Welcome to mirror list, hosted at ThFree Co, Russian Federation.

github.com/mapsme/omim.git - Unnamed repository; edit this file 'description' to name the repository.
summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorAlex Zolotarev <alex@mapswithme.com>2013-05-29 17:32:16 +0400
committerAlex Zolotarev <alex@maps.me>2015-09-23 01:55:31 +0300
commit9add6f84771e02bd8e60a1e7f86220ed2ced1a2c (patch)
tree27b7e2c23817c030829f974962e82a38046887d0 /3party/utfcpp
parentf8acbd06c50d24326b9515290cff6d15533759e7 (diff)
[3party] Updated utfcpp to 2.3.4
Diffstat (limited to '3party/utfcpp')
-rw-r--r--[-rwxr-xr-x]3party/utfcpp/doc/ReleaseNotes14
-rw-r--r--[-rwxr-xr-x]3party/utfcpp/doc/utf8cpp.html30
-rw-r--r--3party/utfcpp/source/utf8/checked.h118
-rw-r--r--[-rwxr-xr-x]3party/utfcpp/source/utf8/core.h209
-rw-r--r--[-rwxr-xr-x]3party/utfcpp/source/utf8/unchecked.h46
5 files changed, 191 insertions, 226 deletions
diff --git a/3party/utfcpp/doc/ReleaseNotes b/3party/utfcpp/doc/ReleaseNotes
index c0c01a3c61..364411a23d 100755..100644
--- a/3party/utfcpp/doc/ReleaseNotes
+++ b/3party/utfcpp/doc/ReleaseNotes
@@ -1,12 +1,12 @@
utf8 cpp library
-Release 2.3.1
+Release 2.3.4
-A bug fix release. Special thanks to dalle and Ivan Sorokin who reported the bugs.
+A minor bug fix release. Thanks to all who reported bugs.
-Changes from version 2.3
-- Bug fix [3025042]: is_bom documentation issue.
-- Bug fix [3083640]: is_code_point_valid incorrectly returns false.
-- Bug fix [3167987]: prior moves it before start.
-- Bug fix [3185087]: utf8::prior and utf8::previous documentation issue.
+Note: Version 2.3.3 contained a regression, and therefore was removed.
+
+Changes from version 2.3.2
+- Bug fix [39]: checked.h Line 273 and unchecked.h Line 182 have an extra ';'
+- Bug fix [36]: replace_invalid() only works with back_inserter
Files included in the release: utf8.h, core.h, checked.h, unchecked.h, utf8cpp.html, ReleaseNotes
diff --git a/3party/utfcpp/doc/utf8cpp.html b/3party/utfcpp/doc/utf8cpp.html
index c0a89a27de..6f2aacbe7b 100755..100644
--- a/3party/utfcpp/doc/utf8cpp.html
+++ b/3party/utfcpp/doc/utf8cpp.html
@@ -89,9 +89,6 @@
<a href="#points">Points of Interest</a>
</li>
<li>
- <a href="#conclusion">Conclusion</a>
- </li>
- <li>
<a href="#links">Links</a>
</li>
</ul>
@@ -101,10 +98,12 @@
</h2>
<p>
Many C++ developers miss an easy and portable way of handling Unicode encoded
- strings. The original C++ Standard (known as C++98 or C++03) is Unicode agnostic,
- and while some work is being done to introduce Unicode to the next incarnation
- called C++0x, for the moment nothing of the sort is available. In the meantime,
- developers use third party libraries like ICU, OS specific capabilities, or simply
+ strings. The original C++ Standard (known as C++98 or C++03) is Unicode agnostic.
+ C++11 provides some support for Unicode on core language and library level:
+ u8, u, and U character and string literals, char16_t and char32_t character types,
+ u16string and u32string library classes, and codecvt support for conversions
+ between Unicode encoding forms.
+ In the meantime, developers use third party libraries like ICU, OS specific capabilities, or simply
roll out their own solutions.
</p>
<p>
@@ -1730,7 +1729,7 @@ assert (*un_it == <span class="literal">0x10346</span>);
for Windows (both 32 and 64 bit), and most 32 bit and 64 bit Unix derivatives.
