 2a44db85f0..81841c55ce 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c @@ -18,22 +18,22 @@ #include "../../Unicode/koi8r_to_utf8.map" #include "../../Unicode/utf8_to_win1251.map" #include "../../Unicode/win1251_to_utf8.map" -#include "../../Unicode/utf8_to_alt.map" -#include "../../Unicode/alt_to_utf8.map" +#include "../../Unicode/utf8_to_win866.map" +#include "../../Unicode/win866_to_utf8.map" PG_FUNCTION_INFO_V1(utf8_to_koi8r); PG_FUNCTION_INFO_V1(koi8r_to_utf8); PG_FUNCTION_INFO_V1(utf8_to_win1251); PG_FUNCTION_INFO_V1(win1251_to_utf8); -PG_FUNCTION_INFO_V1(utf8_to_alt); -PG_FUNCTION_INFO_V1(alt_to_utf8); +PG_FUNCTION_INFO_V1(utf8_to_win866); +PG_FUNCTION_INFO_V1(win866_to_utf8); extern Datum utf8_to_koi8r(PG_FUNCTION_ARGS); extern Datum koi8r_to_utf8(PG_FUNCTION_ARGS); extern Datum utf8_to_win1251(PG_FUNCTION_ARGS); extern Datum win1251_to_utf8(PG_FUNCTION_ARGS); -extern Datum utf8_to_alt(PG_FUNCTION_ARGS); -extern Datum alt_to_utf8(PG_FUNCTION_ARGS); +extern Datum utf8_to_win866(PG_FUNCTION_ARGS); +extern Datum win866_to_utf8(PG_FUNCTION_ARGS); /* ---------- * conv_proc( @@ -115,35 +115,35 @@ win1251_to_utf8(PG_FUNCTION_ARGS) } Datum -utf8_to_alt(PG_FUNCTION_ARGS) +utf8_to_win866(PG_FUNCTION_ARGS) { unsigned char *src = PG_GETARG_CSTRING(2); unsigned char *dest = PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); Assert(PG_GETARG_INT32(0) == PG_UTF8); - Assert(PG_GETARG_INT32(1) == PG_ALT); + Assert(PG_GETARG_INT32(1) == PG_WIN866); Assert(len >= 0); - UtfToLocal(src, dest, ULmap_ALT, - sizeof(ULmap_ALT) / sizeof(pg_utf_to_local), len); + UtfToLocal(src, dest, ULmap_WIN866, + sizeof(ULmap_WIN866) / sizeof(pg_utf_to_local), len); PG_RETURN_VOID(); } Datum -alt_to_utf8(PG_FUNCTION_ARGS) +win866_to_utf8(PG_FUNCTION_ARGS) { unsigned char *src = PG_GETARG_CSTRING(2); unsigned char *dest = PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); - Assert(PG_GETARG_INT32(0) == PG_ALT); + Assert(PG_GETARG_INT32(0) == PG_WIN866); Assert(PG_GETARG_INT32(1) == PG_UTF8); Assert(len >= 0); - LocalToUtf(src, dest, LUmapALT, - sizeof(LUmapALT) / sizeof(pg_local_to_utf), PG_ALT, len); + LocalToUtf(src, dest, LUmapWIN866, + sizeof(LUmapWIN866) / sizeof(pg_local_to_utf), PG_WIN866, len); PG_RETURN_VOID(); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c index eca4bbac5a..a6c1dd81ae 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c @@ -1,6 +1,6 @@ /*------------------------------------------------------------------------- * - * EUC_CN <--> UTF-8 + * EUC_CN <--> UTF8 * * Portions Copyright (c) 1996-2005, PostgreSQL Global Development Group * Portions Copyright (c) 1994, Regents of the University of California diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c index 9f59ce8358..7049e87de1 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c @@ -1,6 +1,6 @@ /*------------------------------------------------------------------------- * - * EUC_JP <--> UTF-8 + * EUC_JP <--> UTF8 * * Portions Copyright (c) 1996-2005, PostgreSQL Global Development Group * Portions Copyright (c) 1994, Regents of the University of California diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c index 9f772624f7..d1de46d368 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c @@ -1,6 +1,6 @@ /*------------------------------------------------------------------------- * - * EUC_KR <--> UTF-8 + * EUC_KR <--> UTF8 * * Portions Copyright (c) 1996-2005, PostgreSQL Global Development Group * Portions Copyright (c) 1994, Regents of the University of California diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c index b2f088c9a3..64bfffd46f 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c @@ -1,6 +1,6 @@ /*------------------------------------------------------------------------- * - * EUC_TW <--> UTF-8 + * EUC_TW <--> UTF8 * * Portions Copyright (c) 1996-2005, PostgreSQL Global Development Group * Portions Copyright (c) 1994, Regents of the University of California diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c b/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c index 7f7b4625d8..2af3ae45a2 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c @@ -1,6 +1,6 @@ /*------------------------------------------------------------------------- * - * GB18030 <--> UTF-8 + * GB18030 <--> UTF8 * * Portions Copyright (c) 1996-2005, PostgreSQL Global Development Group * Portions Copyright (c) 1994, Regents of the University of California diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c b/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c index 39ff56aaf8..1c8b42362d 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c @@ -1,6 +1,6 @@ /*------------------------------------------------------------------------- * - * GBK <--> UTF-8 + * GBK <--> UTF8 * * Portions Copyright (c) 1996-2005, PostgreSQL Global Development Group * Portions Copyright (c) 1994, Regents of the University of California diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c index 9da468a056..be07e339b8 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c @@ -1,6 +1,6 @@ /*------------------------------------------------------------------------- * - * ISO 8859 2-16 <--> UTF-8 + * ISO 8859 2-16 <--> UTF8 * * Portions Copyright (c) 1996-2005, PostgreSQL Global Development Group * Portions Copyright (c) 1994, Regents of the University of California @@ -61,8 +61,8 @@ extern Datum utf8_to_iso8859(PG_FUNCTION_ARGS); typedef struct { pg_enc encoding; - pg_local_to_utf *map1; /* to UTF-8 map name */ - pg_utf_to_local *map2; /* from UTF-8 map name */ + pg_local_to_utf *map1; /* to UTF8 map name */ + pg_utf_to_local *map2; /* from UTF8 map name */ int size1; /* size of map1 */ int size2; /* size of map2 */ } pg_conv_map; @@ -74,7 +74,7 @@ static pg_conv_map maps[] = { {PG_EUC_KR}, /* EUC for Korean */ {PG_EUC_TW}, /* EUC for Taiwan */ {PG_JOHAB}, /* EUC for Korean JOHAB */ - {PG_UTF8}, /* Unicode UTF-8 */ + {PG_UTF8}, /* Unicode UTF8 */ {PG_MULE_INTERNAL}, /* Mule internal code */ {PG_LATIN1}, /* ISO-8859-1 Latin 1 */ {PG_LATIN2, LUmapISO8859_2, ULmapISO8859_2, @@ -105,11 +105,11 @@ static pg_conv_map maps[] = { sizeof(LUmapISO8859_16) / sizeof(pg_local_to_utf), sizeof(ULmapISO8859_16) / sizeof(pg_utf_to_local)}, /* ISO-8859-16 Latin 10 */ {PG_WIN1256}, /* windows-1256 */ - {PG_TCVN}, /* TCVN (Windows-1258) */ + {PG_WIN1258}, /* Windows-1258 */ {PG_WIN874}, /* windows-874 */ {PG_KOI8R}, /* KOI8-R */ {PG_WIN1251}, /* windows-1251 (was: WIN) */ - {PG_ALT}, /* (MS-DOS CP866) */ + {PG_WIN866}, /* (MS-DOS CP866) */ {PG_ISO_8859_5, LUmapISO8859_5, ULmapISO8859_5, sizeof(LUmapISO8859_5) / sizeof(pg_local_to_utf), sizeof(ULmapISO8859_5) / sizeof(pg_utf_to_local)}, /* ISO-8859-5 */ diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c index 9265c807c6..01e04cc4ca 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c @@ -1,6 +1,6 @@ /*------------------------------------------------------------------------- * - * ISO8859_1 <--> UTF-8 + * ISO8859_1 <--> UTF8 * * Portions Copyright (c) 1996-2005, PostgreSQL Global Development Group * Portions Copyright (c) 1994, Regents of the University of California @@ -84,7 +84,7 @@ utf8_to_iso8859_1(PG_FUNCTION_ARGS) len -= 2; } else if ((c & 0xe0) == 0xe0) - elog(ERROR, "could not convert UTF-8 character 0x%04x to ISO8859-1", + elog(ERROR, "could not convert UTF8 character 0x%04x to ISO8859-1", c); else { diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c b/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c index 7a8f6db907..b3cf6f1df7 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c @@ -1,6 +1,6 @@ /*------------------------------------------------------------------------- * - * JOHAB <--> UTF-8 + * JOHAB <--> UTF8 * * Portions Copyright (c) 1996-2005, PostgreSQL Global Development Group * Portions Copyright (c) 1994, Regents of the University of California diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c b/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c index e56124aaad..9cbf38186d 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c @@ -1,6 +1,6 @@ /*------------------------------------------------------------------------- * - * SJIS <--> UTF-8 + * SJIS <--> UTF8 * * Portions Copyright (c) 1996-2005, PostgreSQL Global Development Group * Portions Copyright (c) 1994, Regents of the University of California diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c b/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c index f311f4936a..044478238d 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c @@ -1,6 +1,6 @@ /*------------------------------------------------------------------------- * - * UHC <--> UTF-8 + * UHC <--> UTF8 * * Portions Copyright (c) 1996-2005, PostgreSQL Global Development Group * Portions Copyright (c) 1994, Regents of the University of California diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_win1250/utf8_and_win1250.c b/src/backend/utils/mb/conversion_procs/utf8_and_win1250/utf8_and_win1250.c index 7448e507f8..cfca3796f1 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_win1250/utf8_and_win1250.