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
|
commit f25f0b75bbeb485961dc139aed6b5b474552d043 (HEAD -> main)
Author: Taiki Sugawara <buzz.taiki@gmail.com>
Date: Wed May 12 18:26:11 2021 +0900
natspec patch for p7zip 17.x
diff --git a/CPP/7zip/Archive/Zip/ZipItem.cpp b/CPP/7zip/Archive/Zip/ZipItem.cpp
index 353e895..44071f3 100644
--- a/CPP/7zip/Archive/Zip/ZipItem.cpp
+++ b/CPP/7zip/Archive/Zip/ZipItem.cpp
@@ -1,9 +1,7 @@
// Archive/ZipItem.cpp
-#if (!defined _WIN32) && (!defined __CYGWIN__) && (!defined __APPLE__)
#include <iconv.h>
-#include <locale.h>
-#endif
+#include <natspec.h>
#include "StdAfx.h"
@@ -355,87 +353,15 @@ void CItem::GetUnicodeString(UString &res, const AString &s, bool isComment, boo
#endif
}
- #if (!defined _WIN32) && (!defined __CYGWIN__) && (!defined __APPLE__)
- // Convert OEM char set to UTF-8 if needed
- // Use system locale to select code page
-
- Byte hostOS = GetHostOS();
- if (!isUtf8 && ((hostOS == NFileHeader::NHostOS::kFAT) || (hostOS == NFileHeader::NHostOS::kNTFS))) {
-
- const char *oemcp;
- oemcp = getenv("OEMCP");
- if (!oemcp) {
- oemcp = "CP437\0"; // CP name is 6 chars max
-
- const char *lc_to_cp_table[] = {
- "af_ZA", "CP850", "ar_SA", "CP720", "ar_LB", "CP720", "ar_EG", "CP720",
- "ar_DZ", "CP720", "ar_BH", "CP720", "ar_IQ", "CP720", "ar_JO", "CP720",
- "ar_KW", "CP720", "ar_LY", "CP720", "ar_MA", "CP720", "ar_OM", "CP720",
- "ar_QA", "CP720", "ar_SY", "CP720", "ar_TN", "CP720", "ar_AE", "CP720",
- "ar_YE", "CP720","ast_ES", "CP850", "az_AZ", "CP866", "az_AZ", "CP857",
- "be_BY", "CP866", "bg_BG", "CP866", "br_FR", "CP850", "ca_ES", "CP850",
- "zh_CN", "CP936", "zh_TW", "CP950", "kw_GB", "CP850", "cs_CZ", "CP852",
- "cy_GB", "CP850", "da_DK", "CP850", "de_AT", "CP850", "de_LI", "CP850",
- "de_LU", "CP850", "de_CH", "CP850", "de_DE", "CP850", "el_GR", "CP737",
- "en_AU", "CP850", "en_CA", "CP850", "en_GB", "CP850", "en_IE", "CP850",
- "en_JM", "CP850", "en_BZ", "CP850", "en_PH", "CP437", "en_ZA", "CP437",
- "en_TT", "CP850", "en_US", "CP437", "en_ZW", "CP437", "en_NZ", "CP850",
- "es_PA", "CP850", "es_BO", "CP850", "es_CR", "CP850", "es_DO", "CP850",
- "es_SV", "CP850", "es_EC", "CP850", "es_GT", "CP850", "es_HN", "CP850",
- "es_NI", "CP850", "es_CL", "CP850", "es_MX", "CP850", "es_ES", "CP850",
- "es_CO", "CP850", "es_ES", "CP850", "es_PE", "CP850", "es_AR", "CP850",
- "es_PR", "CP850", "es_VE", "CP850", "es_UY", "CP850", "es_PY", "CP850",
- "et_EE", "CP775", "eu_ES", "CP850", "fa_IR", "CP720", "fi_FI", "CP850",
- "fo_FO", "CP850", "fr_FR", "CP850", "fr_BE", "CP850", "fr_CA", "CP850",
- "fr_LU", "CP850", "fr_MC", "CP850", "fr_CH", "CP850", "ga_IE", "CP437",
- "gd_GB", "CP850", "gv_IM", "CP850", "gl_ES", "CP850", "he_IL", "CP862",
- "hr_HR", "CP852", "hu_HU", "CP852", "id_ID", "CP850", "is_IS", "CP850",
- "it_IT", "CP850", "it_CH", "CP850", "iv_IV", "CP437", "ja_JP", "CP932",
- "kk_KZ", "CP866", "ko_KR", "CP949", "ky_KG", "CP866", "lt_LT", "CP775",
- "lv_LV", "CP775", "mk_MK", "CP866", "mn_MN", "CP866", "ms_BN", "CP850",
- "ms_MY", "CP850", "nl_BE", "CP850", "nl_NL", "CP850", "nl_SR", "CP850",
- "nn_NO", "CP850", "nb_NO", "CP850", "pl_PL", "CP852", "pt_BR", "CP850",
- "pt_PT", "CP850", "rm_CH", "CP850", "ro_RO", "CP852", "ru_RU", "CP866",
- "sk_SK", "CP852", "sl_SI", "CP852", "sq_AL", "CP852", "sr_RS", "CP855",
- "sr_RS", "CP852", "sv_SE", "CP850", "sv_FI", "CP850", "sw_KE", "CP437",
- "th_TH", "CP874", "tr_TR", "CP857", "tt_RU", "CP866", "uk_UA", "CP866",
- "ur_PK", "CP720", "uz_UZ", "CP866", "uz_UZ", "CP857", "vi_VN", "CP1258",
- "wa_BE", "CP850", "zh_HK", "CP950", "zh_SG", "CP936"};
- int table_len = sizeof(lc_to_cp_table) / sizeof(char *);
- int lc_len, i;
-
- char *lc = setlocale(LC_CTYPE, "");
-
- if (lc && lc[0]) {
- // Compare up to the dot, if it exists, e.g. en_US.UTF-8
- for (lc_len = 0; lc[lc_len] != '.' && lc[lc_len] != '\0'; ++lc_len)
- ;
- for (i = 0; i < table_len; i += 2)
- if (strncmp(lc, lc_to_cp_table[i], lc_len) == 0)
- oemcp = lc_to_cp_table[i + 1];
- }
- }
-
- iconv_t cd;
- if ((cd = iconv_open("UTF-8", oemcp)) != (iconv_t)-1) {
-
- AString s_utf8;
- const char* src = s.Ptr();
- size_t slen = s.Len();
- size_t dlen = slen * 4;
- const char* dest = s_utf8.GetBuf_SetEnd(dlen + 1); // (source length * 4) + null termination
-
- size_t done = iconv(cd, (char**)&src, &slen, (char**)&dest, &dlen);
- bzero((size_t*)dest + done, 1);
-
- iconv_close(cd);
-
- if (ConvertUTF8ToUnicode(s_utf8, res) || ignore_Utf8_Errors)
- return;
- }
+ if (!isUtf8) {
+ const char *oem_charset = natspec_get_charset_by_locale(NATSPEC_DOSCS, "");
+ char *p = natspec_convert(s.Ptr(), NULL, oem_charset, 0);
+ AString utf = p;
+ free(p);
+ if (ConvertUTF8ToUnicode(utf, res))
+ return;
}
- #endif
-
+
if (isUtf8)
if (ConvertUTF8ToUnicode(s, res) || ignore_Utf8_Errors)
return;
|
GitWeb