CVSROOT: /sources/gnash
Module name: gnash
Changes by: Benjamin Wolsey <bwy> 08/02/05 12:01:52
Modified files:
. : ChangeLog
server : button_character_instance.cpp
edit_text_character.cpp edit_text_character.h
event_id.h gnash.h movie_root.cpp
libbase : utf8.cpp utf8.h
Log message:
2008-02-05 Benjamin Wolsey <[EMAIL PROTECTED]>
* server/movie_root.cpp: send unique gnash::key::code not
SWFCode
to event_id; edit_text_character relies on this code to work
out
which character was passed and SWFcode is bogus.
* server/event_id.h: store gnash::key::code not SWFCode;
setKeyCode
converts SWFCode to a corresponding gnash::key::code.
* server/gnash.h: add enum for different key code types.
* server/button_character_instance.cpp: lookup SWFCode from
gnash::key::code.
* libbase/utf8.{cpp,h}: add {decode,encode}CanonicalString
methods
for converting between UTF-8 encoded std::string and
std::wstring.
Fix some bugs in character decoding.
* server/edit_text_character.{cpp.h}: use std::wstring
internally,
as once we receive multi-byte characters the cursor position
and
std::string position are different. Wide characters mean
string
manipulation can stay as before. Interfaces still use
std::string
with conversions when necessary. Make wstring methods
private.
set_text_value(const char*) -> setTextValue(const wstring&).
Handles characters like ö or ¶.
Sorry for the large commit. It was just a small bug with a lot of
implications.
It passes the testsuite and I think I've adapted button key events
correctly, but I hope someone who knows more about them can check.
CVSWeb URLs:
http://cvs.savannah.gnu.org/viewcvs/gnash/ChangeLog?cvsroot=gnash&r1=1.5557&r2=1.5558
http://cvs.savannah.gnu.org/viewcvs/gnash/server/button_character_instance.cpp?cvsroot=gnash&r1=1.79&r2=1.80
http://cvs.savannah.gnu.org/viewcvs/gnash/server/edit_text_character.cpp?cvsroot=gnash&r1=1.145&r2=1.146
http://cvs.savannah.gnu.org/viewcvs/gnash/server/edit_text_character.h?cvsroot=gnash&r1=1.65&r2=1.66
http://cvs.savannah.gnu.org/viewcvs/gnash/server/event_id.h?cvsroot=gnash&r1=1.15&r2=1.16
http://cvs.savannah.gnu.org/viewcvs/gnash/server/gnash.h?cvsroot=gnash&r1=1.113&r2=1.114
http://cvs.savannah.gnu.org/viewcvs/gnash/server/movie_root.cpp?cvsroot=gnash&r1=1.157&r2=1.158
http://cvs.savannah.gnu.org/viewcvs/gnash/libbase/utf8.cpp?cvsroot=gnash&r1=1.7&r2=1.8
http://cvs.savannah.gnu.org/viewcvs/gnash/libbase/utf8.h?cvsroot=gnash&r1=1.5&r2=1.6
Patches:
Index: ChangeLog
===================================================================
RCS file: /sources/gnash/gnash/ChangeLog,v
retrieving revision 1.5557
retrieving revision 1.5558
diff -u -b -r1.5557 -r1.5558
--- ChangeLog 5 Feb 2008 10:50:14 -0000 1.5557
+++ ChangeLog 5 Feb 2008 12:01:50 -0000 1.5558
@@ -1,3 +1,24 @@
+2008-02-05 Benjamin Wolsey <[EMAIL PROTECTED]>
+
+ * server/movie_root.cpp: send unique gnash::key::code not SWFCode
+ to event_id; edit_text_character relies on this code to work out
+ which character was passed and SWFcode is bogus.
+ * server/event_id.h: store gnash::key::code not SWFCode; setKeyCode
+ converts SWFCode to a corresponding gnash::key::code.
+ * server/gnash.h: add enum for different key code types.
+ * server/button_character_instance.cpp: lookup SWFCode from
+ gnash::key::code.
+ * libbase/utf8.{cpp,h}: add {decode,encode}CanonicalString methods
+ for converting between UTF-8 encoded std::string and std::wstring.
+ Fix some bugs in character decoding.
+ * server/edit_text_character.{cpp.h}: use std::wstring internally,
+ as once we receive multi-byte characters the cursor position and
+ std::string position are different. Wide characters mean string
+ manipulation can stay as before. Interfaces still use std::string
+ with conversions when necessary. Make wstring methods private.
+ set_text_value(const char*) -> setTextValue(const wstring&).
+ Handles characters like ö or ¶.