</li>
<li>
- Lightweight: follow the "pay only for what you use" guidline.
+ Lightweight: follow the "pay only for what you use" guideline.
</li>
<li>
Unintrusive: avoid forcing any particular design or even programming style on the
@@ -1752,6 +1751,10 @@ assert (*un_it == <span class="literal">0x10346</span>);
recommend looking at ICU even if you don't plan to use it.
</li>
<li>
+ C++11 language and library features. Still far from complete, and not widely
+ supported by compiler vendors.
+ </li>
+ <li>
<a href=
"http://www.gtkmm.org/gtkmm2/docs/tutorial/html/ch03s04.html">Glib::ustring</a>.
A class specifically made to work with UTF-8 strings, and also feel like
@@ -1761,18 +1764,9 @@ assert (*un_it == <span class="literal">0x10346</span>);
<li>
Platform dependent solutions: Windows and POSIX have functions to convert strings
from one encoding to another. That is only a subset of what my library offers,
- but if that is all you need it may be good enough, especially given the fact that
- these functions are mature and tested in production.
+ but if that is all you need it may be good enough.
</li>
</ol>
- <h2 id="conclusion">
- Conclusion
- </h2>
- <p>
- Until Unicode becomes officially recognized by the C++ Standard Library, we need to
- use other means to work with UTF-8 strings. Template functions I describe in this
- article may be a good step in this direction.
- </p>
<h2 id="links">
Links
</h2>
diff --git a/3party/utfcpp/source/utf8/checked.h b/3party/utfcpp/source/utf8/checked.h
index 9cb8d2c7f2..1331155138 100644
--- a/3party/utfcpp/source/utf8/checked.h
+++ b/3party/utfcpp/source/utf8/checked.h
@@ -34,7 +34,7 @@ DEALINGS IN THE SOFTWARE.
namespace utf8
{
// Base for the exceptions that may be thrown from the library
- class exception : public std::exception {
+ class exception : public ::std::exception {
};
// Exceptions that may be thrown from the library functions.
@@ -69,12 +69,38 @@ namespace utf8
/// The library API - functions intended to be called by the users
+ template <typename octet_iterator>
+ octet_iterator append(uint32_t cp, octet_iterator result)
+ {
+ if (!utf8::internal::is_code_point_valid(cp))
+ throw invalid_code_point(cp);
+
+ if (cp < 0x80) // one octet
+ *(result++) = static_cast<uint8_t>(cp);
+ else if (cp < 0x800) { // two octets
+ *(result++) = static_cast<uint8_t>((cp >> 6) | 0xc0);
+ *(result++) = static_cast<uint8_t>((cp & 0x3f) | 0x80);
+ }
+ else if (cp < 0x10000) { // three octets
+ *(result++) = static_cast<uint8_t>((cp >> 12) | 0xe0);
+ *(result++) = static_cast<uint8_t>(((cp >> 6) & 0x3f) | 0x80);
+ *(result++) = static_cast<uint8_t>((cp & 0x3f) | 0x80);
+ }
+ else { // four octets
+ *(result++) = static_cast<uint8_t>((cp >> 18) | 0xf0);
+ *(result++) = static_cast<uint8_t>(((cp >> 12) & 0x3f) | 0x80);
+ *(result++) = static_cast<uint8_t>(((cp >> 6) & 0x3f) | 0x80);
+ *(result++) = static_cast<uint8_t>((cp & 0x3f) | 0x80);
+ }
+ return result;
+ }
+
template <typename octet_iterator, typename output_iterator>
output_iterator replace_invalid(octet_iterator start, octet_iterator end, output_iterator out, uint32_t replacement)
{
while (start != end) {
octet_iterator sequence_start = start;
- internal::utf_error err_code = internal::validate_next(start, end);
+ internal::utf_error err_code = utf8::internal::validate_next(start, end);
switch (err_code) {
case internal::UTF8_OK :
for (octet_iterator it = sequence_start; it != start; ++it)
