aboutsummaryrefslogtreecommitdiffstats
path: root/library/cpp/charset/wide_ut.cpp
diff options
context:
space:
mode:
authoraosipenko <aosipenko@yandex-team.ru>2022-02-10 16:48:08 +0300
committerDaniil Cherednik <dcherednik@yandex-team.ru>2022-02-10 16:48:08 +0300
commit948fd24d47d4b3b7815aaef1686aea00ef3f4288 (patch)
tree8ad4c39c2a5f8b341bc02e3b0c5e8f26c40373cb /library/cpp/charset/wide_ut.cpp
parentd2eb4aae699fa2f6901bf32d22eec019c8f29838 (diff)
downloadydb-948fd24d47d4b3b7815aaef1686aea00ef3f4288.tar.gz
Restoring authorship annotation for <aosipenko@yandex-team.ru>. Commit 1 of 2.
Diffstat (limited to 'library/cpp/charset/wide_ut.cpp')
-rw-r--r--library/cpp/charset/wide_ut.cpp82
1 files changed, 41 insertions, 41 deletions
diff --git a/library/cpp/charset/wide_ut.cpp b/library/cpp/charset/wide_ut.cpp
index 78947d51ba..218a329041 100644
--- a/library/cpp/charset/wide_ut.cpp
+++ b/library/cpp/charset/wide_ut.cpp
@@ -1,6 +1,6 @@
#include "wide.h"
#include "codepage.h"
-#include "recyr.hh"
+#include "recyr.hh"
#include <library/cpp/testing/unittest/registar.h>
@@ -12,25 +12,25 @@
namespace {
//! three UTF8 encoded russian letters (A, B, V)
- const char yandexCyrillicAlphabet[] =
- "\xC0\xC1\xC2\xC3\xC4\xC5\xC6\xC7\xC8\xC9\xCA\xCB\xCC\xCD\xCE\xCF" // A - P
- "\xD0\xD1\xD2\xD3\xD4\xD5\xD6\xD7\xD8\xD9\xDA\xDB\xDC\xDD\xDE\xDF" // R - YA
- "\xE0\xE1\xE2\xE3\xE4\xE5\xE6\xE7\xE8\xE9\xEA\xEB\xEC\xED\xEE\xEF" // a - p
- "\xF0\xF1\xF2\xF3\xF4\xF5\xF6\xF7\xF8\xF9\xFA\xFB\xFC\xFD\xFE\xFF"; // r - ya
+ const char yandexCyrillicAlphabet[] =
+ "\xC0\xC1\xC2\xC3\xC4\xC5\xC6\xC7\xC8\xC9\xCA\xCB\xCC\xCD\xCE\xCF" // A - P
+ "\xD0\xD1\xD2\xD3\xD4\xD5\xD6\xD7\xD8\xD9\xDA\xDB\xDC\xDD\xDE\xDF" // R - YA
+ "\xE0\xE1\xE2\xE3\xE4\xE5\xE6\xE7\xE8\xE9\xEA\xEB\xEC\xED\xEE\xEF" // a - p
+ "\xF0\xF1\xF2\xF3\xF4\xF5\xF6\xF7\xF8\xF9\xFA\xFB\xFC\xFD\xFE\xFF"; // r - ya
const wchar16 wideCyrillicAlphabet[] = {
0x0410, 0x0411, 0x0412, 0x0413, 0x0414, 0x0415, 0x0416, 0x0417, 0x0418, 0x0419, 0x041A, 0x041B, 0x041C, 0x041D, 0x041E, 0x041F,
0x0420, 0x0421, 0x0422, 0x0423, 0x0424, 0x0425, 0x0426, 0x0427, 0x0428, 0x0429, 0x042A, 0x042B, 0x042C, 0x042D, 0x042E, 0x042F,
0x0430, 0x0431, 0x0432, 0x0433, 0x0434, 0x0435, 0x0436, 0x0437, 0x0438, 0x0439, 0x043A, 0x043B, 0x043C, 0x043D, 0x043E, 0x043F,
0x0440, 0x0441, 0x0442, 0x0443, 0x0444, 0x0445, 0x0446, 0x0447, 0x0448, 0x0449, 0x044A, 0x044B, 0x044C, 0x044D, 0x044E, 0x044F, 0x00};
- const char utf8CyrillicAlphabet[] =
- "\xd0\x90\xd0\x91\xd0\x92\xd0\x93\xd0\x94\xd0\x95\xd0\x96\xd0\x97"
- "\xd0\x98\xd0\x99\xd0\x9a\xd0\x9b\xd0\x9c\xd0\x9d\xd0\x9e\xd0\x9f"
- "\xd0\xa0\xd0\xa1\xd0\xa2\xd0\xa3\xd0\xa4\xd0\xa5\xd0\xa6\xd0\xa7"
