diff options
| -rw-r--r-- | localedata/ChangeLog | 7 | ||||
| -rw-r--r-- | localedata/locales/translit_combining | 18 | ||||
| -rw-r--r-- | localedata/locales/translit_compat | 18 | ||||
| -rw-r--r-- | localedata/locales/translit_fraction | 35 |
4 files changed, 50 insertions, 28 deletions
diff --git a/localedata/ChangeLog b/localedata/ChangeLog index e420ad0bde..3c4195fd2f 100644 --- a/localedata/ChangeLog +++ b/localedata/ChangeLog @@ -1,3 +1,10 @@ +2000-11-03 Bruno Haible <haible@clisp.cons.org> + + * locales/translit_neutral: Add more entries. Mostly from Markus Kuhn. + * locales/translit_compat: Add a few ligatures. + * locales/translit_combining: Add a few plain ASCII alternatives. + * locales/translit_fraction: Likewise. Surround with spaces. + 2000-10-29 Bruno Haible <haible@clisp.cons.org> * locales/translit_hangul: New file. diff --git a/localedata/locales/translit_combining b/localedata/locales/translit_combining index f415f7e734..86a932bc5c 100644 --- a/localedata/locales/translit_combining +++ b/localedata/locales/translit_combining @@ -525,9 +525,9 @@ translit_start % LATIN SMALL LETTER A WITH DOT ABOVE AND MACRON <U01E1> <U0061> % LATIN CAPITAL LETTER AE WITH MACRON -<U01E2> <U00C6> +<U01E2> <U00C6>;"<U0041><U0045>" % LATIN SMALL LETTER AE WITH MACRON -<U01E3> <U00E6> +<U01E3> <U00E6>;"<U0061><U0065>" % LATIN CAPITAL LETTER G WITH CARON <U01E6> <U0047> % LATIN SMALL LETTER G WITH CARON @@ -563,9 +563,9 @@ translit_start % LATIN SMALL LETTER A WITH RING ABOVE AND ACUTE <U01FB> <U0061> % LATIN CAPITAL LETTER AE WITH ACUTE -<U01FC> <U00C6> +<U01FC> <U00C6>;"<U0041><U0045>" % LATIN SMALL LETTER AE WITH ACUTE -<U01FD> <U00E6> +<U01FD> <U00E6>;"<U0061><U0065>" % LATIN CAPITAL LETTER O WITH STROKE AND ACUTE <U01FE> <U004F> % LATIN SMALL LETTER O WITH STROKE AND ACUTE @@ -1911,9 +1911,9 @@ translit_start % GREEK OXIA <U1FFD> <U00B4> % EN QUAD -<U2000> <U2002> +<U2000> <U2002>;<U0020> % EM QUAD -<U2001> <U2003> +<U2001> <U2003>;<U0020> % OHM SIGN <U2126> <U03A9> % KELVIN SIGN @@ -1921,9 +1921,9 @@ translit_start % ANGSTROM SIGN <U212B> <U00C5> % LEFT-POINTING ANGLE BRACKET -<U2329> <U3008> +<U2329> <U3008>;<U003C> % RIGHT-POINTING ANGLE BRACKET -<U232A> <U3009> +<U232A> <U3009>;<U003E> % HIRAGANA LETTER GA <U304C> <U304B> % HIRAGANA LETTER GI @@ -2043,7 +2043,7 @@ translit_start % HEBREW LETTER YOD WITH HIRIQ <UFB1D> <U05D9> % HEBREW LIGATURE YIDDISH YOD YOD PATAH -<UFB1F> <U05F2> +<UFB1F> <U05F2>;"<U05D9><U05D9>" % HEBREW LETTER SHIN WITH SHIN DOT <UFB2A> <U05E9> % HEBREW LETTER SHIN WITH SIN DOT diff --git