aboutsummaryrefslogtreecommitdiffstats
path: root/library/cpp/unicode
diff options
context:
space:
mode:
authorVlad Yaroslavlev <vladon@vladon.com>2022-02-10 16:46:25 +0300
committerDaniil Cherednik <dcherednik@yandex-team.ru>2022-02-10 16:46:25 +0300
commit344ea37b4a345701ab0e67de2266a1c1bd7baf2d (patch)
tree1a2c5ffcf89eb53ecd79dbc9bc0a195c27404d0c /library/cpp/unicode
parent706b83ed7de5a473436620367af31fc0ceecde07 (diff)
downloadydb-344ea37b4a345701ab0e67de2266a1c1bd7baf2d.tar.gz
Restoring authorship annotation for Vlad Yaroslavlev <vladon@vladon.com>. Commit 2 of 2.
Diffstat (limited to 'library/cpp/unicode')
-rw-r--r--library/cpp/unicode/normalization/normalization.h2
-rw-r--r--library/cpp/unicode/normalization/ut/normalization_ut.cpp4
-rw-r--r--library/cpp/unicode/punycode/punycode.cpp14
-rw-r--r--library/cpp/unicode/punycode/punycode.h22
-rw-r--r--library/cpp/unicode/punycode/punycode_ut.cpp30
5 files changed, 36 insertions, 36 deletions
diff --git a/library/cpp/unicode/normalization/normalization.h b/library/cpp/unicode/normalization/normalization.h
index bce2759dc1..4f5f57881c 100644
--- a/library/cpp/unicode/normalization/normalization.h
+++ b/library/cpp/unicode/normalization/normalization.h
@@ -127,7 +127,7 @@ namespace NUnicode {
};
typedef std::pair<wchar32, TCombining> TSymbol;
- typedef TVector<TSymbol> TBuffer;
+ typedef TVector<TSymbol> TBuffer;
template <bool doCompose>
class TCompositor;
diff --git a/library/cpp/unicode/normalization/ut/normalization_ut.cpp b/library/cpp/unicode/normalization/ut/normalization_ut.cpp
index dbccd0810d..54d4940a26 100644
--- a/library/cpp/unicode/normalization/ut/normalization_ut.cpp
+++ b/library/cpp/unicode/normalization/ut/normalization_ut.cpp
@@ -8,8 +8,8 @@ Y_UNIT_TEST_SUITE(TUnicodeNormalizationTest) {
template <NUnicode::ENormalization NormType>
void TestInit() {
NUnicode::TNormalizer<NormType> normalizer;
- TString s("упячка detected");
- TUtf16String w;
+ TString s("упячка detected");
+ TUtf16String w;
UTF8ToWide(s, w);
normalizer.Normalize(w);
}
diff --git a/library/cpp/unicode/punycode/punycode.cpp b/library/cpp/unicode/punycode/punycode.cpp
index 4a8993a95b..800d1f19fe 100644
--- a/library/cpp/unicode/punycode/punycode.cpp
+++ b/library/cpp/unicode/punycode/punycode.cpp
@@ -39,7 +39,7 @@ static inline void AppendUtf32ToWide(const ui32* in, size_t len, TUtf16String& o
}
}
-TStringBuf WideToPunycode(const TWtringBuf& in16, TString& out) {
+TStringBuf WideToPunycode(const TWtringBuf& in16, TString& out) {
TVector<ui32> in32;
AppendWideToUtf32(in16, in32);
size_t outlen = in32.size();
@@ -57,7 +57,7 @@ TStringBuf WideToPunycode(const TWtringBuf& in16, TString& out) {
return out;
}
-TWtringBuf PunycodeToWide(const TStringBuf& in, TUtf16String& out16) {
+TWtringBuf PunycodeToWide(const TStringBuf& in, TUtf16String& out16) {
size_t outlen = in.size();
TVector<ui32> out32(outlen);
@@ -79,7 +79,7 @@ namespace {
};
}
-TString HostNameToPunycode(const TWtringBuf& unicodeHost) {
+TString HostNameToPunycode(const TWtringBuf& unicodeHost) {
TVector<ui32> in32;
AppendWideToUtf32(unicodeHost, in32);
in32.push_back(0);
@@ -91,7 +91,7 @@ TString HostNameToPunycode(const TWtringBuf& unicodeHost) {
return out.Data;
}
-TUtf16String PunycodeToHostName(const TStringBuf& punycodeHost) {