@@ -83,16 +109,16 @@ namespace utf8
case internal::NOT_ENOUGH_ROOM:
throw not_enough_room();
case internal::INVALID_LEAD:
- append (replacement, out);
+ out = utf8::append (replacement, out);
++start;
break;
case internal::INCOMPLETE_SEQUENCE:
case internal::OVERLONG_SEQUENCE:
case internal::INVALID_CODE_POINT:
- append (replacement, out);
+ out = utf8::append (replacement, out);
++start;
// just one replacement mark for the sequence
- while (internal::is_trail(*start) && start != end)
+ while (start != end && utf8::internal::is_trail(*start))
++start;
break;
}
@@ -103,41 +129,15 @@ namespace utf8
template <typename octet_iterator, typename output_iterator>
inline output_iterator replace_invalid(octet_iterator start, octet_iterator end, output_iterator out)
{
- static const uint32_t replacement_marker = internal::mask16(0xfffd);
- return replace_invalid(start, end, out, replacement_marker);
- }
-
- template <typename octet_iterator>
- octet_iterator append(uint32_t cp, octet_iterator result)
- {
- if (!internal::is_code_point_valid(cp))
- throw invalid_code_point(cp);
-
- if (cp < 0x80) // one octet
- *(result++) = static_cast<uint8_t>(cp);
- else if (cp < 0x800) { // two octets
- *(result++) = static_cast<uint8_t>((cp >> 6) | 0xc0);
- *(result++) = static_cast<uint8_t>((cp & 0x3f) | 0x80);
- }
- else if (cp < 0x10000) { // three octets
- *(result++) = static_cast<uint8_t>((cp >> 12) | 0xe0);
- *(result++) = static_cast<uint8_t>(((cp >> 6) & 0x3f) | 0x80);
- *(result++) = static_cast<uint8_t>((cp & 0x3f) | 0x80);
- }
- else { // four octets
- *(result++) = static_cast<uint8_t>((cp >> 18) | 0xf0);
- *(result++) = static_cast<uint8_t>(((cp >> 12) & 0x3f) | 0x80);
- *(result++) = static_cast<uint8_t>(((cp >> 6) & 0x3f) | 0x80);
- *(result++) = static_cast<uint8_t>((cp & 0x3f) | 0x80);
- }
- return result;
+ static const uint32_t replacement_marker = utf8::internal::mask16(0xfffd);
+ return utf8::replace_invalid(start, end, out, replacement_marker);
}
template <typename octet_iterator>
uint32_t next(octet_iterator& it, octet_iterator end)
{
uint32_t cp = 0;
- internal::utf_error err_code = internal::validate_next(it, end, &cp);
+ internal::utf_error err_code = utf8::internal::validate_next(it, end, cp);
switch (err_code) {
case internal::UTF8_OK :
break;
@@ -156,22 +156,22 @@ namespace utf8
template <typename octet_iterator>
uint32_t peek_next(octet_iterator it, octet_iterator end)
{
- return next(it, end);
+ return utf8::next(it, end);
}
template <typename octet_iterator>
uint32_t prior(octet_iterator& it, octet_iterator start)
- {
+ {
// can't do much if it == start
- if (it == start)
+ if (it == start)
throw not_enough_room();
- octet_iterator end = it;
+ octet_iterator end = it;
// Go back until we hit either a lead octet or start
- while (internal::is_trail(*(--it)))
+ while (utf8::internal::is_trail(*(--it)))
if (it == start)
throw invalid_utf8(*it); // error - no lead byte in the sequence
- return peek_next(it, end);
+ return utf8::peek_next(it, end);
}
/// Deprecated in versions that include "prior"
@@ -179,18 +179,18 @@ namespace utf8
uint32_t previous(octet_iterator& it, octet_iterator pass_start)
{
octet_iterator end = it;
- while (internal::is_trail(*(--it)))
+ while (utf8::internal::is_trail(*(--it)))
if (it == pass_start)
throw invalid_utf8(*it); // error - no lead byte in the sequence
octet_iterator temp = it;
- return next(temp, end);