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_win1250/utf8_and_win1250.c @@ -1,6 +1,6 @@ /*------------------------------------------------------------------------- * - * WIN1250 and UTF-8 + * WIN1250 and UTF8 * * Portions Copyright (c) 1996-2005, PostgreSQL Global Development Group * Portions Copyright (c) 1994, Regents of the University of California diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_win1256/utf8_and_win1256.c b/src/backend/utils/mb/conversion_procs/utf8_and_win1256/utf8_and_win1256.c index 2e15022eb3..6a3fccffb7 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_win1256/utf8_and_win1256.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_win1256/utf8_and_win1256.c @@ -1,6 +1,6 @@ /*------------------------------------------------------------------------- * - * WIN1256 and UTF-8 + * WIN1256 and UTF8 * * Portions Copyright (c) 1996-2005, PostgreSQL Global Development Group * Portions Copyright (c) 1994, Regents of the University of California diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_tcvn/Makefile b/src/backend/utils/mb/conversion_procs/utf8_and_win1258/Makefile index 3ba33503e0..f0e9d70cb2 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_tcvn/Makefile +++ b/src/backend/utils/mb/conversion_procs/utf8_and_win1258/Makefile @@ -7,6 +7,6 @@ subdir = src/backend/utils/mb/conversion_procs/utf8_and_tcvn top_builddir = ../../../../../.. include $(top_builddir)/src/Makefile.global -NAME := utf8_and_tcvn +NAME := utf8_and_win1258 include $(srcdir)/../proc.mk diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_tcvn/utf8_and_tcvn.c b/src/backend/utils/mb/conversion_procs/utf8_and_win1258/utf8_and_win1258.c index 892951196c..a33e5a14ae 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_tcvn/utf8_and_tcvn.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_win1258/utf8_and_win1258.c @@ -1,6 +1,6 @@ /*------------------------------------------------------------------------- * - * TCVN <--> UTF-8 + * WIN1258 <--> UTF8 * * Portions Copyright (c) 1996-2005, PostgreSQL Global Development Group * Portions Copyright (c) 1994, Regents of the University of California @@ -14,14 +14,14 @@ #include "postgres.h" #include "fmgr.h" #include "mb/pg_wchar.h" -#include "../../Unicode/tcvn_to_utf8.map" -#include "../../Unicode/utf8_to_tcvn.map" +#include "../../Unicode/win1258_to_utf8.map" +#include "../../Unicode/utf8_to_win1258.map" -PG_FUNCTION_INFO_V1(tcvn_to_utf8); -PG_FUNCTION_INFO_V1(utf8_to_tcvn); +PG_FUNCTION_INFO_V1(win1258_to_utf8); +PG_FUNCTION_INFO_V1(utf8_to_win1258); -extern Datum tcvn_to_utf8(PG_FUNCTION_ARGS); -extern Datum utf8_to_tcvn(PG_FUNCTION_ARGS); +extern Datum win1258_to_utf8(PG_FUNCTION_ARGS); +extern Datum utf8_to_win1258(PG_FUNCTION_ARGS); /* ---------- * conv_proc( @@ -34,35 +34,35 @@ extern Datum utf8_to_tcvn(PG_FUNCTION_ARGS); * ---------- */ Datum -tcvn_to_utf8(PG_FUNCTION_ARGS) +win1258_to_utf8(PG_FUNCTION_ARGS) { unsigned char *src = PG_GETARG_CSTRING(2); unsigned char *dest = PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); - Assert(PG_GETARG_INT32(0) == PG_TCVN); + Assert(PG_GETARG_INT32(0) == PG_WIN1258); Assert(PG_GETARG_INT32(1) == PG_UTF8); Assert(len >= 0); - LocalToUtf(src, dest, LUmapTCVN, - sizeof(LUmapTCVN) / sizeof(pg_local_to_utf), PG_TCVN, len); + LocalToUtf(src, dest, LUmapWIN1258, + sizeof(LUmapWIN1258) / sizeof(pg_local_to_utf), PG_WIN1258, len); PG_RETURN_VOID(); } Datum -utf8_to_tcvn(PG_FUNCTION_ARGS) +utf8_to_win1258(PG_FUNCTION_ARGS) { unsigned char *src = PG_GETARG_CSTRING(2); unsigned char *dest = PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); Assert(PG_GETARG_INT32(0) == PG_UTF8); - Assert(PG_GETARG_INT32(1) == PG_TCVN); + Assert(PG_GETARG_INT32(1) == PG_WIN1258); Assert(len >= 0); - UtfToLocal(src, dest, ULmapTCVN, - sizeof(ULmapTCVN) / sizeof(pg_utf_to_local), len); + UtfToLocal(src, dest, ULmapWIN1258, + sizeof(ULmapWIN1258) / sizeof(pg_utf_to_local), len); PG_RETURN_VOID(); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_win874/utf8_and_win874.c b/src/backend/utils/mb/conversion_procs/utf8_and_win874/utf8_and_win874.c index b866b190f6..78cb1a3306 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_win874/utf8_and_win874.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_win874/utf8_and_win874.c @@ -1,6 +1,6 @@ /*------------------------------------------------------------------------- * - * WIN874 and UTF-8 + * WIN874 and UTF8 * * Portions Copyright (c) 1996-2005, PostgreSQL Global Development Group * Portions Copyright (c) 1994, Regents of the University of California diff --git a/src/backend/utils/mb/encnames.c b/src/backend/utils/mb/encnames.c index 31b491a782..f83e102298 100644 --- a/src/backend/utils/mb/encnames.c +++ b/src/backend/utils/mb/encnames.c @@ -27,7 +27,7 @@ * isalnum() chars only. It means ISO-8859-1, iso_8859-1 and Iso8859_1 * are always converted to 'iso88591'. All must be lower case. * - * The table doesn't contain 'cs' aliases (like csISOLatin1). It's needful? + * The table doesn't contain 'cs' aliases (like csISOLatin1). It's needed? * * Karel Zak, Aug 2001 * ---------- @@ -35,10 +35,10 @@ pg_encname pg_encname_tbl[] = { { - "abc", PG_TCVN - }, /* alias for TCVN */ + "abc", PG_WIN1258 + }, /* alias for WIN1258 */ { - "alt", PG_ALT + "alt", PG_WIN866 }, /* IBM866 */ { "big5", PG_BIG5 @@ -166,23 +166,26 @@ pg_encname pg_encname_tbl[] = "sqlascii", PG_SQL_ASCII }, { - "tcvn", PG_TCVN - }, /* TCVN; Vietnamese TCVN-5712 */ + "tcvn", PG_WIN1258 + }, /* alias for WIN1258 */ { - "tcvn5712", PG_TCVN - }, /* alias for TCVN */ + "tcvn5712", PG_WIN1258 + }, /* alias for WIN1258 */ { "uhc", PG_UHC }, /* UHC; Korean Windows CodePage 949 */ { "unicode", PG_UTF8 - }, /* alias for UTF-8 */ + }, /* alias for UTF8 */ + { + "utf-8", PG_UTF8 + }, /* UTF8; RFC2279 */ { "utf8", PG_UTF8 - }, /* UTF-8; RFC2279 */ + }, /* alias for UTF8 */ { - "vscii", PG_TCVN - }, /* alias for TCVN */ + "vscii", PG_WIN1258 + }, /* alias for WIN1258 */ { "win", PG_WIN1251 }, /* _dirty_ alias for windows-1251 @@ -197,9 +200,12 @@ pg_encname pg_encname_tbl[] = "win1256", PG_WIN1256 }, /* alias for Windows-1256 */ { - "win1258", PG_TCVN + "win1258", PG_WIN1258 }, /* alias for Windows-1258 */ { + "win866", PG_WIN866 + }, /* IBM866 */ + { "win874", PG_WIN874 }, /* alias for Windows-874 */ { @@ -224,9 +230,12 @@ pg_encname pg_encname_tbl[] = "windows1256", PG_WIN1256 }, /* Windows-1256; Microsoft */ { - "windows1258", PG_TCVN + "windows1258", PG_WIN1258 }, /* Windows-1258; Microsoft */ { + "windows866", PG_WIN866 + }, /* IBM866 */ + { "windows874", PG_WIN874 }, /* Windows-874; Microsoft */ { @@ -275,7 +284,7 @@ pg_enc2name pg_enc2name_tbl[] = "JOHAB", PG_JOHAB }, { - "UNICODE", PG_UTF8 + "UTF8", PG_UTF8 }, { "MULE_INTERNAL", PG_MULE_INTERNAL @@ -314,19 +323,19 @@ pg_enc2name pg_enc2name_tbl[] = "WIN1256", PG_WIN1256 }, { - "TCVN", PG_TCVN + "WIN1258", PG_WIN1258 }, { - "WIN874", PG_WIN874 + "WIN866", PG_WIN866 }, { - "KOI8", PG_KOI8R + "WIN874", PG_WIN874 }, { - "WIN", PG_WIN1251 + "KOI8", PG_KOI8R }, { - "ALT", PG_ALT + "WIN1251", PG_WIN1251 }, { "ISO_8859_5", PG_ISO_8859_5 diff --git a/src/backend/utils/mb/mbutils.c b/src/backend/utils/mb/mbutils.c index 4393da9567..5034271a5c 100644 --- a/src/backend/utils/mb/mbutils.c +++ b/src/backend/utils/mb/mbutils.c @@ -222,7 +222,7 @@ pg_get_client_encoding_name(void) * * XXX We assume that storage for converted result is 4-to-1 growth in * the worst case. The rate for currently supported encoding pares are within 3 - * (SJIS JIS X0201 half width kanna -> UTF-8 is the worst case). + * (SJIS JIS X0201 half width kanna -> UTF8 is the worst case). * So "4" should be enough for the moment. */ unsigned char * diff --git a/src/backend/utils/mb/wchar.c b/src/backend/utils/mb/wchar.c index d3892f1b95..c4730566ad 100644 --- a/src/backend/utils/mb/wchar.c +++ b/src/backend/utils/mb/wchar.c @@ -344,7 +344,7 @@ pg_johab_dsplen(const unsigned char *s) } /* - * convert UTF-8 string to pg_wchar (UCS-2) + * convert UTF8 string to pg_wchar (UCS-2) * caller should allocate enough space for "to" * len: length of from. * "from" not necessarily null terminated. @@ -395,7 +395,7 @@ pg_utf2wchar_with_len(const unsigned char *from, pg_wchar *to, int len) } /* - * returns the byte length of a UTF-8 word pointed to by s + * returns the byte length of a UTF8 word pointed to by s */ int pg_utf_mblen(const unsigned char *s) @@ -721,8 +721,8 @@ pg_wchar_tbl pg_wchar_table[] = { {pg_euckr2wchar_with_len, pg_euckr_mblen, pg_euckr_dsplen, 3}, /* 3; PG_EUC_KR */ {pg_euctw2wchar_with_len, pg_euctw_mblen, pg_euctw_dsplen, 3}, /* 4; PG_EUC_TW */ {pg_johab2wchar_with_len, pg_johab_mblen, pg_johab_dsplen, 3}, /* 5; PG_JOHAB */ - {pg_utf2wchar_with_len, pg_utf_mblen, pg_utf_dsplen, 3}, /* 6; PG_UNICODE */ - {pg_mule2wchar_with_len, pg_mule_mblen, pg_mule_dsplen, 3}, /* 7; PG_MULE_INTERNAL */ + {pg_utf2wchar_with_len, pg_utf_mblen, pg_utf_dsplen, 3}, /* 6; PG_UTF8 */ + {pg_mule2wchar_with_len, pg_mule_mblen, pg_mule_dsplen, 3}, /* 7; PG_MULE_INTERNAL */ {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, 1}, /* 8; PG_LATIN1 */ {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, 1}, /* 9; PG_LATIN2 */ {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, 1}, /* 10; PG_LATIN3 */ @@ -822,7 +822,7 @@ pg_verifymbstr(const unsigned char *mbstr, int len, bool noError) while (len > 0 && *mbstr) { - /* special UTF-8 check */ + /* special UTF8 check */ if (encoding == PG_UTF8 && (*mbstr & 0xf8) == 0xf0) { if (noError) diff --git a/src/backend/utils/mb/win.c b/src/backend/utils/mb/win.c deleted file mode 100644 index e281a472d0..0000000000 --- a/src/backend/utils/mb/win.c +++ /dev/null @@ -1,74 +0,0 @@ -/* - * make KOI8->CP1251(win-1251) and CP1251(win-1251)->KOI8 translation table - * from koi-win.tab. - * - * Tatsuo Ishii - * - * $PostgreSQL$ - */ - -#include <stdio.h> - - -main() -{ - int i; - char koitab[128], - wintab[128]; - char buf[4096]; - int koi, - win; - - for (i = 0; i < 128; i++) - koitab[i] = wintab[i] = 0; - - while (fgets(buf, sizeof(buf), stdin) != NULL) - { - if (*buf == '#') - continue; - sscanf(buf, "%d %d", &koi, &win); - if (koi < 128 || koi > 255 || win < 128 || win > 255) - { - fprintf(stderr, "invalid value %d\n", koi); - exit(1); - } - koitab[koi - 128] = win; - wintab[win - 128] = koi; - } - - i = 0; - printf("static char koi2win[] = {\n"); - while (i < 128) - { - int j = 0; - - while (j < 8) - { - printf("0x%02x", koitab[i++]); - j++; - if (i >= 128) - break; - printf(", "); - } - printf("\n"); - } - printf("};\n"); - - i = 0; - printf("static char win2koi[] = {\n"); - while (i < 128) - { - int j = 0; - - while (j < 8) - { - printf("0x%02x", wintab[i++]); - j++; - if (i >= 128) - break; - printf(", "); - } - printf("\n"); - } - printf("};\n"); -} diff --git a/src/backend/utils/mb/alt.c b/src/backend/utils/mb/win866.c index 6504e4a1c0..6504e4a1c0 100644 --- a/src/backend/utils/mb/alt.c +++ b/src/backend/utils/mb/win866.c diff --git a/src/bin/initdb/initdb.c b/src/bin/initdb/initdb.c index 0288cc49be..00756856ab 100644 --- a/src/bin/initdb/initdb.c +++ b/src/bin/initdb/initdb.c @@ -723,7 +723,7 @@ struct encoding_match encoding_match_list[] = { {PG_JOHAB, "???"}, #endif - {PG_UTF8, "UTF-8"}, + {PG_UTF8, "UTF8"}, {PG_UTF8, "utf8"}, {PG_LATIN1, "ISO-8859-1"}, @@ -767,13 +767,13 @@ struct encoding_match encoding_match_list[] = { {PG_LATIN10, "iso885916"}, {PG_WIN1256, "CP1256"}, - {PG_TCVN, "CP1258"}, + {PG_WIN1258, "CP1258"}, #ifdef NOT_VERIFIED {PG_WIN874, "???"}, #endif {PG_KOI8R, "KOI8-R"}, {PG_WIN1251, "CP1251"}, - {PG_ALT, "CP866"}, + {PG_WIN866, "CP866"}, {PG_ISO_8859_5, "ISO-8859-5"}, {PG_ISO_8859_5, "ISO8859-5"}, diff --git a/src/include/mb/pg_wchar.h b/src/include/mb/pg_wchar.h index e93a438d97..0601b16d3e 100644 --- a/src/include/mb/pg_wchar.h +++ b/src/include/mb/pg_wchar.h @@ -155,7 +155,7 @@ typedef enum pg_enc PG_EUC_KR, /* EUC for Korean */ PG_EUC_TW, /* EUC for Taiwan */ PG_JOHAB, /* EUC for Korean JOHAB */ - PG_UTF8, /* Unicode UTF-8 */ + PG_UTF8, /* Unicode UTF8 */ PG_MULE_INTERNAL, /* Mule internal code */ PG_LATIN1, /* ISO-8859-1 Latin 1 */ PG_LATIN2, /* ISO-8859-2 Latin 2 */ @@ -168,11 +168,11 @@ typedef enum pg_enc PG_LATIN9, /* ISO-8859-15 Latin9 */ PG_LATIN10, /* ISO-8859-16 Latin10 */ PG_WIN1256, /* windows-1256 */ - PG_TCVN, /* TCVN (Windows-1258) */ + PG_WIN1258, /* Windows-1258 */ + PG_WIN866, /* (MS-DOS CP866) */ PG_WIN874, /* windows-874 */ PG_KOI8R, /* KOI8-R */ PG_WIN1251, /* windows-1251 (was: WIN) */ - PG_ALT, /* (MS-DOS CP866) */ PG_ISO_8859_5, /* ISO-8859-5 */ PG_ISO_8859_6, /* ISO-8859-6 */ PG_ISO_8859_7, /* ISO-8859-7 */ @@ -263,21 +263,21 @@ typedef struct extern pg_wchar_tbl pg_wchar_table[]; /* - * UTF-8 to local code conversion map + * UTF8 to local code conversion map */ typedef struct { - unsigned int utf; /* UTF-8 */ + unsigned int utf; /* UTF8 */ unsigned int code; /* local code */ } pg_utf_to_local; /* - * local code to UTF-8 conversion map + * local code to UTF8 conversion map */ typedef struct { unsigned int code; /* local code */ - unsigned int utf; /* UTF-8 */ + unsigned int utf; /* UTF8 */ } pg_local_to_utf; extern int pg_mb2wchar(const unsigned char *from, pg_wchar *to); diff --git a/src/test/mb/mbregress.sh b/src/test/mb/mbregress.sh index 3780d0c61b..cb306d0952 100644 --- a/src/test/mb/mbregress.sh +++ b/src/test/mb/mbregress.sh @@ -15,10 +15,10 @@ if [ ! -d results ];then fi dropdb unitest -createdb -E UNICODE unitest +createdb -E UTF8 unitest PSQL="psql -n -e -q" -tests="euc_jp sjis euc_kr euc_cn euc_tw big5 unicode mule_internal" +tests="euc_jp sjis euc_kr euc_cn euc_tw big5 utf8 mule_internal" unset PGCLIENTENCODING for i in $tests do diff --git a/src/test/regress/expected/conversion.out b/src/test/regress/expected/conversion.out index c0e85b85a1..ea2984a227 100644 --- a/src/test/regress/expected/conversion.out +++ b/src/test/regress/expected/conversion.out @@ -3,21 +3,21 @@ -- CREATE USER conversion_test_user WITH NOCREATEDB NOCREATEUSER; SET SESSION AUTHORIZATION conversion_test_user; -CREATE CONVERSION myconv FOR 'LATIN1' TO 'UNICODE' FROM iso8859_1_to_utf8; +CREATE CONVERSION myconv FOR 'LATIN1' TO 'UTF8' FROM iso8859_1_to_utf8; -- -- cannot make same name conversion in same schema -- -CREATE CONVERSION myconv FOR 'LATIN1' TO 'UNICODE' FROM iso8859_1_to_utf8; +CREATE CONVERSION myconv FOR 'LATIN1' TO 'UTF8' FROM iso8859_1_to_utf8; ERROR: conversion "myconv" already exists -- -- create default conversion with qualified name -- -CREATE DEFAULT CONVERSION public.mydef FOR 'LATIN1' TO 'UNICODE' FROM iso8859_1_to_utf8; +CREATE DEFAULT CONVERSION public.mydef FOR 'LATIN1' TO 'UTF8' FROM iso8859_1_to_utf8; -- -- cannot make default conversion with same shcema/for_encoding/to_encoding -- -CREATE DEFAULT CONVERSION public.mydef2 FOR 'LATIN1' TO 'UNICODE' FROM iso8859_1_to_utf8; -ERROR: default conversion for LATIN1 to UNICODE already exists +CREATE DEFAULT CONVERSION public.mydef2 FOR 'LATIN1' TO 'UTF8' FROM iso8859_1_to_utf8; +ERROR: default conversion for