summaryrefslogtreecommitdiff
path: root/biblio/bibtex/bibtex-x/tests/sort3.csf
diff options
context:
space:
mode:
Diffstat (limited to 'biblio/bibtex/bibtex-x/tests/sort3.csf')
-rw-r--r--biblio/bibtex/bibtex-x/tests/sort3.csf281
1 files changed, 281 insertions, 0 deletions
diff --git a/biblio/bibtex/bibtex-x/tests/sort3.csf b/biblio/bibtex/bibtex-x/tests/sort3.csf
new file mode 100644
index 0000000000..909cf0f60e
--- /dev/null
+++ b/biblio/bibtex/bibtex-x/tests/sort3.csf
@@ -0,0 +1,281 @@
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+%
+% CHARACTER SET: ISO 8859-1 (Latin 1)
+%
+% ISO 8859-1 is the system character set used by Unix/X Windows and
+% MS Windows.
+%
+% SORTING ORDER: Swedish
+%
+% Alphabetical sorting order of Aa..Zz (including accented characters).
+%
+% This is a BibTeX Codepage and Sort definition file (CSF). It is
+% used to define the 8-bit character set used by BibTeX and the
+% order in which those characters should be sorted. The file
+% format is documented below this header section.
+%
+% This file will only work with the 8-bit implementation of BibTeX
+% written by Niel Kempson and Alejandro Aguilar-Sierra:
+%
+% http://www.ctan.org/tex-archive/biblio/bibtex/8-bit/
+%
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+%
+% 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{ % Lowercase Uppercase
+ % Code TeX Code TeX
+ %
+ à À % ^^e0 \`{a} ^^c0 \`{A}
+ á Á % ^^e1 \'{a} ^^c1 \'{A}
+ â Â % ^^e2 \^{a} ^^c2 \^{A}
+ ã Ã % ^^e3 \~{a} ^^c3 \~{A}
+ ä Ä % ^^e4 \"{a} ^^c4 \"{A}
+ å Å % ^^e5 \aa ^^c5 \AA
+ æ Æ % ^^e6 \ae ^^c6 \AE
+ ç Ç % ^^e7 \c{c} ^^c7 \c{C}
+ è È % ^^e8 \`{e} ^^c8 \`{E}
+ é É % ^^e9 \'{e} ^^c9 \'{E}
+ ê Ê % ^^ea \^{e} ^^ca \^{E}
+ ë Ë % ^^eb \"{e} ^^cb \"{E}
+ ì Ì % ^^ec \`{\i} ^^cc \`{I}
+ í Í % ^^ed \'{\i} ^^cd \'{I}
+ î Î % ^^ee \^{\i} ^^ce \^{I}
+ ï Ï % ^^ef \"{\i} ^^cf \"{I}
+ ð Ð % ^^f0 \dh ^^d0 \DH
+ ñ Ñ % ^^f1 \~{n} ^^d1 \~{N}
+ ò Ò % ^^f2 \`{o} ^^d2 \`{O}
+ ó Ó % ^^f3 \'{o} ^^d3 \'{O}
+ ô Ô % ^^f4 \^{o} ^^d4 \^{O}
+ õ Õ % ^^f5 \~{o} ^^d5 \~{O}
+ ö Ö % ^^f6 \"{o} ^^d6 \"{O}
+ ø Ø % ^^f8 \o ^^d8 \O
+ ù Ù % ^^f9 \`{u} ^^d9 \`{U}
+ ú Ú % ^^fa \'{u} ^^da \'{U}
+ û Û % ^^fb \^{u} ^^db \^{U}
+ ü Ü % ^^fc \"{u} ^^dc \"{U}
+ ý Ý % ^^fd \'{y} ^^dd \'{Y}
+ þ Þ % ^^fe \th ^^de \TH
+}
+
+% SORTING ORDER
+
+\order{
+ 0-9
+ A
+ À Á Â Ã Æ
+ a
+ à á â ã æ
+ B
+ b
+ C Ç
+ c ç
+ D Ð
+ d ð
+ E
+ È É Ê Ë
+ e
+ è é ê ë
+ F
+ f
+ G
+ g
+ H
+ h
+ I
+ Ì Í Î Ï
+ i
+ ì í î ï
+ J
+ j
+ K
+ k
+ L
+ l
+ M
+ m
+ N Ñ
+ n ñ
+ O
+ Ò Ó Ô Õ Ø
+ o
+ ò ó ô õ ø
+ P
+ p
+ Q
+ q
+ R
+ r
+ S
+ s ß
+ T Þ
+ t þ
+ U
+ Ù Ú Û Ü
+ u
+ ù ú û ü
+ V
+ v
+ W
+ w
+ X
+ x
+ Y
+ Ý
+ y
+ ý ÿ
+ Z
+ z
+ Å
+ å
+ Ä
+ ä
+ Ö
+ ö
+}
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% END OF FILE %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%