summaryrefslogtreecommitdiff
path: root/biblio/bibtex/contrib/gost/bibtex/csf/utf8cyrillic.csf
diff options
context:
space:
mode:
Diffstat (limited to 'biblio/bibtex/contrib/gost/bibtex/csf/utf8cyrillic.csf')
-rw-r--r--biblio/bibtex/contrib/gost/bibtex/csf/utf8cyrillic.csf275
1 files changed, 275 insertions, 0 deletions
diff --git a/biblio/bibtex/contrib/gost/bibtex/csf/utf8cyrillic.csf b/biblio/bibtex/contrib/gost/bibtex/csf/utf8cyrillic.csf
new file mode 100644
index 0000000000..60d4550a13
--- /dev/null
+++ b/biblio/bibtex/contrib/gost/bibtex/csf/utf8cyrillic.csf
@@ -0,0 +1,275 @@
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+%%
+%% CHARACTER SET: Cyrillic (utf8)
+%%
+%% SORTING ORDER: Ukrainian/Russian (First Cyrillic then Latin)
+%%
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+%%
+%% FILE FORMAT
+%%
+%% The codepage and sorting order (CS) file defines how BibTeX will treat an
+%% 8-bit character set, specifically which characters are to be treated as
+%% letters, the upper/lower case relationships between characters, and the
+%% sorting order of characters.
+%%
+%% The CS file may contain a number of sections, each presented in the
+%% form of a TeX macro:
+%%
+%% \section-name{
+%% <section definitions>
+%% }
+%%
+%% Four sections are currently supported: \lowupcase, \lowercase, \uppercase
+%% and \order. The syntax of the four supported sections is summarised below.
+%%
+%% 8-bit characters may be entered naturally, but to avoid problems with
+%% character set translation or corruption, they can also be entered using
+%% the TeX-style portable notation for character codes, i.e. ^^XX, where XX
+%% is the hexadecimal value ofthe character code.
+%%
+%% Reading of the sections ends when the first '}' character is reached, so
+%% '}' can't be included in a section. You can't use ^^7d either.
+%%
+%% The percent sign ('%') is used to introduce a trailing comment - it and
+%% all remaining characters on a line are ignored. ^^25 has the same effect.
+%%
+%%
+%% \lowupcase section
+%%
+%% The \lowupcase section of the CS file is used to define the lower
+%% /upper and upper/lower case relationship of pairs of specified
+%% characters. It is only used if the relationship is symmetrical - use
+%% \lowercase or \upcase if it isn't.
+%%
+%% The syntax of the \lowupcase section is:
+%%
+%% \lowupcase{
+%% <LC-1> <UC-1> % Comment begins with a percent sign
+%% <LC-2> <UC-2>
+%% ...
+%% <LC-N> <UC-N>
+%% }
+%%
+%% Each <LC-n> <UC-n> pair of characters defines that the upper case
+%% equivalent of <LC-n> is <UC-n> *and* the lower case equivalent of
+%% <UC-n> is <LC-n>.
+%%
+%% You cannot redefine the lower or upper case equivalent of an ASCII
+%% character (code < 128), so all instances of <LC-n> and <UC-n>
+%% (i.e. both sides of the relationship) must have codes > 127.
+%%
+%%
+%% \lowercase section
+%%
+%% The \lowercase section of the CS file is used to define the lower case
+%% equivalent of specified characters. It should normally only be used
+%% if the relationship isn't symmetrical - use \lowupcase if it is.
+%%
+%% The syntax of the \lowercase section is:
+%%
+%% \lowercase{
+%% <UC-1> <LC-1> % Comment begins with a percent sign
+%% <UC-2> <LC-2>
+%% ...
+%% <UC-N> <LC-N>
+%% }
+%%
+%% Each <LC-n> <UC-n> pair of characters defines that the lower case
+%% equivalent of <UC-n> is <LC-n>.
+%%
+%% You cannot redefine the lower case equivalent of an ASCII character
+%% (code < 128), so all instances of <UC-n> (i.e. the left hand side
+%% of the relationship) must have codes > 127.
+%%
+%%
+%% \uppercase section
+%%
+%% The \uppercase section of the CS file is used to define the upper case
+%% equivalent of specified characters. It should normally only be used
+%% if the relationship isn't symmetrical - use \lowupcase if it is.