LATIN1 to UTF8 already exists -- test comments COMMENT ON CONVERSION myconv_bad IS 'foo'; ERROR: conversion "myconv_bad" does not exist @@ -134,27 +134,27 @@ SELECT CONVERT('foo', 'MULE_INTERNAL', 'WIN1251'); foo (1 row) --- ALT --> MULE_INTERNAL +-- WIN866 --> MULE_INTERNAL SELECT CONVERT('foo' USING windows_866_to_mic); convert_using --------------- foo (1 row) -SELECT CONVERT('foo', 'ALT', 'MULE_INTERNAL'); +SELECT CONVERT('foo', 'WIN866', 'MULE_INTERNAL'); convert --------- foo (1 row) --- MULE_INTERNAL --> ALT +-- MULE_INTERNAL --> WIN866 SELECT CONVERT('foo' USING mic_to_windows_866); convert_using --------------- foo (1 row) -SELECT CONVERT('foo', 'MULE_INTERNAL', 'ALT'); +SELECT CONVERT('foo', 'MULE_INTERNAL', 'WIN866'); convert --------- foo @@ -186,53 +186,53 @@ SELECT CONVERT('foo', 'WIN1251', 'KOI8R'); foo (1 row) --- KOI8R --> ALT +-- KOI8R --> WIN866 SELECT CONVERT('foo' USING koi8_r_to_windows_866); convert_using --------------- foo (1 row) -SELECT CONVERT('foo', 'KOI8R', 'ALT'); +SELECT CONVERT('foo', 'KOI8R', 'WIN866'); convert --------- foo (1 row) --- ALT --> KOI8R +-- WIN866 --> KOI8R SELECT CONVERT('foo' USING windows_866_to_koi8_r); convert_using --------------- foo (1 row) -SELECT CONVERT('foo', 'ALT', 'KOI8R'); +SELECT CONVERT('foo', 'WIN866', 'KOI8R'); convert --------- foo (1 row) --- ALT --> WIN1251 +-- WIN866 --> WIN1251 SELECT CONVERT('foo' USING windows_866_to_windows_1251); convert_using --------------- foo (1 row) -SELECT CONVERT('foo', 'ALT', 'WIN1251'); +SELECT CONVERT('foo', 'WIN866', 'WIN1251'); convert --------- foo (1 row) --- WIN1251 --> ALT +-- WIN1251 --> WIN866 SELECT CONVERT('foo' USING windows_1251_to_windows_866); convert_using --------------- foo (1 row) -SELECT CONVERT('foo', 'WIN1251', 'ALT'); +SELECT CONVERT('foo', 'WIN1251', 'WIN866'); convert --------- foo @@ -290,27 +290,27 @@ SELECT CONVERT('foo', 'WIN1251', 'ISO-8859-5'); foo (1 row) --- ISO-8859-5 --> ALT +-- ISO-8859-5 --> WIN866 SELECT CONVERT('foo' USING iso_8859_5_to_windows_866); convert_using --------------- foo (1 row) -SELECT CONVERT('foo', 'ISO-8859-5', 'ALT'); +SELECT CONVERT('foo', 'ISO-8859-5', 'WIN866'); convert --------- foo (1 row) --- ALT --> ISO-8859-5 +-- WIN866 --> ISO-8859-5 SELECT CONVERT('foo' USING windows_866_to_iso_8859_5); convert_using --------------- foo (1 row) -SELECT CONVERT('foo', 'ALT', 'ISO-8859-5'); +SELECT CONVERT('foo', 'WIN866', 'ISO-8859-5'); convert --------- foo @@ -680,833 +680,833 @@ SELECT CONVERT('foo', 'MULE_INTERNAL', 'LATIN4'); foo (1 row) --- SQL_ASCII --> UNICODE -SELECT CONVERT('foo' USING ascii_to_utf_8); +-- SQL_ASCII --> UTF8 +SELECT CONVERT('foo' USING ascii_to_utf8); convert_using --------------- foo (1 row) -SELECT CONVERT('foo', 'SQL_ASCII', 'UNICODE'); +SELECT CONVERT('foo', 'SQL_ASCII', 'UTF8'); convert --------- foo (1 row) --- UNICODE --> SQL_ASCII -SELECT CONVERT('foo' USING utf_8_to_ascii); +-- UTF8 --> SQL_ASCII +SELECT CONVERT('foo' USING utf8_to_ascii); convert_using --------------- foo (1 row) -SELECT CONVERT('foo', 'UNICODE', 'SQL_ASCII'); +SELECT CONVERT('foo', 'UTF8', 'SQL_ASCII'); convert --------- foo (1 row) --- BIG5 --> UNICODE -SELECT CONVERT('foo' USING big5_to_utf_8); +-- BIG5 --> UTF8 +SELECT CONVERT('foo' USING big5_to_utf8); convert_using --------------- foo (1 row) -SELECT CONVERT('foo', 'BIG5', 'UNICODE'); +SELECT CONVERT('foo', 'BIG5', 'UTF8'); convert --------- foo (1 row) --- UNICODE --> BIG5 -SELECT CONVERT('foo' USING utf_8_to_big5); +-- UTF8 --> BIG5 +SELECT CONVERT('foo' USING utf8_to_big5); convert_using --------------- foo (1 row) -SELECT CONVERT('foo', 'UNICODE', 'BIG5'); +SELECT CONVERT('foo', 'UTF8', 'BIG5'); convert --------- foo (1 row) --- UNICODE --> KOI8R -SELECT CONVERT('foo' USING utf_8_to_koi8_r); +-- UTF8 --> KOI8R +SELECT CONVERT('foo' USING utf8_to_koi8_r); convert_using --------------- foo (1 row) -SELECT CONVERT('foo', 'UNICODE', 'KOI8R'); +SELECT CONVERT('foo', 'UTF8', 'KOI8R'); convert --------- foo (1 row) --- KOI8R --> UNICODE -SELECT CONVERT('foo' USING koi8_r_to_utf_8); +-- KOI8R --> UTF8 +SELECT CONVERT('foo' USING koi8_r_to_utf8); convert_using --------------- foo (1 row) -SELECT CONVERT('foo', 'KOI8R', 'UNICODE'); +SELECT CONVERT('foo', 'KOI8R', 'UTF8'); convert --------- foo (1 row) --- UNICODE --> WIN1251 -SELECT CONVERT('foo' USING utf_8_to_windows_1251); +-- UTF8 --> WIN1251 +SELECT CONVERT('foo' USING utf8_to_windows_1251); convert_using --------------- foo (1 row) -SELECT CONVERT('foo', 'UNICODE', 'WIN1251'); +SELECT CONVERT('foo', 'UTF8', 'WIN1251'); convert --------- foo (1 row) --- WIN1251 --> UNICODE -SELECT CONVERT('foo' USING windows_1251_to_utf_8); +-- WIN1251 --> UTF8 +SELECT CONVERT('foo' USING windows_1251_to_utf8); convert_using --------------- foo (1 row) -SELECT CONVERT('foo', 'WIN1251', 'UNICODE'); +SELECT CONVERT('foo', 'WIN1251', 'UTF8'); convert --------- foo (1 row) --- UNICODE --> ALT -SELECT CONVERT('foo' USING utf_8_to_windows_866); +-- UTF8 --> WIN866 +SELECT CONVERT('foo' USING utf8_to_windows_866); convert_using --------------- foo (1 row) -SELECT CONVERT('foo', 'UNICODE', 'ALT'); +SELECT CONVERT('foo', 'UTF8', 'WIN866'); convert --------- foo (1 row) --- ALT --> UNICODE -SELECT CONVERT('foo' USING windows_866_to_utf_8); +-- WIN866 --> UTF8 +SELECT CONVERT('foo' USING windows_866_to_utf8); convert_using --------------- foo (1 row) -SELECT CONVERT('foo', 'ALT', 'UNICODE'); +SELECT CONVERT('foo', 'WIN866', 'UTF8'); convert --------- foo (1 row) --- EUC_CN --> UNICODE -SELECT CONVERT('foo' USING euc_cn_to_utf_8); +-- EUC_CN --> UTF8 +SELECT CONVERT('foo' USING euc_cn_to_utf8); convert_using --------------- foo (1 row) -SELECT CONVERT('foo', 'EUC_CN', 'UNICODE'); +SELECT CONVERT('foo', 'EUC_CN', 'UTF8'); convert --------- foo (1 row) --- UNICODE --> EUC_CN -SELECT CONVERT('foo' USING utf_8_to_euc_cn); +-- UTF8 --> EUC_CN +SELECT CONVERT('foo' USING utf8_to_euc_cn); convert_using --------------- foo (1 row) -SELECT CONVERT('foo', 'UNICODE', 'EUC_CN'); +SELECT CONVERT('foo', 'UTF8', 'EUC_CN'); convert --------- foo (1 row) --- EUC_JP --> UNICODE -SELECT CONVERT('foo' USING euc_jp_to_utf_8); +-- EUC_JP --> UTF8 +SELECT CONVERT('foo' USING euc_jp_to_utf8); convert_using --------------- foo (1 row) -SELECT CONVERT('foo', 'EUC_JP', 'UNICODE'); +SELECT CONVERT('foo', 'EUC_JP', 'UTF8'); convert --------- foo (1 row) --- UNICODE --> EUC_JP -SELECT CONVERT('foo' USING utf_8_to_euc_jp); +-- UTF8 --> EUC_JP +SELECT CONVERT('foo' USING utf8_to_euc_jp); convert_using --------------- foo (1 row) -SELECT CONVERT('foo', 'UNICODE', 'EUC_JP'); +SELECT CONVERT('foo', 'UTF8', 'EUC_JP'); convert --------- foo (1 row) --- EUC_KR --> UNICODE -SELECT CONVERT('foo' USING euc_kr_to_utf_8); +-- EUC_KR --> UTF8 +SELECT CONVERT('foo' USING euc_kr_to_utf8); convert_using --------------- foo (1 row) -SELECT CONVERT('foo', 'EUC_KR', 'UNICODE'); +SELECT CONVERT('foo', 'EUC_KR', 'UTF8'); convert --------- foo (1 row) --- UNICODE --> EUC_KR -SELECT CONVERT('foo' USING utf_8_to_euc_kr); +-- UTF8 --> EUC_KR +SELECT CONVERT('foo' USING utf8_to_euc_kr); convert_using --------------- foo (1 row) -SELECT CONVERT('foo', 'UNICODE', 'EUC_KR'); +SELECT CONVERT('foo', 'UTF8', 'EUC_KR'); convert --------- foo (1 row) --- EUC_TW --> UNICODE -SELECT CONVERT('foo' USING euc_tw_to_utf_8); +-- EUC_TW --> UTF8 +SELECT CONVERT('foo' USING euc_tw_to_utf8); convert_using --------------- foo (1 row) -SELECT CONVERT('foo', 'EUC_TW', 'UNICODE'); +SELECT CONVERT('foo', 'EUC_TW', 'UTF8'); convert --------- foo (1 row) --- UNICODE --> EUC_TW -SELECT CONVERT('foo' USING utf_8_to_euc_tw); +-- UTF8 --> EUC_TW +SELECT CONVERT('foo' USING utf8_to_euc_tw); convert_using --------------- foo (1 row) -SELECT CONVERT('foo', 'UNICODE', 'EUC_TW'); +SELECT CONVERT('foo', 'UTF8', 'EUC_TW'); convert --------- foo (1 row) --- GB18030 --> UNICODE -SELECT CONVERT('foo' USING gb18030_to_utf_8); +-- GB18030 --> UTF8 +SELECT CONVERT('foo' USING gb18030_to_utf8); convert_using --------------- foo (1 row) -SELECT