+
2008-02-05 Bastiaan Jacques <[EMAIL PROTECTED]>
* libmedia/gst/VideoDecoderGst.cpp: Use a different ffdec
Index: server/button_character_instance.cpp
===================================================================
RCS file: /sources/gnash/gnash/server/button_character_instance.cpp,v
retrieving revision 1.79
retrieving revision 1.80
diff -u -b -r1.79 -r1.80
--- server/button_character_instance.cpp 29 Jan 2008 12:31:09 -0000
1.79
+++ server/button_character_instance.cpp 5 Feb 2008 12:01:51 -0000
1.80
@@ -331,7 +331,7 @@
button_character_instance::on_event(const event_id& id)
{
- if( (id.m_id==event_id::KEY_PRESS) && (id.m_key_code == key::INVALID) )
+ if( (id.m_id==event_id::KEY_PRESS) && (id.keyCode == key::INVALID) )
{
// onKeypress only responds to valid key code
return false;
@@ -346,8 +346,10 @@
button_action& ba = *(m_def->m_button_actions[i]);
int keycode = (ba.m_conditions & 0xFE00) >> 9;
- event_id key_event(event_id::KEY_PRESS, (key::code) keycode);
- if (key_event == id)
+
+ // Test match between button action conditions and the SWF code
+ // that maps to id.keyCode (the gnash unique key code).
+ if (id.m_id == event_id::KEY_PRESS &&
gnash::key::codeMap[id.keyCode][key::SWF] == keycode)
{
// Matching action.
VM::get().getRoot().pushAction(ba.m_actions,
boost::intrusive_ptr<character>(this));
Index: server/edit_text_character.cpp
===================================================================
RCS file: /sources/gnash/gnash/server/edit_text_character.cpp,v
retrieving revision 1.145
retrieving revision 1.146
diff -u -b -r1.145 -r1.146
--- server/edit_text_character.cpp 4 Feb 2008 15:16:54 -0000 1.145
+++ server/edit_text_character.cpp 5 Feb 2008 12:01:51 -0000 1.146
@@ -17,8 +17,6 @@
// Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
//
-/* $Id: edit_text_character.cpp,v 1.145 2008/02/04 15:16:54 bwy Exp $ */
-
#ifdef HAVE_CONFIG_H
#include "gnashconfig.h"
#endif
@@ -373,6 +371,7 @@
edit_text_character_def* def, int id)
:
character(parent, id),
+ _text(L""),
m_def(def),
_font(0),
m_has_focus(false),
@@ -408,7 +407,8 @@
// set default text *before* calling registerTextVariable
// (if the textvariable already exist and has a value
// the text will be replaced with it)
- set_text_value(m_def->get_default_text().c_str());
+
+ setTextValue(utf8::decodeCanonicalString(m_def->get_default_text()));
m_dummy_style.push_back(fill_style());
@@ -590,21 +590,22 @@
case event_id::KEY_PRESS:
{
- std::string s(_text);
- std::string c;
- c = (char) id.m_key_code;
+ std::wstring s = _text;
+
+ // id.keyCode is the unique gnash::key::code for a
character
+ uint32_t c = (uint32_t) id.keyCode;
- // may be _text is changed in ActionScript
+ // maybe _text is changed in ActionScript
m_cursor = imin(m_cursor, _text.size());
- switch (c[0])
+ switch (c)
{
case key::BACKSPACE:
if (m_cursor > 0)
{
s.erase(m_cursor - 1, 1);
m_cursor--;
- set_text_value(s.c_str());
+ setTextValue(s);
}
break;
@@ -612,7 +613,7 @@
if (s.size() > m_cursor)
{
s.erase(m_cursor, 1);
- set_text_value(s.c_str());
+ setTextValue(s);
}
break;
@@ -644,12 +645,14 @@
break;
default:
+ wchar_t t = (wchar_t)
gnash::key::codeMap[c][key::ASCII];
+ if (t != 0)
{
- s.insert(m_cursor, c);
+ s.insert(m_cursor, 1, t);
m_cursor++;
- set_text_value(s.c_str());
- break;
}
+ setTextValue(s);
+ break;
}
onChanged();
}
@@ -692,11 +695,19 @@
}
void
-edit_text_character::updateText(const std::string& new_text)
+edit_text_character::updateText(const std::string& str)
+{
+ std::wstring wstr = utf8::decodeCanonicalString(str);
+ updateText(wstr);
+}
+
+
+void
+edit_text_character::updateText(const std::wstring& wstr)
{
unsigned int maxLen = m_def->get_max_length();
- std::string newText = new_text; // copy needed for eventual resize
+ std::wstring newText = wstr; // copy needed for eventual resize
if (maxLen && newText.length() > maxLen )
{
newText.resize(maxLen);
@@ -718,12 +729,10 @@
}
void
-edit_text_character::set_text_value(const char* new_text_cstr)
+edit_text_character::setTextValue(const std::wstring& wstr)
{
- std::string newText;
- if ( new_text_cstr ) newText = new_text_cstr;
- updateText(newText);
+ updateText(wstr);
if ( ! _variable_name.empty() && _text_variable_registered )
{
@@ -732,12 +741,12 @@
as_object* tgt = ref.first;
if ( tgt )
{
- tgt->set_member(ref.second, newText); // we shouldn't
truncate, right ?