+ return utf8::next(temp, end);
}
template <typename octet_iterator, typename distance_type>
void advance (octet_iterator& it, distance_type n, octet_iterator end)
{
for (distance_type i = 0; i < n; ++i)
- next(it, end);
+ utf8::next(it, end);
}
template <typename octet_iterator>
@@ -199,7 +199,7 @@ namespace utf8
{
typename std::iterator_traits<octet_iterator>::difference_type dist;
for (dist = 0; first < last; ++dist)
- next(first, last);
+ utf8::next(first, last);
return dist;
}
@@ -207,12 +207,12 @@ namespace utf8
octet_iterator utf16to8 (u16bit_iterator start, u16bit_iterator end, octet_iterator result)
{
while (start != end) {
- uint32_t cp = internal::mask16(*start++);
+ uint32_t cp = utf8::internal::mask16(*start++);
// Take care of surrogate pairs first
- if (internal::is_lead_surrogate(cp)) {
+ if (utf8::internal::is_lead_surrogate(cp)) {
if (start != end) {
- uint32_t trail_surrogate = internal::mask16(*start++);
- if (internal::is_trail_surrogate(trail_surrogate))
+ uint32_t trail_surrogate = utf8::internal::mask16(*start++);
+ if (utf8::internal::is_trail_surrogate(trail_surrogate))
cp = (cp << 10) + trail_surrogate + internal::SURROGATE_OFFSET;
else
throw invalid_utf16(static_cast<uint16_t>(trail_surrogate));
@@ -222,10 +222,10 @@ namespace utf8
}
// Lone trail surrogate
- else if (internal::is_trail_surrogate(cp))
+ else if (utf8::internal::is_trail_surrogate(cp))
throw invalid_utf16(static_cast<uint16_t>(cp));
- result = append(cp, result);
+ result = utf8::append(cp, result);
}
return result;
}
@@ -234,7 +234,7 @@ namespace utf8
u16bit_iterator utf8to16 (octet_iterator start, octet_iterator end, u16bit_iterator result)
{
while (start != end) {
- uint32_t cp = next(start, end);
+ uint32_t cp = utf8::next(start, end);
if (cp > 0xffff) { //make a surrogate pair
*result++ = static_cast<uint16_t>((cp >> 10) + internal::LEAD_OFFSET);
*result++ = static_cast<uint16_t>((cp & 0x3ff) + internal::TRAIL_SURROGATE_MIN);
@@ -249,7 +249,7 @@ namespace utf8
octet_iterator utf32to8 (u32bit_iterator start, u32bit_iterator end, octet_iterator result)
{
while (start != end)
- result = append(*(start++), result);
+ result = utf8::append(*(start++), result);
return result;
}
@@ -258,7 +258,7 @@ namespace utf8
u32bit_iterator utf8to32 (octet_iterator start, octet_iterator end, u32bit_iterator result)
{
while (start != end)
- (*result++) = next(start, end);
+ (*result++) = utf8::next(start, end);
return result;
}
@@ -270,7 +270,7 @@ namespace utf8
octet_iterator range_start;
octet_iterator range_end;
public:
- iterator () {};
+ iterator () {}
explicit iterator (const octet_iterator& octet_it,
const octet_iterator& range_start,
const octet_iterator& range_end) :
@@ -284,7 +284,7 @@ namespace utf8
uint32_t operator * () const
{
octet_iterator temp = it;
- return next(temp, range_end);
+ return utf8::next(temp, range_end);
}
bool operator == (const iterator& rhs) const
{
@@ -298,24 +298,24 @@ namespace utf8
}
iterator& operator ++ ()
{
- next(it, range_end);
+ utf8::next(it, range_end);
return *this;
}
iterator operator ++ (int)
{
iterator temp = *this;
- next(it, range_end);
+ utf8::next(it, range_end);
return temp;
}
iterator& operator -- ()
{
- prior(it, range_start);
+ utf8::prior(it, range_start);
return *this;
}
iterator operator -- (int)
{
iterator temp = *this;
- prior(it, range_start);
+ utf8::prior(it, range_start);
return temp;
}
}; // class iterator