CONVERT('foo', 'GB18030', 'UNICODE'); +SELECT CONVERT('foo', 'GB18030', 'UTF8'); convert --------- foo (1 row) --- UNICODE --> GB18030 -SELECT CONVERT('foo' USING utf_8_to_gb18030); +-- UTF8 --> GB18030 +SELECT CONVERT('foo' USING utf8_to_gb18030); convert_using --------------- foo (1 row) -SELECT CONVERT('foo', 'UNICODE', 'GB18030'); +SELECT CONVERT('foo', 'UTF8', 'GB18030'); convert --------- foo (1 row) --- GBK --> UNICODE -SELECT CONVERT('foo' USING gbk_to_utf_8); +-- GBK --> UTF8 +SELECT CONVERT('foo' USING gbk_to_utf8); convert_using --------------- foo (1 row) -SELECT CONVERT('foo', 'GBK', 'UNICODE'); +SELECT CONVERT('foo', 'GBK', 'UTF8'); convert --------- foo (1 row) --- UNICODE --> GBK -SELECT CONVERT('foo' USING utf_8_to_gbk); +-- UTF8 --> GBK +SELECT CONVERT('foo' USING utf8_to_gbk); convert_using --------------- foo (1 row) -SELECT CONVERT('foo', 'UNICODE', 'GBK'); +SELECT CONVERT('foo', 'UTF8', 'GBK'); convert --------- foo (1 row) --- UNICODE --> LATIN2 -SELECT CONVERT('foo' USING utf_8_to_iso_8859_2); +-- UTF8 --> LATIN2 +SELECT CONVERT('foo' USING utf8_to_iso_8859_2); convert_using --------------- foo (1 row) -SELECT CONVERT('foo', 'UNICODE', 'LATIN2'); +SELECT CONVERT('foo', 'UTF8', 'LATIN2'); convert --------- foo (1 row) --- LATIN2 --> UNICODE -SELECT CONVERT('foo' USING iso_8859_2_to_utf_8); +-- LATIN2 --> UTF8 +SELECT CONVERT('foo' USING iso_8859_2_to_utf8); convert_using --------------- foo (1 row) -SELECT CONVERT('foo', 'LATIN2', 'UNICODE'); +SELECT CONVERT('foo', 'LATIN2', 'UTF8'); convert --------- foo (1 row) --- UNICODE --> LATIN3 -SELECT CONVERT('foo' USING utf_8_to_iso_8859_3); +-- UTF8 --> LATIN3 +SELECT CONVERT('foo' USING utf8_to_iso_8859_3); convert_using --------------- foo (1 row) -SELECT CONVERT('foo', 'UNICODE', 'LATIN3'); +SELECT CONVERT('foo', 'UTF8', 'LATIN3'); convert --------- foo (1 row) --- LATIN3 --> UNICODE -SELECT CONVERT('foo' USING iso_8859_3_to_utf_8); +-- LATIN3 --> UTF8 +SELECT CONVERT('foo' USING iso_8859_3_to_utf8); convert_using --------------- foo (1 row) -SELECT CONVERT('foo', 'LATIN3', 'UNICODE'); +SELECT CONVERT('foo', 'LATIN3', 'UTF8'); convert --------- foo (1 row) --- UNICODE --> LATIN4 -SELECT CONVERT('foo' USING utf_8_to_iso_8859_4); +-- UTF8 --> LATIN4 +SELECT CONVERT('foo' USING utf8_to_iso_8859_4); convert_using --------------- foo (1 row) -SELECT CONVERT('foo', 'UNICODE', 'LATIN4'); +SELECT CONVERT('foo', 'UTF8', 'LATIN4'); convert --------- foo (1 row) --- LATIN4 --> UNICODE -SELECT CONVERT('foo' USING iso_8859_4_to_utf_8); +-- LATIN4 --> UTF8 +SELECT CONVERT('foo' USING iso_8859_4_to_utf8); convert_using --------------- foo (1 row) -SELECT CONVERT('foo', 'LATIN4', 'UNICODE'); +SELECT CONVERT('foo', 'LATIN4', 'UTF8'); convert --------- foo (1 row) --- UNICODE --> LATIN5 -SELECT CONVERT('foo' USING utf_8_to_iso_8859_9); +-- UTF8 --> LATIN5 +SELECT CONVERT('foo' USING utf8_to_iso_8859_9); convert_using --------------- foo (1 row) -SELECT CONVERT('foo', 'UNICODE', 'LATIN5'); +SELECT CONVERT('foo', 'UTF8', 'LATIN5'); convert --------- foo (1 row) --- LATIN5 --> UNICODE -SELECT CONVERT('foo' USING iso_8859_9_to_utf_8); +-- LATIN5 --> UTF8 +SELECT CONVERT('foo' USING iso_8859_9_to_utf8); convert_using --------------- foo (1 row) -SELECT CONVERT('foo', 'LATIN5', 'UNICODE'); +SELECT CONVERT('foo', 'LATIN5', 'UTF8'); convert --------- foo (1 row) --- UNICODE --> LATIN6 -SELECT CONVERT('foo' USING utf_8_to_iso_8859_10); +-- UTF8 --> LATIN6 +SELECT CONVERT('foo' USING utf8_to_iso_8859_10); convert_using --------------- foo (1 row) -SELECT CONVERT('foo', 'UNICODE', 'LATIN6'); +SELECT CONVERT('foo', 'UTF8', 'LATIN6'); convert --------- foo (1 row) --- LATIN6 --> UNICODE -SELECT CONVERT('foo' USING iso_8859_10_to_utf_8); +-- LATIN6 --> UTF8 +SELECT CONVERT('foo' USING iso_8859_10_to_utf8); convert_using --------------- foo (1 row) -SELECT CONVERT('foo', 'LATIN6', 'UNICODE'); +SELECT CONVERT('foo', 'LATIN6', 'UTF8'); convert --------- foo (1 row) --- UNICODE --> LATIN7 -SELECT CONVERT('foo' USING utf_8_to_iso_8859_13); +-- UTF8 --> LATIN7 +SELECT CONVERT('foo' USING utf8_to_iso_8859_13); convert_using --------------- foo (1 row) -SELECT CONVERT('foo', 'UNICODE', 'LATIN7'); +SELECT CONVERT('foo', 'UTF8', 'LATIN7'); convert --------- foo (1 row) --- LATIN7 --> UNICODE -SELECT CONVERT('foo' USING iso_8859_13_to_utf_8); +-- LATIN7 --> UTF8 +SELECT CONVERT('foo' USING iso_8859_13_to_utf8); convert_using --------------- foo (1 row) -SELECT CONVERT('foo', 'LATIN7', 'UNICODE'); +SELECT CONVERT('foo', 'LATIN7', 'UTF8'); convert --------- foo (1 row) --- UNICODE --> LATIN8 -SELECT CONVERT('foo' USING utf_8_to_iso_8859_14); +-- UTF8 --> LATIN8 +SELECT CONVERT('foo' USING utf8_to_iso_8859_14); convert_using --------------- foo (1 row) -SELECT CONVERT('foo', 'UNICODE', 'LATIN8'); +SELECT CONVERT('foo', 'UTF8', 'LATIN8'); convert --------- foo (1 row) --- LATIN8 --> UNICODE -SELECT CONVERT('foo' USING iso_8859_14_to_utf_8); +-- LATIN8 --> UTF8 +SELECT CONVERT('foo' USING iso_8859_14_to_utf8); convert_using --------------- foo (1 row) -SELECT CONVERT('foo', 'LATIN8', 'UNICODE'); +SELECT CONVERT('foo', 'LATIN8', 'UTF8'); convert --------- foo (1 row) --- UNICODE --> LATIN9 -SELECT CONVERT('foo' USING utf_8_to_iso_8859_15); +-- UTF8 --> LATIN9 +SELECT CONVERT('foo' USING utf8_to_iso_8859_15); convert_using --------------- foo (1 row) -SELECT CONVERT('foo', 'UNICODE', 'LATIN9'); +SELECT CONVERT('foo', 'UTF8', 'LATIN9'); convert --------- foo (1 row) --- LATIN9 --> UNICODE -SELECT CONVERT('foo' USING iso_8859_15_to_utf_8); +-- LATIN9 --> UTF8 +SELECT CONVERT('foo' USING iso_8859_15_to_utf8); convert_using --------------- foo (1 row) -SELECT CONVERT('foo', 'LATIN9', 'UNICODE'); +SELECT CONVERT('foo', 'LATIN9', 'UTF8'); convert --------- foo (1 row) --- UNICODE --> LATIN10 -SELECT CONVERT('foo' USING utf_8_to_iso_8859_16); +-- UTF8 --> LATIN10 +SELECT CONVERT('foo' USING utf8_to_iso_8859_16); convert_using --------------- foo (1 row) -SELECT CONVERT('foo', 'UNICODE', 'LATIN10'); +SELECT CONVERT('foo', 'UTF8', 'LATIN10'); convert --------- foo (1 row) --- LATIN10 --> UNICODE -SELECT CONVERT('foo' USING iso_8859_16_to_utf_8); +-- LATIN10 --> UTF8 +SELECT CONVERT('foo' USING iso_8859_16_to_utf8); convert_using --------------- foo (1 row) -SELECT CONVERT('foo', 'LATIN10', 'UNICODE'); +SELECT CONVERT('foo', 'LATIN10', 'UTF8'); convert --------- foo (1 row) --- UNICODE --> ISO-8859-5 -SELECT CONVERT('foo' USING utf_8_to_iso_8859_5); +-- UTF8 --> ISO-8859-5 +SELECT CONVERT('foo' USING utf8_to_iso_8859_5); convert_using --------------- foo (1 row) -SELECT CONVERT('foo', 'UNICODE', 'ISO-8859-5'); +SELECT CONVERT('foo', 'UTF8', 'ISO-8859-5'); convert --------- foo (1 row) --- ISO-8859-5 --> UNICODE -SELECT CONVERT('foo' USING iso_8859_5_to_utf_8); +-- ISO-8859-5 --> UTF8 +SELECT CONVERT('foo' USING iso_8859_5_to_utf8); convert_using --------------- foo (1 row) -SELECT CONVERT('foo', 'ISO-8859-5', 'UNICODE'); +SELECT CONVERT('foo', 'ISO-8859-5', 'UTF8'); convert --------- foo (1 row) --- UNICODE --> ISO-8859-6 -SELECT CONVERT('foo' USING utf_8_to_iso_8859_6); +-- UTF8 --> ISO-8859-6 +SELECT CONVERT('foo' USING utf8_to_iso_8859_6); convert_using --------------- foo (1 row) -SELECT CONVERT('foo', 'UNICODE', 'ISO-8859-6'); +SELECT CONVERT('foo', 'UTF8', 'ISO-8859-6'); convert --------- foo (1 row) --- ISO-8859-6 --> UNICODE -SELECT CONVERT('foo' USING iso_8859_6_to_utf_8); +-- ISO-8859-6 --> UTF8 +SELECT CONVERT('foo' USING iso_8859_6_to_utf8); convert_using --------------- foo (1 row) -SELECT CONVERT('foo', 'ISO-8859-6', 'UNICODE'); +SELECT CONVERT('foo', 'ISO-8859-6', 'UTF8'); convert --------- foo (1 row) --- UNICODE --> ISO-8859-7 -SELECT CONVERT('foo' USING utf_8_to_iso_8859_7); +-- UTF8 --> ISO-8859-7 +SELECT CONVERT('foo' USING utf8_to_iso_8859_7); convert_using --------------- foo (1 row) -SELECT CONVERT('foo', 'UNICODE', 'ISO-8859-7'); +SELECT CONVERT('foo', 'UTF8', 'ISO-8859-7'); convert --------- foo (1 row) --- ISO-8859-7 --> UNICODE -SELECT CONVERT('foo' USING iso_8859_7_to_utf_8); +-- ISO-8859-7 --> UTF8 +SELECT CONVERT('foo' USING iso_8859_7_to_utf8); convert_using --------------- foo (1 row) -SELECT CONVERT('foo', 'ISO-8859-7', 'UNICODE'); +SELECT CONVERT('foo', 'ISO-8859-7', 'UTF8'); convert --------- foo (1 row) --- UNICODE --> ISO-8859-8 -SELECT CONVERT('foo' USING utf_8_to_iso_8859_8); +-- UTF8 --> ISO-8859-8 +SELECT CONVERT('foo' USING utf8_to_iso_8859_8); convert_using --------------- foo (1 row) -SELECT CONVERT('foo', 'UNICODE', 'ISO-8859-8'); +SELECT CONVERT('foo', 'UTF8', 'ISO-8859-8'); convert --------- foo (1 row) --- ISO-8859-8 --> UNICODE -SELECT CONVERT('foo' USING iso_8859_8_to_utf_8); +-- ISO-8859-8 --> UTF8 +SELECT CONVERT('foo' USING iso_8859_8_to_utf8); convert_using --------------- foo (1 row) -SELECT CONVERT('foo', 'ISO-8859-8', 'UNICODE'); +SELECT CONVERT('foo', 'ISO-8859-8', 'UTF8'); convert --------- foo (1 row) --- LATIN1 --> UNICODE -SELECT CONVERT('foo' USING iso_8859_1_to_utf_8); +-- LATIN1 --> UTF8 +SELECT CONVERT('foo' USING iso_8859_1_to_utf8); convert_using --------------- foo (1 row) -SELECT CONVERT('foo', 'LATIN1', 'UNICODE'); +SELECT CONVERT('foo', 'LATIN1', 'UTF8'); convert --------- foo (1 row) --- UNICODE --> LATIN1 -SELECT CONVERT('foo' USING utf_8_to_iso_8859_1); +-- UTF8 --> LATIN1 +SELECT CONVERT('foo' USING utf8_to_iso_8859_1); convert_using --------------- foo (1 row) -SELECT CONVERT('foo', 'UNICODE', 'LATIN1'); +SELECT CONVERT('foo', 'UTF8', 'LATIN1'); convert --------- foo (1 row) --- JOHAB --> UNICODE -SELECT CONVERT('foo' USING johab_to_utf_8); +-- JOHAB --> UTF8 +SELECT CONVERT('foo' USING johab_to_utf8); convert_using --------------- foo (1 row) -SELECT CONVERT('foo', 'JOHAB', 'UNICODE'); +SELECT CONVERT('foo', 'JOHAB', 'UTF8'); convert --------- foo (1 row) --- UNICODE --> JOHAB -SELECT CONVERT('foo' USING utf_8_to_johab); +-- UTF8 --> JOHAB +SELECT CONVERT('foo' USING utf8_to_johab); convert_using --------------- foo (1 row) -SELECT CONVERT('foo', 'UNICODE', 'JOHAB'); +SELECT CONVERT('foo', 'UTF8', 'JOHAB'); convert --------- foo (1 row) --- SJIS --> UNICODE -SELECT CONVERT('foo' USING sjis_to_utf_8); +-- SJIS --> UTF8 +SELECT CONVERT('foo' USING sjis_to_utf8); convert_using --------------- foo (1 row) -SELECT CONVERT('foo', 'SJIS', 'UNICODE'); +SELECT CONVERT('foo', 'SJIS', 'UTF8'); convert --------- foo (1 row) --- UNICODE --> SJIS -SELECT CONVERT('foo' USING utf_8_to_sjis); +-- UTF8 --> SJIS +SELECT CONVERT('foo' USING utf8_to_sjis); convert_using --------------- foo (1 row) -SELECT CONVERT('foo', 'UNICODE', 'SJIS'); +SELECT CONVERT('foo', 'UTF8', 'SJIS'); convert --------- foo (1 row) --- TCVN --> UNICODE -SELECT CONVERT('foo' USING tcvn_to_utf_8); +-- WIN1258 --> UTF8 +SELECT CONVERT('foo' USING win1258_to_utf8); convert_using --------------- foo (1 row) -SELECT CONVERT('foo', 'TCVN', 'UNICODE'); +SELECT CONVERT('foo', 'WIN1258', 'UTF8'); convert --------- foo (1 row) --- UNICODE --> TCVN -SELECT CONVERT('foo' USING utf_8_to_tcvn); +-- UTF8 --> WIN1258 +SELECT CONVERT('foo' USING utf8_to_win1258); convert_using --------------- foo (1 row) -SELECT CONVERT('foo', 'UNICODE', 'TCVN'); +SELECT CONVERT('foo', 'UTF8', 'WIN1258'); convert --------- foo (1 row) --- UHC --> UNICODE -SELECT CONVERT('foo' USING uhc_to_utf_8); +-- UHC --> UTF8 +SELECT CONVERT('foo' USING uhc_to_utf8); convert_using --------------- foo (1 row) -SELECT CONVERT('foo', 'UHC', 'UNICODE'); +SELECT CONVERT('foo', 'UHC', 'UTF8'); convert --------- foo (1 row) --- UNICODE --> UHC -SELECT CONVERT('foo' USING utf_8_to_uhc); +-- UTF8 --> UHC +SELECT CONVERT('foo' USING utf8_to_uhc); convert_using --------------- foo (1 row) -SELECT CONVERT('foo', 'UNICODE', 'UHC'); +SELECT CONVERT('foo', 'UTF8', 'UHC'); convert --------- foo (1 row) --- UNICODE --> WIN1250 -SELECT CONVERT('foo' USING utf_8_to_windows_1250); +-- UTF8 --> WIN1250 +SELECT CONVERT('foo' USING utf8_to_windows_1250); convert_using --------------- foo (1 row) -SELECT CONVERT('foo', 'UNICODE', 'WIN1250'); +SELECT CONVERT('foo', 'UTF8', 'WIN1250'); convert --------- foo (1 row) --- WIN1250 --> UNICODE -SELECT CONVERT('foo' USING windows_1250_to_utf_8); +-- WIN1250 --> UTF8 +SELECT CONVERT('foo' USING windows_1250_to_utf8); convert_using --------------- foo (1 row) -SELECT CONVERT('foo', 'WIN1250', 'UNICODE'); +SELECT CONVERT('foo', 'WIN1250', 'UTF8'); convert --------- foo (1 row) --- UNICODE --> WIN1256 -SELECT CONVERT('foo' USING utf_8_to_windows_1256); +-- UTF8 --> WIN1256 +SELECT CONVERT('foo' USING utf8_to_windows_1256); convert_using --------------- foo (1 row) -SELECT CONVERT('foo', 'UNICODE', 'WIN1256'); +SELECT CONVERT('foo', 'UTF8', 'WIN1256'); convert --------- foo (1 row) --- WIN1256 --> UNICODE -SELECT CONVERT('foo' USING windows_1256_to_utf_8); +-- WIN1256 --> UTF8 +SELECT CONVERT('foo' USING windows_1256_to_utf8); convert_using --------------- foo (1 row) -SELECT CONVERT('foo', 'WIN1256', 'UNICODE'); +SELECT CONVERT('foo', 'WIN1256', 'UTF8'); convert --------- foo (1 row) --- UNICODE --> WIN874 -SELECT CONVERT('foo' USING utf_8_to_windows_874); +-- UTF8 --> WIN874 +SELECT CONVERT('foo' USING utf8_to_windows_874); convert_using --------------- foo (1 row) -SELECT CONVERT('foo', 'UNICODE', 'WIN874'); +SELECT CONVERT('foo', 'UTF8', 'WIN874'); convert --------- foo (1 row) --- WIN874 --> UNICODE -SELECT CONVERT('foo' USING windows_874_to_utf_8); +-- WIN874 --> UTF8 +SELECT CONVERT('foo' USING windows_874_to_utf8); convert_using --------------- foo (1 row) -SELECT CONVERT('foo', 'WIN874', 'UNICODE'); +SELECT CONVERT('foo', 'WIN874', 'UTF8'); convert --------- foo diff --git a/src/test/regress/sql/conversion.sql b/src/test/regress/sql/conversion.sql index c84ffee95f..765064bc4f 100644 --- a/src/test/regress/sql/conversion.sql +++ b/src/test/regress/sql/conversion.sql @@ -3,19 +3,19 @@ -- CREATE USER conversion_test_user WITH NOCREATEDB NOCREATEUSER; SET SESSION AUTHORIZATION conversion_test_user; -CREATE CONVERSION myconv FOR 'LATIN1' TO 'UNICODE' FROM iso8859_1_to_utf8; +CREATE CONVERSION myconv FOR 'LATIN1' TO 'UTF8' FROM iso8859_1_to_utf8; -- -- cannot make same name conversion in same schema -- -CREATE CONVERSION myconv FOR 'LATIN1' TO 'UNICODE' FROM iso8859_1_to_utf8; +CREATE CONVERSION myconv FOR 'LATIN1' TO 'UTF8' FROM iso8859_1_to_utf8; -- -- create default conversion with qualified name -- -CREATE DEFAULT CONVERSION public.mydef FOR 'LATIN1' TO 'UNICODE' FROM iso8859_1_to_utf8; +CREATE DEFAULT CONVERSION public.mydef FOR 'LATIN1' TO 'UTF8' FROM iso8859_1_to_utf8; -- -- cannot make default conversion with same shcema/for_encoding/to_encoding -- -CREATE DEFAULT CONVERSION public.mydef2 FOR 'LATIN1' TO 'UNICODE' FROM iso8859_1_to_utf8; +CREATE DEFAULT CONVERSION public.mydef2 FOR 'LATIN1' TO 'UTF8' FROM iso8859_1_to_utf8; -- test comments COMMENT ON CONVERSION myconv_bad IS 'foo'; COMMENT ON CONVERSION myconv IS 'bar'; @@ -51,30 +51,30 @@ SELECT CONVERT('foo', 'WIN1251', 'MULE_INTERNAL'); -- MULE_INTERNAL --> WIN1251 SELECT CONVERT('foo' USING mic_to_windows_1251); SELECT CONVERT('foo', 'MULE_INTERNAL', 'WIN1251'); --- ALT --> MULE_INTERNAL +-- WIN866 --> MULE_INTERNAL SELECT CONVERT('foo' USING windows_866_to_mic); -SELECT CONVERT('foo', 'ALT', 'MULE_INTERNAL'); --- MULE_INTERNAL --> ALT +SELECT CONVERT('foo', 'WIN866', 'MULE_INTERNAL'); +-- MULE_INTERNAL --> WIN866 SELECT CONVERT('foo' USING mic_to_windows_866); -SELECT CONVERT('foo', 'MULE_INTERNAL', 'ALT'); +SELECT CONVERT('foo', 'MULE_INTERNAL', 'WIN866'); -- KOI8R --> WIN1251 SELECT CONVERT('foo' USING koi8_r_to_windows_1251); SELECT CONVERT('foo', 'KOI8R', 'WIN1251'); -- WIN1251 --> KOI8R SELECT CONVERT('foo' USING windows_1251_to_koi8_r); SELECT CONVERT('foo', 'WIN1251', 'KOI8R'); --- KOI8R --> ALT +-- KOI8R --> WIN866 SELECT CONVERT('foo' USING koi8_r_to_windows_866); -SELECT CONVERT('foo', 'KOI8R', 'ALT'); --- ALT --> KOI8R +SELECT CONVERT('foo', 'KOI8R', 'WIN866'); +-- WIN866 --> KOI8R SELECT CONVERT('foo' USING windows_866_to_koi8_r); -SELECT