updated according to the newest tables downloaded from ftp.unicode.org

diff --git a/charset/set/win-1250 b/charset/set/win-1250
index 09d7ffc3ec65d16c5babf5c76d40d9c8c6c0ba88..c3c88e01fe818fef55dfd130a205e9f46f388a82 100644 (file)
--- a/charset/set/win-1250
+++ b/charset/set/win-1250
@@ -1,38 +1,39 @@
-# Windows CP-1250 Charset File
-# Adapted from CStoCS "1250.enc" by Martin Mares <mj@atrey.karlin.mff.cuni.cz>
+# VENDORS/MICSFT/WINDOWS/CP1250.TXT charset file
+# Imported from ftp://ftp.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1250.TXT
+# (c) 2003, Robert Spalek <robert.cz>
 
-00     0000    <control>
-01     0001    <control>
-02     0002    <control>
-03     0003    <control>
-04     0004    <control>
-05     0005    <control>
-06     0006    <control>
-07     0007    <control>
-08     0008    <control>
-09     0009    <control>
-0A     000A    <control>
-0B     000B    <control>
-0C     000C    <control>
-0D     000D    <control>
-0E     000E    <control>
-0F     000F    <control>
-10     0010    <control>
-11     0011    <control>
-12     0012    <control>
-13     0013    <control>
-14     0014    <control>
-15     0015    <control>
-16     0016    <control>
-17     0017    <control>
-18     0018    <control>
-19     0019    <control>
-1A     001A    <control>
-1B     001B    <control>
-1C     001C    <control>
-1D     001D    <control>
-1E     001E    <control>
-1F     001F    <control>
+00     0000    NULL
+01     0001    START OF HEADING
+02     0002    START OF TEXT
+03     0003    END OF TEXT
+04     0004    END OF TRANSMISSION
+05     0005    ENQUIRY
+06     0006    ACKNOWLEDGE
+07     0007    BELL
+08     0008    BACKSPACE
+09     0009    HORIZONTAL TABULATION
+0A     000A    LINE FEED
+0B     000B    VERTICAL TABULATION
+0C     000C    FORM FEED
+0D     000D    CARRIAGE RETURN
+0E     000E    SHIFT OUT
+0F     000F    SHIFT IN
+10     0010    DATA LINK ESCAPE
+11     0011    DEVICE CONTROL ONE
+12     0012    DEVICE CONTROL TWO
+13     0013    DEVICE CONTROL THREE
+14     0014    DEVICE CONTROL FOUR
+15     0015    NEGATIVE ACKNOWLEDGE
+16     0016    SYNCHRONOUS IDLE
+17     0017    END OF TRANSMISSION BLOCK
+18     0018    CANCEL
+19     0019    END OF MEDIUM
+1A     001A    SUBSTITUTE
+1B     001B    ESCAPE
+1C     001C    FILE SEPARATOR
+1D     001D    GROUP SEPARATOR
+1E     001E    RECORD SEPARATOR
+1F     001F    UNIT SEPARATOR
 20     0020    SPACE
 21     0021    EXCLAMATION MARK
 22     0022    QUOTATION MARK
@@ -128,16 +129,13 @@
 7C     007C    VERTICAL LINE
 7D     007D    RIGHT CURLY BRACKET
 7E     007E    TILDE
-7F     007F    <control>
-80     FFFD    REPLACEMENT CHARACTER
-81     FFFD    REPLACEMENT CHARACTER
+7F     007F    DELETE
+80     20AC    EURO SIGN
 82     201A    SINGLE LOW-9 QUOTATION MARK
-83     FFFD    REPLACEMENT CHARACTER
 84     201E    DOUBLE LOW-9 QUOTATION MARK
-85     0EAF    LAO ELLIPSIS
+85     2026    HORIZONTAL ELLIPSIS
 86     2020    DAGGER
 87     2021    DOUBLE DAGGER
-88     FFFD    REPLACEMENT CHARACTER
 89     2030    PER MILLE SIGN
 8A     0160    LATIN CAPITAL LETTER S WITH CARON
 8B     2039    SINGLE LEFT-POINTING ANGLE QUOTATION MARK
@@ -145,7 +143,6 @@
 8D     0164    LATIN CAPITAL LETTER T WITH CARON
 8E     017D    LATIN CAPITAL LETTER Z WITH CARON