diff --git a/3party/utfcpp/source/utf8/core.h b/3party/utfcpp/source/utf8/core.h
index 268cf7cd48..693d388c07 100755..100644
--- a/3party/utfcpp/source/utf8/core.h
+++ b/3party/utfcpp/source/utf8/core.h
@@ -68,7 +68,7 @@ namespace internal
template<typename octet_type>
inline bool is_trail(octet_type oc)
{
- return ((mask8(oc) >> 6) == 0x2);
+ return ((utf8::internal::mask8(oc) >> 6) == 0x2);
}
template <typename u16>
@@ -92,14 +92,14 @@ namespace internal
template <typename u32>
inline bool is_code_point_valid(u32 cp)
{
- return (cp <= CODE_POINT_MAX && !is_surrogate(cp));
+ return (cp <= CODE_POINT_MAX && !utf8::internal::is_surrogate(cp));
}
template <typename octet_iterator>
inline typename std::iterator_traits<octet_iterator>::difference_type
sequence_length(octet_iterator lead_it)
{
- uint8_t lead = mask8(*lead_it);
+ uint8_t lead = utf8::internal::mask8(*lead_it);
if (lead < 0x80)
return 1;
else if ((lead >> 5) == 0x6)
@@ -133,123 +133,94 @@ namespace internal
enum utf_error {UTF8_OK, NOT_ENOUGH_ROOM, INVALID_LEAD, INCOMPLETE_SEQUENCE, OVERLONG_SEQUENCE, INVALID_CODE_POINT};
- /// get_sequence_x functions decode utf-8 sequences of the length x
+ /// Helper for get_sequence_x
+ template <typename octet_iterator>
+ utf_error increase_safely(octet_iterator& it, octet_iterator end)
+ {
+ if (++it == end)
+ return NOT_ENOUGH_ROOM;
+
+ if (!utf8::internal::is_trail(*it))
+ return INCOMPLETE_SEQUENCE;
+
+ return UTF8_OK;
+ }
+ #define UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(IT, END) {utf_error ret = increase_safely(IT, END); if (ret != UTF8_OK) return ret;}
+
+ /// get_sequence_x functions decode utf-8 sequences of the length x
template <typename octet_iterator>
- utf_error get_sequence_1(octet_iterator& it, octet_iterator end, uint32_t* code_point)
+ utf_error get_sequence_1(octet_iterator& it, octet_iterator end, uint32_t& code_point)
{
- if (it != end) {
- if (code_point)
- *code_point = mask8(*it);
- return UTF8_OK;
- }
- return NOT_ENOUGH_ROOM;
+ if (it == end)
+ return NOT_ENOUGH_ROOM;
+
+ code_point = utf8::internal::mask8(*it);
+
+ return UTF8_OK;
}
template <typename octet_iterator>
- utf_error get_sequence_2(octet_iterator& it, octet_iterator end, uint32_t* code_point)
+ utf_error get_sequence_2(octet_iterator& it, octet_iterator end, uint32_t& code_point)
{
- utf_error ret_code = NOT_ENOUGH_ROOM;
+ if (it == end)
+ return NOT_ENOUGH_ROOM;
+
+ code_point = utf8::internal::mask8(*it);
- if (it != end) {
- uint32_t cp = mask8(*it);
- if (++it != end) {
- if (is_trail(*it)) {
- cp = ((cp << 6) & 0x7ff) + ((*it) & 0x3f);
+ UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end)
- if (code_point)
- *code_point = cp;
- ret_code = UTF8_OK;
- }
- else
- ret_code = INCOMPLETE_SEQUENCE;
- }
- else
- ret_code = NOT_ENOUGH_ROOM;
- }
+ code_point = ((code_point << 6) & 0x7ff) + ((*it) & 0x3f);
- return ret_code;
+ return UTF8_OK;
}
template <typename octet_iterator>
- utf_error get_sequence_3(octet_iterator& it, octet_iterator end, uint32_t* code_point)
+ utf_error get_sequence_3(octet_iterator& it, octet_iterator end, uint32_t& code_point)
{
- utf_error ret_code = NOT_ENOUGH_ROOM;
-
- if (it != end) {
- uint32_t cp = mask8(*it);
- if (++it != end) {
- if (is_trail(*it)) {
- cp = ((cp << 12) & 0xffff) + ((mask8(*it) << 6) & 0xfff);
- if (++it != end) {
- if (is_trail(*it)) {
- cp += (*it) & 0x3f;
-
- if (code_point)
- *code_point = cp;
- ret_code = UTF8_OK;
- }
- else