CONVERT('foo', 'ALT', 'KOI8R'); --- ALT --> WIN1251 +SELECT CONVERT('foo', 'WIN866', 'KOI8R'); +-- WIN866 --> WIN1251 SELECT CONVERT('foo' USING windows_866_to_windows_1251); -SELECT CONVERT('foo', 'ALT', 'WIN1251'); --- WIN1251 --> ALT +SELECT CONVERT('foo', 'WIN866', 'WIN1251'); +-- WIN1251 --> WIN866 SELECT CONVERT('foo' USING windows_1251_to_windows_866); -SELECT CONVERT('foo', 'WIN1251', 'ALT'); +SELECT CONVERT('foo', 'WIN1251', 'WIN866'); -- ISO-8859-5 --> KOI8R SELECT CONVERT('foo' USING iso_8859_5_to_koi8_r); SELECT CONVERT('foo', 'ISO-8859-5', 'KOI8R'); @@ -87,12 +87,12 @@ SELECT CONVERT('foo', 'ISO-8859-5', 'WIN1251'); -- WIN1251 --> ISO-8859-5 SELECT CONVERT('foo' USING windows_1251_to_iso_8859_5); SELECT CONVERT('foo', 'WIN1251', 'ISO-8859-5'); --- ISO-8859-5 --> ALT +-- ISO-8859-5 --> WIN866 SELECT CONVERT('foo' USING iso_8859_5_to_windows_866); -SELECT CONVERT('foo', 'ISO-8859-5', 'ALT'); --- ALT --> ISO-8859-5 +SELECT CONVERT('foo', 'ISO-8859-5', 'WIN866'); +-- WIN866 --> ISO-8859-5 SELECT CONVERT('foo' USING windows_866_to_iso_8859_5); -SELECT CONVERT('foo', 'ALT', 'ISO-8859-5'); +SELECT CONVERT('foo', 'WIN866', 'ISO-8859-5'); -- EUC_CN --> MULE_INTERNAL SELECT CONVERT('foo' USING euc_cn_to_mic); SELECT CONVERT('foo', 'EUC_CN', 'MULE_INTERNAL'); @@ -177,198 +177,198 @@ SELECT CONVERT('foo', 'LATIN4', 'MULE_INTERNAL'); -- MULE_INTERNAL --> LATIN4 SELECT CONVERT('foo' USING mic_to_iso_8859_4); SELECT CONVERT('foo', 'MULE_INTERNAL', 'LATIN4'); --- SQL_ASCII --> UNICODE -SELECT CONVERT('foo' USING ascii_to_utf_8); -SELECT CONVERT('foo', 'SQL_ASCII', 'UNICODE'); --- UNICODE --> SQL_ASCII -SELECT CONVERT('foo' USING utf_8_to_ascii); -SELECT CONVERT('foo', 'UNICODE', 'SQL_ASCII'); --- BIG5 --> UNICODE -SELECT CONVERT('foo' USING big5_to_utf_8); -SELECT CONVERT('foo', 'BIG5', 'UNICODE'); --- UNICODE --> BIG5 -SELECT CONVERT('foo' USING utf_8_to_big5); -SELECT CONVERT('foo', 'UNICODE', 'BIG5'); --- UNICODE --> KOI8R -SELECT CONVERT('foo' USING utf_8_to_koi8_r); -SELECT CONVERT('foo', 'UNICODE', 'KOI8R'); --- KOI8R --> UNICODE -SELECT CONVERT('foo' USING koi8_r_to_utf_8); -SELECT CONVERT('foo', 'KOI8R', 'UNICODE'); --- UNICODE --> WIN1251 -SELECT CONVERT('foo' USING utf_8_to_windows_1251); -SELECT CONVERT('foo', 'UNICODE', 'WIN1251'); --- WIN1251 --> UNICODE -SELECT CONVERT('foo' USING windows_1251_to_utf_8); -SELECT CONVERT('foo', 'WIN1251', 'UNICODE'); --- UNICODE --> ALT -SELECT CONVERT('foo' USING utf_8_to_windows_866); -SELECT CONVERT('foo', 'UNICODE', 'ALT'); --- ALT --> UNICODE -SELECT CONVERT('foo' USING windows_866_to_utf_8); -SELECT CONVERT('foo', 'ALT', 'UNICODE'); --- EUC_CN --> UNICODE -SELECT CONVERT('foo' USING euc_cn_to_utf_8); -SELECT CONVERT('foo', 'EUC_CN', 'UNICODE'); --- UNICODE --> EUC_CN -SELECT CONVERT('foo' USING utf_8_to_euc_cn); -SELECT CONVERT('foo', 'UNICODE', 'EUC_CN'); --- EUC_JP --> UNICODE -SELECT CONVERT('foo' USING euc_jp_to_utf_8); -SELECT CONVERT('foo', 'EUC_JP', 'UNICODE'); --- UNICODE --> EUC_JP -SELECT CONVERT('foo' USING utf_8_to_euc_jp); -SELECT CONVERT('foo', 'UNICODE', 'EUC_JP'); --- EUC_KR --> UNICODE -SELECT CONVERT('foo' USING euc_kr_to_utf_8); -SELECT CONVERT('foo', 'EUC_KR', 'UNICODE'); --- UNICODE --> EUC_KR -SELECT CONVERT('foo' USING utf_8_to_euc_kr); -SELECT CONVERT('foo', 'UNICODE', 'EUC_KR'); --- EUC_TW --> UNICODE -SELECT CONVERT('foo' USING euc_tw_to_utf_8); -SELECT CONVERT('foo', 'EUC_TW', 'UNICODE'); --- UNICODE --> EUC_TW -SELECT CONVERT('foo' USING utf_8_to_euc_tw); -SELECT CONVERT('foo', 'UNICODE', 'EUC_TW'); --- GB18030 --> UNICODE -SELECT CONVERT('foo' USING gb18030_to_utf_8); -SELECT CONVERT('foo', 'GB18030', 'UNICODE'); --- UNICODE --> GB18030 -SELECT CONVERT('foo' USING utf_8_to_gb18030); -SELECT CONVERT('foo', 'UNICODE', 'GB18030'); --- GBK --> UNICODE -SELECT CONVERT('foo' USING gbk_to_utf_8); -SELECT CONVERT('foo', 'GBK', 'UNICODE'); --- UNICODE --> GBK -SELECT CONVERT('foo' USING utf_8_to_gbk); -SELECT CONVERT('foo', 'UNICODE', 'GBK'); --- UNICODE --> LATIN2 -SELECT CONVERT('foo' USING utf_8_to_iso_8859_2); -SELECT CONVERT('foo', 'UNICODE', 'LATIN2'); --- LATIN2 --> UNICODE -SELECT CONVERT('foo' USING iso_8859_2_to_utf_8); -SELECT CONVERT('foo', 'LATIN2', 'UNICODE'); --- UNICODE --> LATIN3 -SELECT CONVERT('foo' USING utf_8_to_iso_8859_3); -SELECT CONVERT('foo', 'UNICODE', 'LATIN3'); --- LATIN3 --> UNICODE -SELECT CONVERT('foo' USING iso_8859_3_to_utf_8); -SELECT CONVERT('foo', 'LATIN3', 'UNICODE'); --- UNICODE --> LATIN4 -SELECT CONVERT('foo' USING utf_8_to_iso_8859_4); -SELECT CONVERT('foo', 'UNICODE', 'LATIN4'); --- LATIN4 --> UNICODE -SELECT CONVERT('foo' USING iso_8859_4_to_utf_8); -SELECT CONVERT('foo', 'LATIN4', 'UNICODE'); --- UNICODE --> LATIN5 -SELECT CONVERT('foo' USING utf_8_to_iso_8859_9); -SELECT CONVERT('foo', 'UNICODE', 'LATIN5'); --- LATIN5 --> UNICODE -SELECT CONVERT('foo' USING iso_8859_9_to_utf_8); -SELECT CONVERT('foo', 'LATIN5', 'UNICODE'); --- UNICODE --> LATIN6 -SELECT CONVERT('foo' USING utf_8_to_iso_8859_10); -SELECT CONVERT('foo', 'UNICODE', 'LATIN6'); --- LATIN6 --> UNICODE -SELECT CONVERT('foo' USING iso_8859_10_to_utf_8); -SELECT CONVERT('foo', 'LATIN6', 'UNICODE'); --- UNICODE --> LATIN7 -SELECT CONVERT('foo' USING utf_8_to_iso_8859_13); -SELECT CONVERT('foo', 'UNICODE', 'LATIN7'); --- LATIN7 --> UNICODE -SELECT CONVERT('foo' USING iso_8859_13_to_utf_8); -SELECT CONVERT('foo', 'LATIN7', 'UNICODE'); --- UNICODE --> LATIN8 -SELECT CONVERT('foo' USING utf_8_to_iso_8859_14); -SELECT CONVERT('foo', 'UNICODE', 'LATIN8'); --- LATIN8 --> UNICODE -SELECT CONVERT('foo' USING iso_8859_14_to_utf_8); -SELECT CONVERT('foo', 'LATIN8', 'UNICODE'); --- UNICODE --> LATIN9 -SELECT CONVERT('foo' USING utf_8_to_iso_8859_15); -SELECT CONVERT('foo', 'UNICODE', 'LATIN9'); --- LATIN9 --> UNICODE -SELECT CONVERT('foo' USING iso_8859_15_to_utf_8); -SELECT CONVERT('foo', 'LATIN9', 'UNICODE'); --- UNICODE --> LATIN10 -SELECT CONVERT('foo' USING utf_8_to_iso_8859_16); -SELECT CONVERT('foo', 'UNICODE', 'LATIN10'); --- LATIN10 --> UNICODE -SELECT CONVERT('foo' USING iso_8859_16_to_utf_8); -SELECT CONVERT('foo', 'LATIN10', 'UNICODE'); --- UNICODE --> ISO-8859-5 -SELECT CONVERT('foo' USING utf_8_to_iso_8859_5); -SELECT CONVERT('foo', 'UNICODE', 'ISO-8859-5'); --- ISO-8859-5 --> UNICODE -SELECT CONVERT('foo' USING iso_8859_5_to_utf_8); -SELECT CONVERT('foo', 'ISO-8859-5', 'UNICODE'); --- UNICODE --> ISO-8859-6 -SELECT CONVERT('foo' USING utf_8_to_iso_8859_6); -SELECT CONVERT('foo', 'UNICODE', 'ISO-8859-6'); --- ISO-8859-6 --> UNICODE -SELECT CONVERT('foo' USING iso_8859_6_to_utf_8); -SELECT CONVERT('foo', 'ISO-8859-6', 'UNICODE'); --- UNICODE --> ISO-8859-7 -SELECT CONVERT('foo' USING utf_8_to_iso_8859_7); -SELECT CONVERT('foo', 'UNICODE', 'ISO-8859-7'); --- ISO-8859-7 --> UNICODE -SELECT CONVERT('foo' USING iso_8859_7_to_utf_8); -SELECT CONVERT('foo', 'ISO-8859-7', 'UNICODE'); --- UNICODE --> ISO-8859-8 -SELECT CONVERT('foo' USING utf_8_to_iso_8859_8); -SELECT CONVERT('foo', 'UNICODE', 'ISO-8859-8'); --- ISO-8859-8 --> UNICODE -SELECT CONVERT('foo' USING iso_8859_8_to_utf_8); -SELECT CONVERT('foo', 'ISO-8859-8', 'UNICODE'); --- LATIN1 --> UNICODE -SELECT CONVERT('foo' USING iso_8859_1_to_utf_8); -SELECT CONVERT('foo', 'LATIN1', 'UNICODE'); --- UNICODE --> LATIN1 -SELECT CONVERT('foo' USING utf_8_to_iso_8859_1); -SELECT CONVERT('foo', 'UNICODE', 'LATIN1'); --- JOHAB --> UNICODE -SELECT CONVERT('foo' USING johab_to_utf_8); -SELECT CONVERT('foo', 'JOHAB', 'UNICODE'); --- UNICODE --> JOHAB -SELECT CONVERT('foo' USING utf_8_to_johab); -SELECT CONVERT('foo', 'UNICODE', 'JOHAB'); --- SJIS --> UNICODE -SELECT CONVERT('foo' USING sjis_to_utf_8); -SELECT CONVERT('foo', 'SJIS', 'UNICODE'); --- UNICODE --> SJIS -SELECT CONVERT('foo' USING utf_8_to_sjis); -SELECT CONVERT('foo', 'UNICODE', 'SJIS'); --- TCVN --> UNICODE -SELECT CONVERT('foo' USING tcvn_to_utf_8); -SELECT CONVERT('foo', 'TCVN', 'UNICODE'); --- UNICODE --> TCVN -SELECT CONVERT('foo' USING utf_8_to_tcvn); -SELECT CONVERT('foo', 'UNICODE', 'TCVN'); --- UHC --> UNICODE -SELECT CONVERT('foo' USING uhc_to_utf_8); -SELECT CONVERT('foo', 'UHC', 'UNICODE'); --- UNICODE --> UHC -SELECT CONVERT('foo' USING utf_8_to_uhc); -SELECT CONVERT('foo', 'UNICODE', 'UHC'); --- UNICODE --> WIN1250 -SELECT CONVERT('foo' USING utf_8_to_windows_1250); -SELECT CONVERT('foo', 'UNICODE', 'WIN1250'); --- WIN1250 --> UNICODE -SELECT CONVERT('foo' USING windows_1250_to_utf_8); -SELECT CONVERT('foo', 'WIN1250', 'UNICODE'); --- UNICODE --> WIN1256 -SELECT CONVERT('foo' USING utf_8_to_windows_1256); -SELECT CONVERT('foo', 'UNICODE', 'WIN1256'); --- WIN1256 --> UNICODE -SELECT CONVERT('foo' USING windows_1256_to_utf_8); -SELECT CONVERT('foo', 'WIN1256', 'UNICODE'); --- UNICODE --> WIN874 -SELECT CONVERT('foo' USING utf_8_to_windows_874); -SELECT CONVERT('foo', 'UNICODE', 'WIN874'); --- WIN874 --> UNICODE -SELECT CONVERT('foo' USING windows_874_to_utf_8); -SELECT CONVERT('foo', 'WIN874', 'UNICODE'); +-- SQL_ASCII --> UTF8 +SELECT CONVERT('foo' USING ascii_to_utf8); +SELECT CONVERT('foo', 'SQL_ASCII', 'UTF8'); +-- UTF8 --> SQL_ASCII +SELECT CONVERT('foo' USING utf8_to_ascii); +SELECT CONVERT('foo', 'UTF8', 'SQL_ASCII'); +-- BIG5 --> UTF8 +SELECT CONVERT('foo' USING big5_to_utf8); +SELECT CONVERT('foo', 'BIG5', 'UTF8'); +-- UTF8 --> BIG5 +SELECT CONVERT('foo' USING utf8_to_big5); +SELECT CONVERT('foo', 'UTF8', 'BIG5'); +-- UTF8 --> KOI8R +SELECT CONVERT('foo' USING utf8_to_koi8_r); +SELECT CONVERT('foo', 'UTF8', 'KOI8R'); +-- KOI8R --> UTF8 +SELECT CONVERT('foo' USING koi8_r_to_utf8); +SELECT CONVERT('foo', 'KOI8R', 'UTF8'); +-- UTF8 --> WIN1251 +SELECT CONVERT('foo' USING utf8_to_windows_1251); +SELECT CONVERT('foo', 'UTF8', 'WIN1251'); +-- WIN1251 --> UTF8 +SELECT CONVERT('foo' USING windows_1251_to_utf8); +SELECT CONVERT('foo', 'WIN1251', 'UTF8'); +-- UTF8 --> WIN866 +SELECT CONVERT('foo' USING utf8_to_windows_866); +SELECT CONVERT('foo', 'UTF8', 'WIN866'); +-- WIN866 --> UTF8 +SELECT CONVERT('foo' USING windows_866_to_utf8); +SELECT CONVERT('foo', 'WIN866', 'UTF8'); +-- EUC_CN --> UTF8 +SELECT CONVERT('foo' USING euc_cn_to_utf8); +SELECT CONVERT('foo', 'EUC_CN', 'UTF8'); +-- UTF8 --> EUC_CN +SELECT CONVERT('foo' USING utf8_to_euc_cn); +SELECT CONVERT('foo', 'UTF8', 'EUC_CN'); +-- EUC_JP --> UTF8 +SELECT CONVERT('foo' USING euc_jp_to_utf8); +SELECT CONVERT('foo', 'EUC_JP', 'UTF8'); +-- UTF8 --> EUC_JP +SELECT CONVERT('foo' USING utf8_to_euc_jp); +SELECT CONVERT('foo', 'UTF8', 'EUC_JP'); +-- EUC_KR --> UTF8 +SELECT CONVERT('foo' USING euc_kr_to_utf8); +SELECT CONVERT('foo', 'EUC_KR', 'UTF8'); +-- UTF8 --> EUC_KR +SELECT CONVERT('foo' USING utf8_to_euc_kr); +SELECT CONVERT('foo', 'UTF8', 'EUC_KR'); +-- EUC_TW --> UTF8 +SELECT CONVERT('foo' USING euc_tw_to_utf8); +SELECT CONVERT('foo', 'EUC_TW', 'UTF8'); +-- UTF8 --> EUC_TW +SELECT CONVERT('foo' USING utf8_to_euc_tw); +SELECT CONVERT('foo', 'UTF8', 'EUC_TW'); +-- GB18030 --> UTF8 +SELECT CONVERT('foo' USING gb18030_to_utf8); +SELECT CONVERT('foo', 'GB18030', 'UTF8'); +-- UTF8 --> GB18030 +SELECT CONVERT('foo' USING utf8_to_gb18030); +SELECT CONVERT('foo', 'UTF8', 'GB18030'); +-- GBK --> UTF8 +SELECT CONVERT('foo' USING gbk_to_utf8); +SELECT CONVERT('foo', 'GBK', 'UTF8'); +-- UTF8 --> GBK +SELECT CONVERT('foo' USING utf8_to_gbk); +SELECT CONVERT('foo', 'UTF8', 'GBK'); +-- UTF8 --> LATIN2 +SELECT CONVERT('foo' USING utf8_to_iso_8859_2); +SELECT CONVERT('foo', 'UTF8', 'LATIN2'); +-- LATIN2 --> UTF8 +SELECT CONVERT('foo' USING iso_8859_2_to_utf8); +SELECT CONVERT('foo', 'LATIN2', 'UTF8'); +-- UTF8 --> LATIN3 +SELECT CONVERT('foo' USING utf8_to_iso_8859_3); +SELECT CONVERT('foo', 'UTF8', 'LATIN3'); +-- LATIN3 --> UTF8 +SELECT CONVERT('foo' USING iso_8859_3_to_utf8); +SELECT CONVERT('foo', 'LATIN3', 'UTF8'); +-- UTF8 --> LATIN4 +SELECT CONVERT('foo' USING utf8_to_iso_8859_4); +SELECT CONVERT('foo', 'UTF8', 'LATIN4'); +-- LATIN4 --> UTF8 +SELECT CONVERT('foo' USING iso_8859_4_to_utf8); +SELECT CONVERT('foo', 'LATIN4', 'UTF8'); +-- UTF8 --> LATIN5 +SELECT CONVERT('foo' USING utf8_to_iso_8859_9); +SELECT CONVERT('foo', 'UTF8', 'LATIN5'); +-- LATIN5 --> UTF8 +SELECT CONVERT('foo' USING iso_8859_9_to_utf8); +SELECT CONVERT('foo', 'LATIN5', 'UTF8'); +-- UTF8 --> LATIN6 +SELECT CONVERT('foo' USING utf8_to_iso_8859_10); +SELECT CONVERT('foo', 'UTF8', 'LATIN6'); +-- LATIN6 --> UTF8 +SELECT CONVERT('foo' USING iso_8859_10_to_utf8); +SELECT CONVERT('foo', 'LATIN6', 'UTF8'); +-- UTF8 --> LATIN7 +SELECT CONVERT('foo' USING utf8_to_iso_8859_13); +SELECT CONVERT('foo', 'UTF8', 'LATIN7'); +-- LATIN7 --> UTF8 +SELECT CONVERT('foo' USING iso_8859_13_to_utf8); +SELECT CONVERT('foo', 'LATIN7', 'UTF8'); +-- UTF8 --> LATIN8 +SELECT CONVERT('foo' USING utf8_to_iso_8859_14); +SELECT CONVERT('foo', 'UTF8', 'LATIN8'); +-- LATIN8 --> UTF8 +SELECT CONVERT('foo' USING iso_8859_14_to_utf8); +SELECT CONVERT('foo', 'LATIN8', 'UTF8'); +-- UTF8 --> LATIN9 +SELECT CONVERT('foo' USING utf8_to_iso_8859_15); +SELECT CONVERT('foo', 'UTF8', 'LATIN9'); +-- LATIN9 --> UTF8 +SELECT CONVERT('foo' USING iso_8859_15_to_utf8); +SELECT CONVERT('foo', 'LATIN9', 'UTF8'); +-- UTF8 --> LATIN10 +SELECT CONVERT('foo' USING utf8_to_iso_8859_16); +SELECT CONVERT('foo', 'UTF8', 'LATIN10'); +-- LATIN10 --> UTF8 +SELECT CONVERT('foo' USING iso_8859_16_to_utf8); +SELECT CONVERT('foo', 'LATIN10', 'UTF8'); +-- UTF8 --> ISO-8859-5 +SELECT CONVERT('foo' USING utf8_to_iso_8859_5); +SELECT CONVERT('foo', 'UTF8', 'ISO-8859-5'); +-- ISO-8859-5 --> UTF8 +SELECT CONVERT('foo' USING iso_8859_5_to_utf8); +SELECT CONVERT('foo', 'ISO-8859-5', 'UTF8'); +-- UTF8 --> ISO-8859-6 +SELECT CONVERT('foo' USING utf8_to_iso_8859_6); +SELECT CONVERT('foo', 'UTF8', 'ISO-8859-6'); +-- ISO-8859-6 --> UTF8 +SELECT CONVERT('foo' USING iso_8859_6_to_utf8); +SELECT CONVERT('foo', 'ISO-8859-6', 'UTF8'); +-- UTF8 --> ISO-8859-7 +SELECT CONVERT('foo' USING utf8_to_iso_8859_7); +SELECT CONVERT('foo', 'UTF8', 'ISO-8859-7'); +-- ISO-8859-7 --> UTF8 +SELECT CONVERT('foo' USING iso_8859_7_to_utf8); +SELECT CONVERT('foo', 'ISO-8859-7', 'UTF8'); +-- UTF8 --> ISO-8859-8 +SELECT CONVERT('foo' USING utf8_to_iso_8859_8); +SELECT CONVERT('foo', 'UTF8', 'ISO-8859-8'); +-- ISO-8859-8 --> UTF8 +SELECT CONVERT('foo' USING iso_8859_8_to_utf8); +SELECT CONVERT('foo', 'ISO-8859-8', 'UTF8'); +-- LATIN1 --> UTF8 +SELECT CONVERT('foo' USING iso_8859_1_to_utf8); +SELECT CONVERT('foo', 'LATIN1', 'UTF8'); +-- UTF8 --> LATIN1 +SELECT CONVERT('foo' USING utf8_to_iso_8859_1); +SELECT CONVERT('foo', 'UTF8', 'LATIN1'); +-- JOHAB --> UTF8 +SELECT CONVERT('foo' USING johab_to_utf8); +SELECT CONVERT('foo', 'JOHAB', 'UTF8'); +-- UTF8 --> JOHAB +SELECT CONVERT('foo' USING utf8_to_johab); +SELECT CONVERT('foo', 'UTF8', 'JOHAB'); +-- SJIS --> UTF8 +SELECT CONVERT('foo' USING sjis_to_utf8); +SELECT CONVERT('foo', 'SJIS', 'UTF8'); +-- UTF8 --> SJIS +SELECT CONVERT('foo' USING utf8_to_sjis); +SELECT CONVERT('foo', 'UTF8', 'SJIS'); +-- WIN1258 --> UTF8 +SELECT CONVERT('foo' USING win1258_to_utf8); +SELECT CONVERT('foo', 'WIN1258', 'UTF8'); +-- UTF8 --> WIN1258 +SELECT CONVERT('foo' USING utf8_to_win1258); +SELECT CONVERT('foo', 'UTF8', 'WIN1258'); +-- UHC --> UTF8 +SELECT CONVERT('foo' USING uhc_to_utf8); +SELECT CONVERT('foo', 'UHC', 'UTF8'); +-- UTF8 --> UHC +SELECT CONVERT('foo' USING utf8_to_uhc); +SELECT CONVERT('foo', 'UTF8', 'UHC'); +-- UTF8 --> WIN1250 +SELECT CONVERT('foo' USING utf8_to_windows_1250); +SELECT CONVERT('foo', 'UTF8', 'WIN1250'); +-- WIN1250 --> UTF8 +SELECT CONVERT('foo' USING windows_1250_to_utf8); +SELECT CONVERT('foo', 'WIN1250', 'UTF8'); +-- UTF8 --> WIN1256 +SELECT CONVERT('foo' USING utf8_to_windows_1256); +SELECT CONVERT('foo', 'UTF8', 'WIN1256'); +-- WIN1256 --> UTF8 +SELECT CONVERT('foo' USING windows_1256_to_utf8); +SELECT CONVERT('foo', 'WIN1256', 'UTF8'); +-- UTF8 --> WIN874 +SELECT CONVERT('foo' USING utf8_to_windows_874); +SELECT CONVERT('foo', 'UTF8', 'WIN874'); +-- WIN874 --> UTF8 +SELECT CONVERT('foo' USING windows_874_to_utf8); +SELECT CONVERT('foo', 'WIN874', 'UTF8'); -- -- return to the super user -- |