+ tgt->set_member(ref.second,
utf8::encodeCanonicalString(wstr)); // we shouldn't truncate, right ?
}
else
{
// nothing to do (too early ?)
- log_debug("set_text_value: variable name %s points to
an unexisting target, I guess we would not be registered in this was true, or
the sprite we've registered our variable name has been unloaded",
_variable_name.c_str());
+ log_debug("setTextValue: variable name %s points to an
unexisting target, I guess we would not be registered in this was true, or the
sprite we've registered our variable name has been unloaded",
_variable_name.c_str());
}
}
}
@@ -747,13 +756,13 @@
{
// we need the const_cast here because registerTextVariable
// *might* change our text value, calling the non-const
- // set_text_value().
+ // setTextValue().
// This happens if the TextVariable has not been already registered
// and during registration comes out to name an existing variable
// with a pre-existing value.
const_cast<edit_text_character*>(this)->registerTextVariable();
- return _text;
+ return utf8::encodeCanonicalString(_text);
}
void
@@ -774,14 +783,14 @@
//if (name == "text")
{
int version =
get_parent()->get_movie_definition()->get_version();
- set_text_value(val.to_string_versioned(version).c_str());
+
setTextValue(utf8::decodeCanonicalString(val.to_string_versioned(version)));
return;
}
case NSV::PROP_HTML_TEXT:
//if (name == "htmlText")
{
int version =
get_parent()->get_movie_definition()->get_version();
- set_text_value(val.to_string_versioned(version).c_str());
+
setTextValue(utf8::decodeCanonicalString(val.to_string_versioned(version)));
format_text();
return;
}
@@ -1172,12 +1181,12 @@
assert(! _text.empty() );
- std::string::const_iterator it = _text.begin();
+ std::wstring::const_iterator it = _text.begin();
// decodeNextUnicodeCharacter(std::string::const_iterator &it) works,
// but unfortunately nothing is encoded in utf8.
- while (boost::uint32_t code = utf8::decodeNextUnicodeCharacter(it))
+ while (boost::uint32_t code = *it++)
{
if ( _embedFonts )
{
@@ -1262,7 +1271,7 @@
// HTML tag, just skip it...
bool closingTagFound = false;
- while ( (code = utf8::decodeNextUnicodeCharacter(it)) )
+ while ( (code = *it++) )
{
if (code == '>')
{
@@ -1369,7 +1378,7 @@
//log_debug(" autoSize=NONE!");
// truncate long line, but keep
expanding text box
bool newlinefound = false;
- while ( (code =
utf8::decodeNextUnicodeCharacter(it)) )
+ while ( (code = *it++ ) )
{
if ( _embedFonts )
{
@@ -1585,14 +1594,14 @@
#endif
// TODO: pass environment to to_string ?
// as_environment& env = get_environment();
- set_text_value(val.to_string().c_str());
+ setTextValue(utf8::decodeCanonicalString(val.to_string()));
}
else
{
#ifdef DEBUG_DYNTEXT_VARIABLES
log_msg(_("target sprite (%p) does NOT have a member named %s
(no problem, we'll add it)"), (void*)sprite,
_vm.getStringTable().value(key).c_str());
#endif
- target->set_member(key, as_value(_text));
+ target->set_member(key,
as_value(utf8::encodeCanonicalString(_text)));
}
sprite_instance* sprite = target->to_movie();
@@ -1618,7 +1627,7 @@
{
_variable_name = newname;
_text_variable_registered = false;
- //set_text_value(m_def->get_default_text().c_str());
+ //setTextValue(m_def->get_default_text());
#ifdef DEBUG_DYNTEXT_VARIABLES
log_debug("Calling updateText after change of variable name");
#endif
Index: server/edit_text_character.h
===================================================================
RCS file: /sources/gnash/gnash/server/edit_text_character.h,v
retrieving revision 1.65
retrieving revision 1.66
diff -u -b -r1.65 -r1.66
--- server/edit_text_character.h 21 Jan 2008 20:55:50 -0000 1.65
+++ server/edit_text_character.h 5 Feb 2008 12:01:51 -0000 1.66
@@ -90,17 +90,10 @@
///
void set_variable_name(const std::string& newname);
- /// Set our text to the given string.