- ret_code = INCOMPLETE_SEQUENCE;
- }
- else
- ret_code = NOT_ENOUGH_ROOM;
- }
- else
- ret_code = INCOMPLETE_SEQUENCE;
- }
- else
- ret_code = NOT_ENOUGH_ROOM;
- }
+ if (it == end)
+ return NOT_ENOUGH_ROOM;
+
+ code_point = utf8::internal::mask8(*it);
+
+ UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end)
+
+ code_point = ((code_point << 12) & 0xffff) + ((utf8::internal::mask8(*it) << 6) & 0xfff);
+
+ UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end)
- return ret_code;
+ code_point += (*it) & 0x3f;
+
+ return UTF8_OK;
}
template <typename octet_iterator>
- utf_error get_sequence_4(octet_iterator& it, octet_iterator end, uint32_t* code_point)
+ utf_error get_sequence_4(octet_iterator& it, octet_iterator end, uint32_t& code_point)
{
- utf_error ret_code = NOT_ENOUGH_ROOM;
-
- if (it != end) {
- uint32_t cp = mask8(*it);
- if (++it != end) {
- if (is_trail(*it)) {
- cp = ((cp << 18) & 0x1fffff) + ((mask8(*it) << 12) & 0x3ffff);
- if (++it != end) {
- if (is_trail(*it)) {
- cp += (mask8(*it) << 6) & 0xfff;
- if (++it != end) {
- if (is_trail(*it)) {
- cp += (*it) & 0x3f;
-
- if (code_point)
- *code_point = cp;
- ret_code = UTF8_OK;
- }
- else
- ret_code = INCOMPLETE_SEQUENCE;
- }
- else
- ret_code = NOT_ENOUGH_ROOM;
- }
- else
- ret_code = INCOMPLETE_SEQUENCE;
- }
- else
- ret_code = NOT_ENOUGH_ROOM;
- }
- else
- ret_code = INCOMPLETE_SEQUENCE;
- }
- else
- ret_code = NOT_ENOUGH_ROOM;
- }
+ if (it == end)
+ return NOT_ENOUGH_ROOM;
- return ret_code;
+ code_point = utf8::internal::mask8(*it);
+
+ UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end)
+
+ code_point = ((code_point << 18) & 0x1fffff) + ((utf8::internal::mask8(*it) << 12) & 0x3ffff);
+
+ UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end)
+
+ code_point += (utf8::internal::mask8(*it) << 6) & 0xfff;
+
+ UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end)
+
+ code_point += (*it) & 0x3f;
+
+ return UTF8_OK;
}
+ #undef UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR
+
template <typename octet_iterator>
- utf_error validate_next(octet_iterator& it, octet_iterator end, uint32_t* code_point)
+ utf_error validate_next(octet_iterator& it, octet_iterator end, uint32_t& code_point)
{
// Save the original value of it so we can go back in case of failure
// Of course, it does not make much sense with i.e. stream iterators
@@ -258,34 +229,33 @@ namespace internal
uint32_t cp = 0;
// Determine the sequence length based on the lead octet
typedef typename std::iterator_traits<octet_iterator>::difference_type octet_difference_type;
- octet_difference_type length = sequence_length(it);
- if (length == 0)
- return INVALID_LEAD;
+ const octet_difference_type length = utf8::internal::sequence_length(it);
- // Now that we have a valid sequence length, get trail octets and calculate the code point
+ // Get trail octets and calculate the code point
utf_error err = UTF8_OK;
switch (length) {
+ case 0:
+ return INVALID_LEAD;
case 1:
- err = get_sequence_1(it, end, &cp);
+ err = utf8::internal::get_sequence_1(it, end, cp);
break;
case 2:
- err = get_sequence_2(it, end, &cp);
+ err = utf8::internal::get_sequence_2(it, end, cp);
break;
case 3:
- err = get_sequence_3(it, end, &cp);
+ err = utf8::internal::get_sequence_3(it, end, cp);
break;
case 4:
- err = get_sequence_4(it, end, &cp);
+ err = utf8::internal::get_sequence_4(it, end, cp);
break;
}
if (err == UTF8_OK) {
// Decoding succeeded. Now, security checks...
