1 dnl PSPP - a program for statistical analysis.
2 dnl Copyright (C) 2017 Free Software Foundation, Inc.
4 dnl This program is free software: you can redistribute it and/or modify
5 dnl it under the terms of the GNU General Public License as published by
6 dnl the Free Software Foundation, either version 3 of the License, or
7 dnl (at your option) any later version.
9 dnl This program is distributed in the hope that it will be useful,
10 dnl but WITHOUT ANY WARRANTY; without even the implied warranty of
11 dnl MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
12 dnl GNU General Public License for more details.
14 dnl You should have received a copy of the GNU General Public License
15 dnl along with this program. If not, see <http://www.gnu.org/licenses/>.
17 AT_BANNER([i18n recoding])
19 # CHECK_I18N_RECODE([TITLE], [FROM-CODING], [TO-CODING],
20 # [FROM-TEXT], [TO-TEXT])
22 # Converts FROM-TEXT from FROM-CODING to TO-CODING and checks that the result
23 # is TO-TEXT. The "printf" program is applied to both FROM-TEXT and TO-TEXT to
24 # allow for backslash-escapes. (Hex escapes are not portable; use octal
26 m4_define([CHECK_I18N_RECODE],
27 [AT_SETUP([convert $1])
30 dnl Skip the test if this host doesn't know the source and target encodings.
31 AT_CHECK([i18n-test supports_encodings '$2' '$3'])
32 AT_CHECK_UNQUOTED([i18n-test recode '$2' '$3' `printf '$4'`], [0], [`printf '$5'`
36 CHECK_I18N_RECODE([reflexively], [ASCII], [ASCII], [abc], [abc])
37 CHECK_I18N_RECODE([without any change], [ASCII], [UTF-8], [abc], [abc])
39 CHECK_I18N_RECODE([from ISO-8859-1 to UTF-8], [ISO-8859-1], [UTF-8],
41 CHECK_I18N_RECODE([from UTF-8 to ISO-8859-1], [UTF-8], [ISO-8859-1],
44 # 0xc0 == 0300 is invalid in UTF-8
45 CHECK_I18N_RECODE([invalid UTF-8 to ISO-8859-1], [UTF-8], [ISO-8859-1],
47 # 0xc2 == 0302 is the first byte of a 2-byte UTF-8 sequence
48 CHECK_I18N_RECODE([truncated UTF-8 to ISO-8559-1], [UTF-8], [ISO-8859-1],
51 # Checks for a bug that caused the last character to be dropped in conversions
52 # from encodings that have combining diacritics (e.g. windows-1258).
53 CHECK_I18N_RECODE([dropped final character in windows-1258], [windows-1258],
54 [UTF-8], [aeiou], [aeiou])
56 dnl The input to this test is 7 bytes long and the expected output is 9 bytes.
57 dnl So it should exercise the E2BIG case
58 CHECK_I18N_RECODE([from ISO-8859-1 to UTF-8 with overflow],
59 [ISO-8859-1], [UTF-8],
60 [Tsch\374\337!], [Tsch\303\274\303\237!])
62 AT_SETUP([convert unknown encoding])
64 AT_CHECK([i18n-test recode nonexistent1 nonexistent2 asdf], [0], [asdf
66 [Warning: cannot create a converter for `nonexistent1' to `nonexistent2': Invalid argument
70 AT_BANNER([i18n concatenation])
72 # CHECK_I18N_CONCAT([HEAD], [TAIL], [ENCODING], [MAX-LEN], [ANSWER])
74 # Concatenates HEAD and TAIL, omitting as many characters from HEAD as needed
75 # to make the result come out to no more than MAX-LEN bytes if it was expressed
76 # in ENCODING, and checks that the answer matches ANSWER. HEAD, TAIL, and
77 # ANSWER are all in UTF-8. The "printf" program is applied to HEAD, TAIL, and
78 # ANSWER to allow for backslash-escapes. (Hex escapes are not portable; use
79 # octal escapes instead.)
80 m4_define([CHECK_I18N_CONCAT],
81 [AT_SETUP([m4_if([$2], [], [truncate "$1" to $4 bytes in $3],
82 [truncate "$1" + "$2" to $4 bytes in $3])])
85 dnl Skip the test if this host doesn't know the encoding.
86 AT_CHECK([i18n-test supports_encodings '$3'])
88 [i18n-test concat "`printf '$1'`" "`printf '$2'`" '$3' '$4'], [0],
93 CHECK_I18N_CONCAT([abc], [], [UTF-8], [6], [abc])
94 CHECK_I18N_CONCAT([], [xyz], [UTF-8], [6], [xyz])
95 CHECK_I18N_CONCAT([], [], [UTF-8], [6], [])
96 CHECK_I18N_CONCAT([abcdefghij], [], [UTF-8], [6], [abcdef])
97 CHECK_I18N_CONCAT([], [tuvwxyz], [UTF-8], [6], [tuvwxyz])
99 CHECK_I18N_CONCAT([abc], [xyz], [UTF-8], [6], [abcxyz])
100 CHECK_I18N_CONCAT([abcd], [xyz], [UTF-8], [6], [abcxyz])
101 CHECK_I18N_CONCAT([abc], [uvwxyz], [UTF-8], [6], [uvwxyz])
103 # x in a box ( x⃞ ) is U+0078, U+20DE, 4 bytes in UTF-8, and one grapheme
105 CHECK_I18N_CONCAT([x\342\203\236], [y], [UTF-8], [0], [y])
106 CHECK_I18N_CONCAT([x\342\203\236], [y], [UTF-8], [1], [y])
107 CHECK_I18N_CONCAT([x\342\203\236], [y], [UTF-8], [2], [y])
108 CHECK_I18N_CONCAT([x\342\203\236], [y], [UTF-8], [3], [y])
109 CHECK_I18N_CONCAT([x\342\203\236], [y], [UTF-8], [4], [y])
110 CHECK_I18N_CONCAT([x\342\203\236], [y], [UTF-8], [5], [x\342\203\236y])
112 # éèä is only 3 bytes in ISO-8859-1.
113 CHECK_I18N_CONCAT([\303\251\303\250\303\244], [xyz], [ISO-8859-1], [0], [xyz])
114 CHECK_I18N_CONCAT([\303\251\303\250\303\244], [xyz], [ISO-8859-1], [1], [xyz])
115 CHECK_I18N_CONCAT([\303\251\303\250\303\244], [xyz], [ISO-8859-1], [2], [xyz])
116 CHECK_I18N_CONCAT([\303\251\303\250\303\244], [xyz], [ISO-8859-1], [3], [xyz])
117 CHECK_I18N_CONCAT([\303\251\303\250\303\244], [xyz], [ISO-8859-1], [4],
119 CHECK_I18N_CONCAT([\303\251\303\250\303\244], [xyz], [ISO-8859-1], [5],
120 [\303\251\303\250xyz])
121 CHECK_I18N_CONCAT([\303\251\303\250\303\244], [xyz], [ISO-8859-1], [6],
122 [\303\251\303\250\303\244xyz])