 8F     0179    LATIN CAPITAL LETTER Z WITH ACUTE
-90     FFFD    REPLACEMENT CHARACTER
 91     2018    LEFT SINGLE QUOTATION MARK
 92     2019    RIGHT SINGLE QUOTATION MARK
 93     201C    LEFT DOUBLE QUOTATION MARK
@@ -153,7 +150,6 @@
 95     2022    BULLET
 96     2013    EN DASH
 97     2014    EM DASH
-98     FFFD    REPLACEMENT CHARACTER
 99     2122    TRADE MARK SIGN
 9A     0161    LATIN SMALL LETTER S WITH CARON
 9B     203A    SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
@@ -162,14 +158,14 @@
 9E     017E    LATIN SMALL LETTER Z WITH CARON
 9F     017A    LATIN SMALL LETTER Z WITH ACUTE
 A0     00A0    NO-BREAK SPACE
-A1     030C    COMBINING CARON
-A2     0306    COMBINING BREVE
+A1     02C7    CARON
+A2     02D8    BREVE
 A3     0141    LATIN CAPITAL LETTER L WITH STROKE
 A4     00A4    CURRENCY SIGN
 A5     0104    LATIN CAPITAL LETTER A WITH OGONEK
 A6     00A6    BROKEN BAR
 A7     00A7    SECTION SIGN
-A8     0308    COMBINING DIAERESIS
+A8     00A8    DIAERESIS
 A9     00A9    COPYRIGHT SIGN
 AA     015E    LATIN CAPITAL LETTER S WITH CEDILLA
 AB     00AB    LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
@@ -179,18 +175,18 @@ AE        00AE    REGISTERED SIGN
 AF     017B    LATIN CAPITAL LETTER Z WITH DOT ABOVE
 B0     00B0    DEGREE SIGN
 B1     00B1    PLUS-MINUS SIGN
-B2     0328    COMBINING OGONEK
+B2     02DB    OGONEK
 B3     0142    LATIN SMALL LETTER L WITH STROKE
 B4     00B4    ACUTE ACCENT
-B5     03BC    GREEK SMALL LETTER MU
-B6     FFFD    REPLACEMENT CHARACTER
+B5     00B5    MICRO SIGN
+B6     00B6    PILCROW SIGN
 B7     00B7    MIDDLE DOT
-B8     0327    COMBINING CEDILLA
+B8     00B8    CEDILLA
 B9     0105    LATIN SMALL LETTER A WITH OGONEK
 BA     015F    LATIN SMALL LETTER S WITH CEDILLA
 BB     00BB    RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
 BC     013D    LATIN CAPITAL LETTER L WITH CARON
-BD     030B    COMBINING DOUBLE ACUTE ACCENT
+BD     02DD    DOUBLE ACUTE ACCENT
 BE     013E    LATIN SMALL LETTER L WITH CARON
 BF     017C    LATIN SMALL LETTER Z WITH DOT ABOVE
 C0     0154    LATIN CAPITAL LETTER R WITH ACUTE
@@ -209,7 +205,7 @@ CC  011A    LATIN CAPITAL LETTER E WITH CARON
 CD     00CD    LATIN CAPITAL LETTER I WITH ACUTE
 CE     00CE    LATIN CAPITAL LETTER I WITH CIRCUMFLEX
 CF     010E    LATIN CAPITAL LETTER D WITH CARON
-D0     00D0    LATIN CAPITAL LETTER ETH
+D0     0110    LATIN CAPITAL LETTER D WITH STROKE
 D1     0143    LATIN CAPITAL LETTER N WITH ACUTE
 D2     0147    LATIN CAPITAL LETTER N WITH CARON
 D3     00D3    LATIN CAPITAL LETTER O WITH ACUTE
@@ -241,7 +237,7 @@ EC  011B    LATIN SMALL LETTER E WITH CARON
 ED     00ED    LATIN SMALL LETTER I WITH ACUTE
 EE     00EE    LATIN SMALL LETTER I WITH CIRCUMFLEX
 EF     010F    LATIN SMALL LETTER D WITH CARON
-F0     00F0    LATIN SMALL LETTER ETH
+F0     0111    LATIN SMALL LETTER D WITH STROKE
 F1     0144    LATIN SMALL LETTER N WITH ACUTE
 F2     0148    LATIN SMALL LETTER N WITH CARON
 F3     00F3    LATIN SMALL LETTER O WITH ACUTE

diff --git a/charset/set/win-1252 b/charset/set/win-1252
index 220a108efefdb565bceac2d0e05675510560657a..0df841d940efe6209b8a973644d38b582bc8aca1 100644 (file)
--- a/charset/set/win-1252
+++ b/charset/set/win-1252