- if (is_code_point_valid(cp)) {
- if (!is_overlong_sequence(cp, length)){
+ if (utf8::internal::is_code_point_valid(cp)) {
+ if (!utf8::internal::is_overlong_sequence(cp, length)){
// Passed! Return here.
- if (code_point)
- *code_point = cp;
+ code_point = cp;
++it;
return UTF8_OK;
}
@@ -303,7 +273,8 @@ namespace internal
template <typename octet_iterator>
inline utf_error validate_next(octet_iterator& it, octet_iterator end) {
- return validate_next(it, end, 0);
+ uint32_t ignored;
+ return utf8::internal::validate_next(it, end, ignored);
}
} // namespace internal
@@ -318,7 +289,7 @@ namespace internal
{
octet_iterator result = start;
while (result != end) {
- internal::utf_error err_code = internal::validate_next(result, end);
+ utf8::internal::utf_error err_code = utf8::internal::validate_next(result, end);
if (err_code != internal::UTF8_OK)
return result;
}
@@ -328,27 +299,27 @@ namespace internal
template <typename octet_iterator>
inline bool is_valid(octet_iterator start, octet_iterator end)
{
- return (find_invalid(start, end) == end);
+ return (utf8::find_invalid(start, end) == end);
}
template <typename octet_iterator>
inline bool starts_with_bom (octet_iterator it, octet_iterator end)
{
return (
- ((it != end) && (internal::mask8(*it++)) == bom[0]) &&
- ((it != end) && (internal::mask8(*it++)) == bom[1]) &&
- ((it != end) && (internal::mask8(*it)) == bom[2])
+ ((it != end) && (utf8::internal::mask8(*it++)) == bom[0]) &&
+ ((it != end) && (utf8::internal::mask8(*it++)) == bom[1]) &&
+ ((it != end) && (utf8::internal::mask8(*it)) == bom[2])
);
}
- //Deprecated in release 2.3
+ //Deprecated in release 2.3
template <typename octet_iterator>
inline bool is_bom (octet_iterator it)
{
return (
- (internal::mask8(*it++)) == bom[0] &&
- (internal::mask8(*it++)) == bom[1] &&
- (internal::mask8(*it)) == bom[2]
+ (utf8::internal::mask8(*it++)) == bom[0] &&
+ (utf8::internal::mask8(*it++)) == bom[1] &&
+ (utf8::internal::mask8(*it)) == bom[2]
);
}
} // namespace utf8
diff --git a/3party/utfcpp/source/utf8/unchecked.h b/3party/utfcpp/source/utf8/unchecked.h
index 2f3eb4d1d0..cb2427166b 100755..100644
--- a/3party/utfcpp/source/utf8/unchecked.h
+++ b/3party/utfcpp/source/utf8/unchecked.h
@@ -60,7 +60,7 @@ namespace utf8
template <typename octet_iterator>
uint32_t next(octet_iterator& it)
{
- uint32_t cp = internal::mask8(*it);
+ uint32_t cp = utf8::internal::mask8(*it);
typename std::iterator_traits<octet_iterator>::difference_type length = utf8::internal::sequence_length(it);
switch (length) {
case 1:
@@ -71,15 +71,15 @@ namespace utf8
break;
case 3:
++it;
- cp = ((cp << 12) & 0xffff) + ((internal::mask8(*it) << 6) & 0xfff);
+ cp = ((cp << 12) & 0xffff) + ((utf8::internal::mask8(*it) << 6) & 0xfff);
++it;
cp += (*it) & 0x3f;
break;
case 4:
++it;
- cp = ((cp << 18) & 0x1fffff) + ((internal::mask8(*it) << 12) & 0x3ffff);
+ cp = ((cp << 18) & 0x1fffff) + ((utf8::internal::mask8(*it) << 12) & 0x3ffff);
++it;
- cp += (internal::mask8(*it) << 6) & 0xfff;
+ cp += (utf8::internal::mask8(*it) << 6) & 0xfff;
++it;
cp += (*it) & 0x3f;
break;
@@ -91,29 +91,29 @@ namespace utf8
template <typename octet_iterator>
uint32_t peek_next(octet_iterator it)
{
- return next(it);
+ return utf8::unchecked::next(it);
}
template <typename octet_iterator>
uint32_t prior(octet_iterator& it)
{
- while (internal::is_trail(*(--it))) ;
+ while (utf8::internal::is_trail(*(--it))) ;