a/localedata/locales/translit_compat b/localedata/locales/translit_compat index 2240a809a1..ba07c2f066 100644 --- a/localedata/locales/translit_compat +++ b/localedata/locales/translit_compat @@ -1,17 +1,19 @@ escape_char / comment_char % -% Transliterations of compatibility characters. +% Transliterations of compatibility characters and ligatures. % Generated through % $ grep '^[^;]*;[^;]*;[^;]*;[^;]*;[^;]*;<compat>[^;]*;' UnicodeData.txt | \ % sed -e 's/^\([^;]*\);\([^;]*\);[^;]*;[^;]*;[^;]*;<compat> \([^;]*\);.*$/<U\1> "<U\3>"% \2/' | grep -v '0020 03[0-6][0-9A-F]' | sed -e 'h' -e 's/^\([^%]*\)% .*$/\1/' -e 's/\([0-9A-F]\) \([0-9A-F]\)/\1><U\2/g' -e 'x' -e 's/^[^%]*\(% .*\)$/\1/' -e 'G' +% and +% $ grep '[^;]*;[^;]*LIGATURE[^;]*;' UnicodeData.txt LC_CTYPE translit_start % MICRO SIGN -<U00B5> "<U03BC>" +<U00B5> "<U03BC>";<U0075> % LATIN CAPITAL LIGATURE IJ <U0132> "<U0049><U004A>" % LATIN SMALL LIGATURE IJ @@ -21,7 +23,11 @@ translit_start % LATIN SMALL LETTER L WITH MIDDLE DOT <U0140> "<U006C><U00B7>" % LATIN SMALL LETTER N PRECEDED BY APOSTROPHE -<U0149> "<U02BC><U006E>" +<U0149> "<U02BC><U006E>";"<U0027><U006E>" +% LATIN CAPITAL LIGATURE OE +<U0152> "<U004F><U0045>" +% LATIN SMALL LIGATURE OE +<U0153> "<U006F><U0065>" % LATIN SMALL LETTER LONG S <U017F> "<U0073>" % LATIN CAPITAL LETTER DZ WITH CARON @@ -66,6 +72,12 @@ translit_start <U03F2> "<U03C2>" % ARMENIAN SMALL LIGATURE ECH YIWN <U0587> "<U0565><U0582>" +% HEBREW LIGATURE YIDDISH DOUBLE VAV +<U05F0> "<U05D5><U05D5>" +% HEBREW LIGATURE YIDDISH VAV YOD +<U05F1> "<U05D5><U05D9>" +% HEBREW LIGATURE YIDDISH DOUBLE YOD +<U05F2> "<U05D9><U05D9>" % ARABIC LETTER HIGH HAMZA ALEF <U0675> "<U0627><U0674>" % ARABIC LETTER HIGH HAMZA WAW diff --git a/localedata/locales/translit_fraction b/localedata/locales/translit_fraction index 9a8d0e98e2..50dbd78b65 100644 --- a/localedata/locales/translit_fraction +++ b/localedata/locales/translit_fraction @@ -5,43 +5,46 @@ comment_char % % Generated through % $ grep '^[^;]*;[^;]*;[^;]*;[^;]*;[^;]*;<fraction>[^;]*;' UnicodeData.txt | \ % sed -e 's/^\([^;]*\);\([^;]*\);[^;]*;[^;]*;[^;]*;<fraction> \([^;]*\);.*$/<U\1> "<U\3>"% \2/' -e 'h' -e 's/^\([^%]*\)% .*$/\1/' -e 's/\([0-9A-F]\) \([0-9A-F]\)/\1><U\2/g' -e 'x' -e 's/^[^%]*\(% .