- "\xd0\xa8\xd0\xa9\xd0\xaa\xd0\xab\xd0\xac\xd0\xad\xd0\xae\xd0\xaf"
- "\xd0\xb0\xd0\xb1\xd0\xb2\xd0\xb3\xd0\xb4\xd0\xb5\xd0\xb6\xd0\xb7"
- "\xd0\xb8\xd0\xb9\xd0\xba\xd0\xbb\xd0\xbc\xd0\xbd\xd0\xbe\xd0\xbf"
- "\xd1\x80\xd1\x81\xd1\x82\xd1\x83\xd1\x84\xd1\x85\xd1\x86\xd1\x87"
- "\xd1\x88\xd1\x89\xd1\x8a\xd1\x8b\xd1\x8c\xd1\x8d\xd1\x8e\xd1\x8f";
+ const char utf8CyrillicAlphabet[] =
+ "\xd0\x90\xd0\x91\xd0\x92\xd0\x93\xd0\x94\xd0\x95\xd0\x96\xd0\x97"
+ "\xd0\x98\xd0\x99\xd0\x9a\xd0\x9b\xd0\x9c\xd0\x9d\xd0\x9e\xd0\x9f"
+ "\xd0\xa0\xd0\xa1\xd0\xa2\xd0\xa3\xd0\xa4\xd0\xa5\xd0\xa6\xd0\xa7"
+ "\xd0\xa8\xd0\xa9\xd0\xaa\xd0\xab\xd0\xac\xd0\xad\xd0\xae\xd0\xaf"
+ "\xd0\xb0\xd0\xb1\xd0\xb2\xd0\xb3\xd0\xb4\xd0\xb5\xd0\xb6\xd0\xb7"
+ "\xd0\xb8\xd0\xb9\xd0\xba\xd0\xbb\xd0\xbc\xd0\xbd\xd0\xbe\xd0\xbf"
+ "\xd1\x80\xd1\x81\xd1\x82\xd1\x83\xd1\x84\xd1\x85\xd1\x86\xd1\x87"
+ "\xd1\x88\xd1\x89\xd1\x8a\xd1\x8b\xd1\x8c\xd1\x8d\xd1\x8e\xd1\x8f";
TString CreateYandexText() {
const int len = 256;
@@ -69,31 +69,31 @@ namespace {
}
TString CreateUTF8Text() {
- char text[] = {
- '\x00', '\x01', '\x02', '\x03', '\x04', '\x05', '\x06', '\x07', '\x08', '\x09', '\x0a', '\x0b', '\x0c', '\x0d', '\x0e', '\x0f',
- '\x10', '\x11', '\x12', '\x13', '\x14', '\x15', '\x16', '\x17', '\x18', '\x19', '\x1a', '\x1b', '\x1c', '\x1d', '\x1e', '\x1f',
- '\x20', '\x21', '\x22', '\x23', '\x24', '\x25', '\x26', '\x27', '\x28', '\x29', '\x2a', '\x2b', '\x2c', '\x2d', '\x2e', '\x2f',
- '\x30', '\x31', '\x32', '\x33', '\x34', '\x35', '\x36', '\x37', '\x38', '\x39', '\x3a', '\x3b', '\x3c', '\x3d', '\x3e', '\x3f',
- '\x40', '\x41', '\x42', '\x43', '\x44', '\x45', '\x46', '\x47', '\x48', '\x49', '\x4a', '\x4b', '\x4c', '\x4d', '\x4e', '\x4f',
- '\x50', '\x51', '\x52', '\x53', '\x54', '\x55', '\x56', '\x57', '\x58', '\x59', '\x5a', '\x5b', '\x5c', '\x5d', '\x5e', '\x5f',
- '\x60', '\x61', '\x62', '\x63', '\x64', '\x65', '\x66', '\x67', '\x68', '\x69', '\x6a', '\x6b', '\x6c', '\x6d', '\x6e', '\x6f',
- '\x70', '\x71', '\x72', '\x73', '\x74', '\x75', '\x76', '\x77', '\x78', '\x79', '\x7a', '\x7b', '\x7c', '\x7d', '\x7e', '\x7f',
- '\xcc', '\x81', '\xc3', '\x84', '\xc3', '\x96', '\xc3', '\x9c', '\xc4', '\x84', '\xc4', '\x86', '\xc4', '\x98', '\xc5', '\x81',
- '\xc3', '\xa0', '\xc3', '\xa2', '\xc3', '\xa7', '\xc3', '\xa8', '\xc3', '\xa9', '\xc3', '\xaa', '\xd2', '\x90', '\xc2', '\xad',
- '\xc3', '\x9f', '\xc3', '\xa4', '\xc3', '\xb6', '\xc3', '\xbc', '\xc4', '\x85', '\xc4', '\x87', '\xc4', '\x99', '\xc5', '\x82',
- '\xc3', '\xab', '\xc3', '\xae', '\xc3', '\xaf', '\xc3', '\xb4', '\xc3', '\xb9', '\xc3', '\xbb', '\xd2', '\x91', '\xe9', '\x8b',