octet_iterator temp = it;
- return next(temp);
+ return utf8::unchecked::next(temp);
}
// Deprecated in versions that include prior, but only for the sake of consistency (see utf8::previous)
template <typename octet_iterator>
inline uint32_t previous(octet_iterator& it)
{
- return prior(it);
+ return utf8::unchecked::prior(it);
}
template <typename octet_iterator, typename distance_type>
void advance (octet_iterator& it, distance_type n)
{
for (distance_type i = 0; i < n; ++i)
- next(it);
+ utf8::unchecked::next(it);
}
template <typename octet_iterator>
@@ -122,7 +122,7 @@ namespace utf8
{
typename std::iterator_traits<octet_iterator>::difference_type dist;
for (dist = 0; first < last; ++dist)
- next(first);
+ utf8::unchecked::next(first);
return dist;
}
@@ -130,13 +130,13 @@ namespace utf8
octet_iterator utf16to8 (u16bit_iterator start, u16bit_iterator end, octet_iterator result)
{
while (start != end) {
- uint32_t cp = internal::mask16(*start++);
+ uint32_t cp = utf8::internal::mask16(*start++);
// Take care of surrogate pairs first
- if (internal::is_lead_surrogate(cp)) {
- uint32_t trail_surrogate = internal::mask16(*start++);
+ if (utf8::internal::is_lead_surrogate(cp)) {
+ uint32_t trail_surrogate = utf8::internal::mask16(*start++);
cp = (cp << 10) + trail_surrogate + internal::SURROGATE_OFFSET;
}
- result = append(cp, result);
+ result = utf8::unchecked::append(cp, result);
}
return result;
}
@@ -145,7 +145,7 @@ namespace utf8
u16bit_iterator utf8to16 (octet_iterator start, octet_iterator end, u16bit_iterator result)
{
while (start < end) {
- uint32_t cp = next(start);
+ uint32_t cp = utf8::unchecked::next(start);
if (cp > 0xffff) { //make a surrogate pair
*result++ = static_cast<uint16_t>((cp >> 10) + internal::LEAD_OFFSET);
*result++ = static_cast<uint16_t>((cp & 0x3ff) + internal::TRAIL_SURROGATE_MIN);
@@ -160,7 +160,7 @@ namespace utf8
octet_iterator utf32to8 (u32bit_iterator start, u32bit_iterator end, octet_iterator result)
{
while (start != end)
- result = append(*(start++), result);
+ result = utf8::unchecked::append(*(start++), result);
return result;
}
@@ -169,7 +169,7 @@ namespace utf8
u32bit_iterator utf8to32 (octet_iterator start, octet_iterator end, u32bit_iterator result)
{
while (start < end)
- (*result++) = next(start);
+ (*result++) = utf8::unchecked::next(start);
return result;
}
@@ -179,14 +179,14 @@ namespace utf8
class iterator : public std::iterator <std::bidirectional_iterator_tag, uint32_t> {
octet_iterator it;
public:
- iterator () {};
+ iterator () {}
explicit iterator (const octet_iterator& octet_it): it(octet_it) {}
// the default "big three" are OK
octet_iterator base () const { return it; }
uint32_t operator * () const
{
octet_iterator temp = it;
- return next(temp);
+ return utf8::unchecked::next(temp);
}
bool operator == (const iterator& rhs) const
{
@@ -198,24 +198,24 @@ namespace utf8
}
iterator& operator ++ ()
{
- std::advance(it, internal::sequence_length(it));
+ ::std::advance(it, utf8::internal::sequence_length(it));
return *this;
}
iterator operator ++ (int)
{
iterator temp = *this;
- std::advance(it, internal::sequence_length(it));
+ ::std::advance(it, utf8::internal::sequence_length(it));
return temp;
}
iterator& operator -- ()
{
- prior(it);
+ utf8::unchecked::prior(it);
return *this;
}
iterator operator -- (int)
{
iterator temp = *this;
- prior(it);
+ utf8::unchecked::prior(it);
return temp;
}
}; // class iterator