+TUtf16String PunycodeToHostName(const TStringBuf& punycodeHost) {
if (!IsStringASCII(punycodeHost.begin(), punycodeHost.end()))
ythrow TPunycodeError() << "Non-ASCII punycode input";
@@ -105,12 +105,12 @@ TUtf16String PunycodeToHostName(const TStringBuf& punycodeHost) {
int rc = idna_to_unicode_4z4z(in32.begin(), &out.Data, 0);
CheckIdnaResult(rc);
- TUtf16String decoded;
+ TUtf16String decoded;
AppendUtf32ToWide(out.Data, std::char_traits<ui32>::length(out.Data), decoded);
return decoded;
}
-TString ForceHostNameToPunycode(const TWtringBuf& unicodeHost) {
+TString ForceHostNameToPunycode(const TWtringBuf& unicodeHost) {
try {
return HostNameToPunycode(unicodeHost);
} catch (const TPunycodeError&) {
@@ -118,7 +118,7 @@ TString ForceHostNameToPunycode(const TWtringBuf& unicodeHost) {
}
}
-TUtf16String ForcePunycodeToHostName(const TStringBuf& punycodeHost) {
+TUtf16String ForcePunycodeToHostName(const TStringBuf& punycodeHost) {
try {
return PunycodeToHostName(punycodeHost);
} catch (const TPunycodeError&) {
diff --git a/library/cpp/unicode/punycode/punycode.h b/library/cpp/unicode/punycode/punycode.h
index 868e473253..af4acc25c1 100644
--- a/library/cpp/unicode/punycode/punycode.h
+++ b/library/cpp/unicode/punycode/punycode.h
@@ -1,6 +1,6 @@
#pragma once
-#include <util/generic/string.h>
+#include <util/generic/string.h>
#include <util/generic/strbuf.h>
#include <util/generic/yexception.h>
@@ -9,17 +9,17 @@
// Raw strings encoder/decoder: does not prepend with ACE prefix ("xn--"),
// does not limit input length. Throws TPunycodeError on any internal error.
// Returned strbuf points to @out data.
-TStringBuf WideToPunycode(const TWtringBuf& in, TString& out);
-TWtringBuf PunycodeToWide(const TStringBuf& in, TUtf16String& out);
+TStringBuf WideToPunycode(const TWtringBuf& in, TString& out);
+TWtringBuf PunycodeToWide(const TStringBuf& in, TUtf16String& out);
-inline TString WideToPunycode(const TWtringBuf& in) {
- TString out;
+inline TString WideToPunycode(const TWtringBuf& in) {
+ TString out;
WideToPunycode(in, out);
return out;
}
-inline TUtf16String PunycodeToWide(const TStringBuf& in) {
- TUtf16String out;
+inline TUtf16String PunycodeToWide(const TStringBuf& in) {
+ TUtf16String out;
PunycodeToWide(in, out);
return out;
}
@@ -29,12 +29,12 @@ inline TUtf16String PunycodeToWide(const TStringBuf& in) {
// Labels containing non-ASCII characters are prefixed with ACE prefix ("xn--").
// Limits maximal encoded domain label length to IDNA_LABEL_MAX_LENGTH (255 by default).
// Throws TPunycodeError on failure.
-TString HostNameToPunycode(const TWtringBuf& unicodeHost);
-TUtf16String PunycodeToHostName(const TStringBuf& punycodeHost);
+TString HostNameToPunycode(const TWtringBuf& unicodeHost);
+TUtf16String PunycodeToHostName(const TStringBuf& punycodeHost);
// Robust versions: on failure return original input, converted to/from UTF8
-TString ForceHostNameToPunycode(const TWtringBuf& unicodeHost);
-TUtf16String ForcePunycodeToHostName(const TStringBuf& punycodeHost);
+TString ForceHostNameToPunycode(const TWtringBuf& unicodeHost);
+TUtf16String ForcePunycodeToHostName(const TStringBuf& punycodeHost);
// True if @host looks like punycode domain label sequence,
// containing at least one ACE-prefixed label.