+%%
+%% The syntax of the \uppercase section is:
+%%
+%% \uppercase{
+%% <LC-1> <UC-1> % Comment begins with a percent sign
+%% <LC-2> <UC-2>
+%% ...
+%% <LC-N> <UC-N>
+%% }
+%%
+%% Each <LC-n> <UC-n> pair of characters defines that the upper case
+%% case equivalent of <LC-n> is <UC-n>.
+%%
+%% You cannot redefine the upper case equivalent of an ASCII character
+%% (code < 128), so all instances of <LC-n> (i.e. the left hand side
+%% of the relationship) must have codes > 127.
+%%
+%%
+%% \order section
+%%
+%% The \order section of the CS file is used to define the order in which
+%% characters are sorted.
+%%
+%% The syntax of the \order section is:
+%%
+%% \order{
+%% <char-1> % Comment begins with a percent sign
+%% <char-2> <char-3> % whitespace between the chars
+%% <char-4> - <char-5> % a hyphen between the chars
+%% <char-4> _ <char-5> % an underscore between the chars
+%% ...
+%% <char-n>
+%% }
+%%
+%% All characters on the same line are given the same sorting weight.
+%%
+%% The construct <char-1> <underscore> <char-2> is used to denote that
+%% all characters in the range <char-1> to <char-2> should be given the
+%% same sorting weight. For example, "A _ Z" would cause all ASCII
+%% upper case alphabetical characters to have the same sorting weight
+%% and would be equivalent to placing all 26 characters on the same line.
+%%
+%% The construct <char-1> <hyphen> <char-2> is used to denote that all
+%% characters in the range <char-1> to <char-2> should be given an
+%% ascending set of sorting weights, starting with <char-1> and ending
+%% with <char-2>. For example, "A - Z" would cause all upper case ASCII
+%% alphabetical characters to be sorted in ascending order and would be
+%% equivalent to placing 'A' on the first line, 'B' on the second,
+%% through to 'Z' on the 26th line.
+%%
+%% The characters at the beginning of the order section are given a lower
+%% sorting weight than characters occuring later. When sorting
+%% alphabetically, characters with the lowest weight come first.
+%%
+%% All characters not in the \order section (including ASCII characters)
+%% are given the same very high sorting weight to ensure that they come
+%% last when sorting alphabetically.
+%%
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+
+
+%%
+%% CHARACTER SET
+%%
+\lowupcase{
+ а А
+ б Б
+ в В
+ г Г
+ ґ Ґ
+ д Д
+ е Е
+ є Є
+ ё Ё
+ ж Ж
+ з З
+ и И
+ і І
+ ї Ї
+ й Й
+ к К
+ л Л
+ м М
+ н Н
+ о О
+ п П
+ р Р
+ с С
+ т Т
+ у У
+ ф Ф
+ х Х
+ ц Ц
+ ч Ч
+ ш Ш
+ щ Щ
+ ъ Ъ
+ ы Ы
+ ь Ь
+ э Э
+ ю Ю
+ я Я
+}
+
+
+
+%%
+%% SORTING ORDER
+%%
+%%
+\order{
+ 0-9
+ А а
+ Б б
+ В в
+ Г г
+ Ґ ґ
+ Д д
+ Е е
+ Є є
+ Ё ё
+ Ж ж
+ З з
+ И и
+ І і
+ Ї ї
+ Й й
+ К к
+ Л л
+ М м
+ Н н
+ О о
+ П п
+ Р р
+ С с
+ Т т
+ У у
+ Ф ф
+ Х х
+ Ц ц
+ Ч ч
+ Ш ш
+ Щ щ
+ Ъ ъ
+ Ы ы
+ Ь ь
+ Э э
+ Ю ю
+ Я я
+ A a
+ B b
+ C c
+ D d
+ E e
+ F f
+ G g
+ H h
+ I i
+ J j
+ K k
+ L l
+ M m
+ N n
+ O o
+ P p
+ Q q
+ R r
+ S s
+ T t
+ U u
+ V v
+ W w
+ X x
+ Y y
+ Z z
+}
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% END OF FILE %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%