- '\x8f', '\xc2', '\xa0', '\xc5', '\x83', '\xc3', '\x93', '\xc5', '\x9a', '\xc5', '\xbb', '\xc5', '\xb9', '\xd1', '\xac', '\xc2',
- '\xa7', '\xd0', '\x81', '\xd1', '\xa2', '\xd1', '\xb2', '\xd1', '\xb4', '\xd0', '\x8e', '\xd0', '\x86', '\xd0', '\x84', '\xd0',
- '\x87', '\xc2', '\xb0', '\xc5', '\x84', '\xc3', '\xb3', '\xc5', '\x9b', '\xc5', '\xbc', '\xc5', '\xba', '\xd1', '\xad', '\xe2',
- '\x84', '\x96', '\xd1', '\x91', '\xd1', '\xa3', '\xd1', '\xb3', '\xd1', '\xb5', '\xd1', '\x9e', '\xd1', '\x96', '\xd1', '\x94',
- '\xd1', '\x97', '\xd0', '\x90', '\xd0', '\x91', '\xd0', '\x92', '\xd0', '\x93', '\xd0', '\x94', '\xd0', '\x95', '\xd0', '\x96',
- '\xd0', '\x97', '\xd0', '\x98', '\xd0', '\x99', '\xd0', '\x9a', '\xd0', '\x9b', '\xd0', '\x9c', '\xd0', '\x9d', '\xd0', '\x9e',
- '\xd0', '\x9f', '\xd0', '\xa0', '\xd0', '\xa1', '\xd0', '\xa2', '\xd0', '\xa3', '\xd0', '\xa4', '\xd0', '\xa5', '\xd0', '\xa6',
- '\xd0', '\xa7', '\xd0', '\xa8', '\xd0', '\xa9', '\xd0', '\xaa', '\xd0', '\xab', '\xd0', '\xac', '\xd0', '\xad', '\xd0', '\xae',
- '\xd0', '\xaf', '\xd0', '\xb0', '\xd0', '\xb1', '\xd0', '\xb2', '\xd0', '\xb3', '\xd0', '\xb4', '\xd0', '\xb5', '\xd0', '\xb6',
- '\xd0', '\xb7', '\xd0', '\xb8', '\xd0', '\xb9', '\xd0', '\xba', '\xd0', '\xbb', '\xd0', '\xbc', '\xd0', '\xbd', '\xd0', '\xbe',
- '\xd0', '\xbf', '\xd1', '\x80', '\xd1', '\x81', '\xd1', '\x82', '\xd1', '\x83', '\xd1', '\x84', '\xd1', '\x85', '\xd1', '\x86',
- '\xd1', '\x87', '\xd1', '\x88', '\xd1', '\x89', '\xd1', '\x8a', '\xd1', '\x8b', '\xd1', '\x8c', '\xd1', '\x8d', '\xd1', '\x8e',
+ char text[] = {
+ '\x00', '\x01', '\x02', '\x03', '\x04', '\x05', '\x06', '\x07', '\x08', '\x09', '\x0a', '\x0b', '\x0c', '\x0d', '\x0e', '\x0f',
+ '\x10', '\x11', '\x12', '\x13', '\x14', '\x15', '\x16', '\x17', '\x18', '\x19', '\x1a', '\x1b', '\x1c', '\x1d', '\x1e', '\x1f',
+ '\x20', '\x21', '\x22', '\x23', '\x24', '\x25', '\x26', '\x27', '\x28', '\x29', '\x2a', '\x2b', '\x2c', '\x2d', '\x2e', '\x2f',
+ '\x30', '\x31', '\x32', '\x33', '\x34', '\x35', '\x36', '\x37', '\x38', '\x39', '\x3a', '\x3b', '\x3c', '\x3d', '\x3e', '\x3f',
+ '\x40', '\x41', '\x42', '\x43', '\x44', '\x45', '\x46', '\x47', '\x48', '\x49', '\x4a', '\x4b', '\x4c', '\x4d', '\x4e', '\x4f',
+ '\x50', '\x51', '\x52', '\x53', '\x54', '\x55', '\x56', '\x57', '\x58', '\x59', '\x5a', '\x5b', '\x5c', '\x5d', '\x5e', '\x5f',
+ '\x60', '\x61', '\x62', '\x63', '\x64', '\x65', '\x66', '\x67', '\x68', '\x69', '\x6a', '\x6b', '\x6c', '\x6d', '\x6e', '\x6f',
+ '\x70', '\x71', '\x72', '\x73', '\x74', '\x75', '\x76', '\x77', '\x78', '\x79', '\x7a', '\x7b', '\x7c', '\x7d', '\x7e', '\x7f',