diff --git a/library/cpp/unicode/punycode/punycode_ut.cpp b/library/cpp/unicode/punycode/punycode_ut.cpp
index bb192169d7..97271cf0d8 100644
--- a/library/cpp/unicode/punycode/punycode_ut.cpp
+++ b/library/cpp/unicode/punycode/punycode_ut.cpp
@@ -11,10 +11,10 @@ namespace {
}
Y_UNIT_TEST_SUITE(TPunycodeTest) {
- static bool TestRaw(const TString& utf8, const TString& punycode) {
- TUtf16String unicode = UTF8ToWide(utf8);
- TString buf1;
- TUtf16String buf2;
+ static bool TestRaw(const TString& utf8, const TString& punycode) {
+ TUtf16String unicode = UTF8ToWide(utf8);
+ TString buf1;
+ TUtf16String buf2;
return HasSameBuffer(WideToPunycode(unicode, buf1), buf1) && buf1 == punycode && HasSameBuffer(PunycodeToWide(punycode, buf2), buf2) && buf2 == unicode && WideToPunycode(unicode) == punycode && PunycodeToWide(punycode) == unicode;
}
@@ -48,25 +48,25 @@ Y_UNIT_TEST_SUITE(TPunycodeTest) {
UNIT_ASSERT_EXCEPTION(PunycodeToWide("-"), TPunycodeError);
{
- TString longIn;
+ TString longIn;
for (size_t i = 0; i < 1024; ++i)
longIn += "Qй";
- TString longOut = "QQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQ-lo11fbabbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbb";
+ TString longOut = "QQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQQ-lo11fbabbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbb";
UNIT_ASSERT(TestRaw(longIn, longOut));
}
}
- static bool TestHostName(const TString& utf8, const TString& punycode, bool canBePunycode = false) {
- TUtf16String unicode = UTF8ToWide(utf8);
- TString buf1;
- TUtf16String buf2;
+ static bool TestHostName(const TString& utf8, const TString& punycode, bool canBePunycode = false) {
+ TUtf16String unicode = UTF8ToWide(utf8);
+ TString buf1;
+ TUtf16String buf2;
//Cerr << "Testing " << utf8 << Endl;
return HostNameToPunycode(unicode) == punycode && HostNameToPunycode(UTF8ToWide(punycode)) == punycode // repeated encoding should give same result
&& PunycodeToHostName(punycode) == unicode && CanBePunycodeHostName(punycode) == canBePunycode;
}
- static bool TestForced(const TString& bad) {
+ static bool TestForced(const TString& bad) {
return ForceHostNameToPunycode(UTF8ToWide(bad)) == bad && ForcePunycodeToHostName(bad) == UTF8ToWide(bad);
}
@@ -89,25 +89,25 @@ Y_UNIT_TEST_SUITE(TPunycodeTest) {
{
// non-ascii
- TString bad = "президент.рф";
+ TString bad = "президент.рф";
UNIT_ASSERT_EXCEPTION(PunycodeToHostName("президент.рф"), TPunycodeError);
UNIT_ASSERT(ForcePunycodeToHostName(bad) == UTF8ToWide(bad));
}
{
// too long domain label
- TString bad(500, 'a');
+ TString bad(500, 'a');
UNIT_ASSERT_EXCEPTION(HostNameToPunycode(UTF8ToWide(bad)), TPunycodeError);
UNIT_ASSERT(TestForced(bad)); // but can decode it
}
{
// already has ACE prefix
- TString bad("xn--яндекс.xn--рф");
+ TString bad("xn--яндекс.xn--рф");
UNIT_ASSERT_EXCEPTION(HostNameToPunycode(UTF8ToWide(bad)), TPunycodeError);
UNIT_ASSERT(TestForced(bad));
}
{
// empty non-root domain is not allowed (?)
- TString bad(".яндекс.рф");
+ TString bad(".яндекс.рф");
UNIT_ASSERT_EXCEPTION(HostNameToPunycode(UTF8ToWide(bad)), TPunycodeError);
UNIT_ASSERT(TestForced(bad));
}