*\)$/\1/' -e 'G' +% +% The replacements have been surrounded with spaces, because fractions are +% often preceded by a decimal number and followed by a unit or a math symbol. LC_CTYPE translit_start % VULGAR FRACTION ONE QUARTER -<U00BC> "<U0031><U2044><U0034>";"<U0031><U002F><U0034>" +<U00BC> "<U0020><U0031><U2044><U0034><U0020>";"<U0020><U0031><U002F><U0034><U0020>" % VULGAR FRACTION ONE HALF -<U00BD> "<U0031><U2044><U0032>";"<U0031><U002F><U0032>" +<U00BD> "<U0020><U0031><U2044><U0032><U0020>";"<U0020><U0031><U002F><U0032><U0020>" % VULGAR FRACTION THREE QUARTERS -<U00BE> "<U0033><U2044><U0034>";"<U0033><U002F><U0034>" +<U00BE> "<U0020><U0033><U2044><U0034><U0020>";"<U0020><U0033><U002F><U0034><U0020>" % VULGAR FRACTION ONE THIRD -<U2153> "<U0031><U2044><U0033>";"<U0031><U002F><U0033>" +<U2153> "<U0020><U0031><U2044><U0033><U0020>";"<U0020><U0031><U002F><U0033><U0020>" % VULGAR FRACTION TWO THIRDS -<U2154> "<U0032><U2044><U0033>";"<U0032><U002F><U0033>" +<U2154> "<U0020><U0032><U2044><U0033><U0020>";"<U0020><U0032><U002F><U0033><U0020>" % VULGAR FRACTION ONE FIFTH -<U2155> "<U0031><U2044><U0035>";"<U0031><U002F><U0035>" +<U2155> "<U0020><U0031><U2044><U0035><U0020>";"<U0020><U0031><U002F><U0035><U0020>" % VULGAR FRACTION TWO FIFTHS -<U2156> "<U0032><U2044><U0035>";"<U0032><U002F><U0035>" +<U2156> "<U0020><U0032><U2044><U0035><U0020>";"<U0020><U0032><U002F><U0035><U0020>" % VULGAR FRACTION THREE FIFTHS -<U2157> "<U0033><U2044><U0035>";"<U0033><U002F><U0035>" +<U2157> "<U0020><U0033><U2044><U0035><U0020>";"<U0020><U0033><U002F><U0035><U0020>" % VULGAR FRACTION FOUR FIFTHS -<U2158> "<U0034><U2044><U0035>";"<U0034><U002F><U0035>" +<U2158> "<U0020><U0034><U2044><U0035><U0020>";"<U0020><U0034><U002F><U0035><U0020>" % VULGAR FRACTION ONE SIXTH -<U2159> "<U0031><U2044><U0036>";"<U0031><U002F><U0036>" +<U2159> "<U0020><U0031><U2044><U0036><U0020>";"<U0020><U0031><U002F><U0036><U0020>" % VULGAR FRACTION FIVE SIXTHS -<U215A> "<U0035><U2044><U0036>";"<U0035><U002F><U0036>" +<U215A> "<U0020><U0035><U2044><U0036><U0020>";"<U0020><U0035><U002F><U0036><U0020>" % VULGAR FRACTION ONE EIGHTH -<U215B> "<U0031><U2044><U0038>";"<U0031><U002F><U0038>" +<U215B> "<U0020><U0031><U2044><U0038><U0020>";"<U0020><U0031><U002F><U0038><U0020>" % VULGAR FRACTION THREE EIGHTHS -<U215C> "<U0033><U2044><U0038>";"<U0033><U002F><U0038>" +<U215C> "<U0020><U0033><U2044><U0038><U0020>";"<U0020><U0033><U002F><U0038><U0020>" % VULGAR FRACTION FIVE EIGHTHS -<U215D> "<U0035><U2044><U0038>";"<U0035><U002F><U0038>" +<U215D> "<U0020><U0035><U2044><U0038><U0020>";"<U0020><U0035><U002F><U0038><U0020>" % VULGAR FRACTION SEVEN EIGHTHS -<U215E> "<U0037><U2044><U0038>";"<U0037><U002F><U0038>" +<U215E> "<U0020><U0037><U2044><U0038><U0020>";"<U0020><U0037><U002F><U0038><U0020>" % FRACTION NUMERATOR ONE -<U215F> "<U0031><U2044>" +<U215F> "<U0020><U0031><U2044>";"<U0020><U0031><U002F>" translit_end |