1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
|
Add a variant of `locale_charset' that returns its result based solely on
information from the environment. See
http://lists.gnu.org/archive/html/guile-devel/2011-11/msg00040.html for the
rationale.
--- a/lib/localcharset.c
+++ b/lib/localcharset.c
@@ -544,3 +544,120 @@ locale_charset (void)
return codeset;
}
+
+/* A variant of the above, without calls to `setlocale', `nl_langinfo',
+ etc. */
+const char *
+environ_locale_charset (void)
+{
+ static char buf[2 + 10 + 1];
+ const char *codeset, *aliases;
+ const char *locale = NULL;
+
+ locale = getenv ("LC_ALL");
+ if (locale == NULL || locale[0] == '\0')
+ {
+ locale = getenv ("LC_CTYPE");
+ if (locale == NULL || locale[0] == '\0')
+ locale = getenv ("LANG");
+ }
+
+ if (locale != NULL && locale[0] != '\0')
+ {
+ /* If the locale name contains an encoding after the dot, return it. */
+ const char *dot = strchr (locale, '.');
+
+ if (dot != NULL)
+ {
+ const char *modifier;
+
+ dot++;
+ /* Look for the possible @... trailer and remove it, if any. */
+ modifier = strchr (dot, '@');
+ if (modifier == NULL)
+ return dot;
+ if (modifier - dot < sizeof (buf))
+ {
+ memcpy (buf, dot, modifier - dot);
+ buf [modifier - dot] = '\0';
+ return buf;
+ }
+ }
+ else if (strcmp (locale, "C") == 0)
+ {
+ strcpy (buf, "ASCII");
+ return buf;
+ }
+ else
+ codeset = "";
+ }
+ else
+ codeset = "";
+
+ /* Resolve alias. */
+ {
+# ifdef alias_table_defined
+ /* On some platforms, UTF-8 locales are the most frequently used ones.
+ Speed up the common case and slow down the less common cases by
+ testing for this case first. */
+# if defined __OpenBSD__ || (defined __APPLE__ && defined __MACH__) || defined __sun || defined __CYGWIN__
+ if (strcmp (codeset, "UTF-8") == 0)
+ goto done_table_lookup;
+ else
+# endif
+ {
+ const struct table_entry * const table = alias_table;
+ size_t const table_size =
+ sizeof (alias_table) / sizeof (struct table_entry);
+ /* The table is sorted. Perform a binary search. */
+ size_t hi = table_size;
+ size_t lo = 0;
+ while (lo < hi)
+ {
+ /* Invariant:
+ for i < lo, strcmp (table[i].alias, codeset) < 0,
+ for i >= hi, strcmp (table[i].alias, codeset) > 0. */
+ size_t mid = (hi + lo) >> 1; /* >= lo, < hi */
+ int cmp = strcmp (table[mid].alias, codeset);
+ if (cmp < 0)
+ lo = mid + 1;
+ else if (cmp > 0)
+ hi = mid;
+ else
+ {
+ /* Found an i with
+ strcmp (table[i].alias, codeset) == 0. */
+ codeset = table[mid].canonical;
+ goto done_table_lookup;
+ }
+ }
+ }
+ if (0)
+ done_table_lookup: ;
+ else
+# endif
+ {
+ /* Did not find it in the table. */
+ /* On Mac OS X, all modern locales use the UTF-8 encoding.
+ BeOS and Haiku have a single locale, and it has UTF-8 encoding. */
+# if (defined __APPLE__ && defined __MACH__) || defined __BEOS__ || defined __HAIKU__
+ codeset = "UTF-8";
+# else
+ /* Don't return an empty string. GNU libc and GNU libiconv interpret
+ the empty string as denoting "the locale's character encoding",
+ thus GNU libiconv would call this function a second time. */
+ if (codeset[0] == '\0')
+ codeset = "ASCII";
+# endif
+ }
+ }
+
+ /* Don't return an empty string. GNU libc and GNU libiconv interpret
+ the empty string as denoting "the locale's character encoding",
+ thus GNU libiconv would call this function a second time. */
+ if (codeset[0] == '\0')
+ /* Default to Latin-1, for backward compatibility with Guile 1.8. */
+ codeset = "ISO-8859-1";
+
+ return codeset;
+}
|