@@ -1,38 +1,39 @@
-# Windows-1252 Charset File
-# (c) 2001 Martin Mares <mj@ucw.cz>
+# VENDORS/MICSFT/WINDOWS/CP1252.TXT charset file
+# Imported from ftp://ftp.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1252.TXT
+# (c) 2003, Robert Spalek <robert.cz>
 
-00     0000    <control>
-01     0001    <control>
-02     0002    <control>
-03     0003    <control>
-04     0004    <control>
-05     0005    <control>
-06     0006    <control>
-07     0007    <control>
-08     0008    <control>
-09     0009    <control>
-0A     000A    <control>
-0B     000B    <control>
-0C     000C    <control>
-0D     000D    <control>
-0E     000E    <control>
-0F     000F    <control>
-10     0010    <control>
-11     0011    <control>
-12     0012    <control>
-13     0013    <control>
-14     0014    <control>
-15     0015    <control>
-16     0016    <control>
-17     0017    <control>
-18     0018    <control>
-19     0019    <control>
-1A     001A    <control>
-1B     001B    <control>
-1C     001C    <control>
-1D     001D    <control>
-1E     001E    <control>
-1F     001F    <control>
+00     0000    NULL
+01     0001    START OF HEADING
+02     0002    START OF TEXT
+03     0003    END OF TEXT
+04     0004    END OF TRANSMISSION
+05     0005    ENQUIRY
+06     0006    ACKNOWLEDGE
+07     0007    BELL
+08     0008    BACKSPACE
+09     0009    HORIZONTAL TABULATION
+0A     000A    LINE FEED
+0B     000B    VERTICAL TABULATION
+0C     000C    FORM FEED
+0D     000D    CARRIAGE RETURN
+0E     000E    SHIFT OUT
+0F     000F    SHIFT IN
+10     0010    DATA LINK ESCAPE
+11     0011    DEVICE CONTROL ONE
+12     0012    DEVICE CONTROL TWO
+13     0013    DEVICE CONTROL THREE
+14     0014    DEVICE CONTROL FOUR
+15     0015    NEGATIVE ACKNOWLEDGE
+16     0016    SYNCHRONOUS IDLE
+17     0017    END OF TRANSMISSION BLOCK
+18     0018    CANCEL
+19     0019    END OF MEDIUM
+1A     001A    SUBSTITUTE
+1B     001B    ESCAPE
+1C     001C    FILE SEPARATOR
+1D     001D    GROUP SEPARATOR
+1E     001E    RECORD SEPARATOR
+1F     001F    UNIT SEPARATOR
 20     0020    SPACE
 21     0021    EXCLAMATION MARK
 22     0022    QUOTATION MARK
@@ -128,9 +129,8 @@
 7C     007C    VERTICAL LINE
 7D     007D    RIGHT CURLY BRACKET
 7E     007E    TILDE
-7F     007F    <control>
+7F     007F    DELETE
 80     20AC    EURO SIGN
-81     0081    <control>
 82     201A    SINGLE LOW-9 QUOTATION MARK
 83     0192    LATIN SMALL LETTER F WITH HOOK
 84     201E    DOUBLE LOW-9 QUOTATION MARK
@@ -142,10 +142,7 @@
 8A     0160    LATIN CAPITAL LETTER S WITH CARON
 8B     2039    SINGLE LEFT-POINTING ANGLE QUOTATION MARK
 8C     0152    LATIN CAPITAL LIGATURE OE
-8D     008D    <control>
 8E     017D    LATIN CAPITAL LETTER Z WITH CARON
-8F     008F    <control>
-90     0090    <control>
 91     2018    LEFT SINGLE QUOTATION MARK
 92     2019    RIGHT SINGLE QUOTATION MARK
 93     201C    LEFT DOUBLE QUOTATION MARK
@@ -158,7 +155,6 @@
 9A     0161    LATIN SMALL LETTER S WITH CARON
 9B     203A    SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
 9C     0153    LATIN SMALL LIGATURE OE
-9D     009D    <control>
 9E     017E    LATIN SMALL LETTER Z WITH CARON
 9F     0178    LATIN CAPITAL LETTER Y WITH DIAERESIS
 A0     00A0    NO-BREAK SPACE