Bug#977790: (no subject)
Please update far2l debian package https://mentors.debian.net/package/far2l/ as recent far2l has license-problem-convert-utf-code problem fixed (ConvertUTF is removed). Thanks!
Bug#965126: this patch in upstream repo
this patch in upstream repo: https://sourceforge.net/p/p7zip/bugs/187/#816e
Bug#965126: p7zip processes OEM file names in .zip archives incorrectly
Package: p7zip
Version: 16.02+dfsg-7
When I try to unzip archive made on Windows containing non-latin file names
using p7zip, I get wrong file names.
This little patch is fixing an issue by selecting OEM code page based on
current locale for archives made on Windows.
That is exactly that Windows internal zip archiver does.
Automated selection can be overriden by OEMCP environment variable.
Locale-to-oem-cp translation table taken from Wine.
@@ -1,5 +1,10 @@
// Archive/ZipItem.cpp
+#ifndef _WIN32
+#include
+#include
+#endif
+
#include "StdAfx.h"
#include "../../../../C/CpuArch.h"
@@ -244,6 +249,86 @@
#endif
}
+ #ifndef _WIN32
+ // 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**), , (char**), );
+ bzero((size_t*)dest + done, 1);
+
+ iconv_close(cd);
+
+ if (ConvertUTF8ToUnicode(s_utf8, res) || ignore_Utf8_Errors)
+return;
+}
+ }
+ #endif
if (isUtf8)
if (ConvertUTF8ToUnicode(s, res) || ignore_Utf8_Errors)
Bug#696914: possible fix
See this patch for possible solution: https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=197427#70
Bug#197427: patch proposal
With this patch unzip will select OEM CP for zip files created on
Windows based on system locale (just as Windows itself does). Used
locale to OEM CP matching from Wine. OEM CP selection can be overrided
by OEMCP environment variable.
Patch proposal in original infozip repo:
https://sourceforge.net/p/infozip/patches/29/
@@ -1958,13 +1958,16 @@
#ifdef USE_ICONV_MAPPING
+/*
typedef struct {
char *local_charset;
char *archive_charset;
} CHARSET_MAP;
+*/
/* A mapping of local <-> archive charsets used by default to convert filenames
* of DOS/Windows Zip archives. Currently very basic. */
+/*
static CHARSET_MAP dos_charset_map[] = {
{ "ANSI_X3.4-1968", "CP850" },
{ "ISO-8859-1", "CP850" },
@@ -1974,18 +1977,79 @@
{ "KOI8-U", "CP866" },
{ "ISO-8859-5", "CP866" }
};
+*/
char OEM_CP[MAX_CP_NAME] = "";
char ISO_CP[MAX_CP_NAME] = "";
+char *lc_to_oem_cp(char *lc) {
+static 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;
+
+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)
+return lc_to_cp_table[i + 1];
+}
+
+return "CP437";
+}
+
/* Try to guess the default value of OEM_CP based on the current locale.
* ISO_CP is left alone for now. */
void init_conversion_charsets()
{
+char *oemcp;
+oemcp = getenv("OEMCP");
+if (!oemcp) {
+oemcp = lc_to_oem_cp(setlocale(LC_CTYPE, ""));
+}
+strncpy(OEM_CP, oemcp, strlen(oemcp));
+
+/*
const char *local_charset;
int i;
+*/
/* Make a guess only if OEM_CP not already set. */
+/*
if(*OEM_CP == '\0') {
local_charset = nl_langinfo(CODESET);
for(i = 0; i < sizeof(dos_charset_map)/sizeof(CHARSET_MAP); i++)
@@ -1995,6 +2059,7 @@
break;
}
}
+*/
}
/* Convert a string from one encoding to the current locale using iconv().