+ '\xcc', '\x81', '\xc3', '\x84', '\xc3', '\x96', '\xc3', '\x9c', '\xc4', '\x84', '\xc4', '\x86', '\xc4', '\x98', '\xc5', '\x81',
+ '\xc3', '\xa0', '\xc3', '\xa2', '\xc3', '\xa7', '\xc3', '\xa8', '\xc3', '\xa9', '\xc3', '\xaa', '\xd2', '\x90', '\xc2', '\xad',
+ '\xc3', '\x9f', '\xc3', '\xa4', '\xc3', '\xb6', '\xc3', '\xbc', '\xc4', '\x85', '\xc4', '\x87', '\xc4', '\x99', '\xc5', '\x82',
+ '\xc3', '\xab', '\xc3', '\xae', '\xc3', '\xaf', '\xc3', '\xb4', '\xc3', '\xb9', '\xc3', '\xbb', '\xd2', '\x91', '\xe9', '\x8b',
+ '\x8f', '\xc2', '\xa0', '\xc5', '\x83', '\xc3', '\x93', '\xc5', '\x9a', '\xc5', '\xbb', '\xc5', '\xb9', '\xd1', '\xac', '\xc2',
+ '\xa7', '\xd0', '\x81', '\xd1', '\xa2', '\xd1', '\xb2', '\xd1', '\xb4', '\xd0', '\x8e', '\xd0', '\x86', '\xd0', '\x84', '\xd0',
+ '\x87', '\xc2', '\xb0', '\xc5', '\x84', '\xc3', '\xb3', '\xc5', '\x9b', '\xc5', '\xbc', '\xc5', '\xba', '\xd1', '\xad', '\xe2',
+ '\x84', '\x96', '\xd1', '\x91', '\xd1', '\xa3', '\xd1', '\xb3', '\xd1', '\xb5', '\xd1', '\x9e', '\xd1', '\x96', '\xd1', '\x94',
+ '\xd1', '\x97', '\xd0', '\x90', '\xd0', '\x91', '\xd0', '\x92', '\xd0', '\x93', '\xd0', '\x94', '\xd0', '\x95', '\xd0', '\x96',
+ '\xd0', '\x97', '\xd0', '\x98', '\xd0', '\x99', '\xd0', '\x9a', '\xd0', '\x9b', '\xd0', '\x9c', '\xd0', '\x9d', '\xd0', '\x9e',
+ '\xd0', '\x9f', '\xd0', '\xa0', '\xd0', '\xa1', '\xd0', '\xa2', '\xd0', '\xa3', '\xd0', '\xa4', '\xd0', '\xa5', '\xd0', '\xa6',
+ '\xd0', '\xa7', '\xd0', '\xa8', '\xd0', '\xa9', '\xd0', '\xaa', '\xd0', '\xab', '\xd0', '\xac', '\xd0', '\xad', '\xd0', '\xae',
+ '\xd0', '\xaf', '\xd0', '\xb0', '\xd0', '\xb1', '\xd0', '\xb2', '\xd0', '\xb3', '\xd0', '\xb4', '\xd0', '\xb5', '\xd0', '\xb6',
+ '\xd0', '\xb7', '\xd0', '\xb8', '\xd0', '\xb9', '\xd0', '\xba', '\xd0', '\xbb', '\xd0', '\xbc', '\xd0', '\xbd', '\xd0', '\xbe',
+ '\xd0', '\xbf', '\xd1', '\x80', '\xd1', '\x81', '\xd1', '\x82', '\xd1', '\x83', '\xd1', '\x84', '\xd1', '\x85', '\xd1', '\x86',
+ '\xd1', '\x87', '\xd1', '\x88', '\xd1', '\x89', '\xd1', '\x8a', '\xd1', '\x8b', '\xd1', '\x8c', '\xd1', '\x8d', '\xd1', '\x8e',
'\xd1', '\x8f'};
return TString(text, Y_ARRAY_SIZE(text));
}
@@ -206,7 +206,7 @@ static void TestSurrogates(const char* str, const wchar16* wide, size_t wideSize
void TConversionTest::TestYandexEncoding() {
TUtf16String w = UTF8ToWide(utf8CyrillicAlphabet, strlen(utf8CyrillicAlphabet), csYandex);
UNIT_ASSERT(w == wideCyrillicAlphabet);
- w = UTF8ToWide(yandexCyrillicAlphabet, strlen(yandexCyrillicAlphabet), csYandex);
+ w = UTF8ToWide(yandexCyrillicAlphabet, strlen(yandexCyrillicAlphabet), csYandex);
UNIT_ASSERT(w == wideCyrillicAlphabet);
const char* utf8NonBMP2 = "ab\xf4\x80\x89\x87n";