- //
- /// This function will also update any registered variable
- ///
- void set_text_value(const char* new_text);
-
/// Set our text to the given string by effect of an update of a
registered variable name
//
/// This cal only updates the text and is only meant to be called by
ourselves
/// or by sprite_instance when a registered TextVariable is updated.
- ///
void updateText(const std::string& s);
/// Return value of our text.
@@ -285,6 +278,19 @@
private:
+ /// Set our text to the given string.
+ //
+ /// This function will also update any registered variable
+ ///
+ void setTextValue(const std::wstring& wstr);
+
+ /// Set our text to the given string by effect of an update of a
registered variable name
+ //
+ /// This cal only updates the text and is only meant to be called by
ourselves
+ /// or by sprite_instance when a registered TextVariable is updated.
+ ///
+ void updateText(const std::wstring& s);
+
/// Set focus
void setFocus();
@@ -300,8 +306,10 @@
/// Call this function when willing to invoke the onKillFocus event
handler
void onKillFocus();
- /// The actual text
- std::string _text;
+ /// The actual text. Because we have to deal with non-ascii characters
(129-255)
+ /// this is a wide string; the cursor position and the position within
the string
+ /// are then the same, which makes manipulating the string much easier.
+ std::wstring _text;
/// immutable definition of this object, as read
/// from the SWF stream. Assured to be not-NULL
Index: server/event_id.h
===================================================================
RCS file: /sources/gnash/gnash/server/event_id.h,v
retrieving revision 1.15
retrieving revision 1.16
diff -u -b -r1.15 -r1.16
--- server/event_id.h 21 Jan 2008 20:55:50 -0000 1.15
+++ server/event_id.h 5 Feb 2008 12:01:51 -0000 1.16
@@ -29,11 +29,8 @@
#include "gnash.h" // for gnash::key namespace
-#include <cwchar>
-
namespace gnash {
-
/// For keyDown and stuff like that.
//
/// Implementation is currently in action.cpp
@@ -95,30 +92,48 @@
};
id_code m_id;
- unsigned char m_key_code;
- event_id() : m_id(INVALID), m_key_code(key::INVALID) {}
+ // keyCode must be the unique gnash key identifier
+ // gnash::key::code.
+ // edit_text_character has to be able to work out the
+ // ASCII value from keyCode, while other users need
+ // the SWF code or the Flash key code.
+ key::code keyCode;
+
+ event_id() : m_id(INVALID), keyCode(key::INVALID) {}
- event_id(id_code id, unsigned char c = key::INVALID)
+ event_id(id_code id, key::code c = key::INVALID)
:
m_id(id),
- m_key_code(c)
+ keyCode(c)
{
// you must supply a key code for KEY_PRESS event
//
- // we do have a testcase with m_id == KEY_PRESS, and
m_key_code==0(KEY_INVALID)
+ // we do have a testcase with m_id == KEY_PRESS, and
keyCode==0(KEY_INVALID)
// see key_event_test.swf(produced by Ming)
//
- //assert((m_key_code == key::INVALID && (m_id != KEY_PRESS))
- // || (m_key_code != key::INVALID && (m_id == KEY_PRESS)));
+ //assert((keyCode == key::INVALID && (m_id != KEY_PRESS))
+ // || (keyCode != key::INVALID && (m_id == KEY_PRESS)));
}
- void setKeyCode(unsigned char key)
+ ///
+ /// @param SWFKey The SWF code matched to the event. This
+ /// must be converted to a unique gnash::key::code.
+ void setKeyCode(boost::uint8_t SWFkey)
{
- m_key_code = key;
+ // Lookup the SWFcode in the gnash::key::code table.
+ // Some are not unique (keypad numbers are the
+ // same as normal numbers), so we take the first match.
+ // As long as we can work out the SWFCode from the
+ // gnash::key::code it's all right.
+ int i = 0;
+ while (key::codeMap[i][key::SWF] != SWFkey && i <
key::KEYCOUNT) i++;
+
+ if (i == key::KEYCOUNT) keyCode = key::INVALID;
+ else keyCode = (key::code)i;
}
- bool operator==(const event_id& id) const { return m_id == id.m_id
&& m_key_code == id.m_key_code; }
+ bool operator==(const event_id& id) const { return m_id == id.m_id
&& keyCode == id.keyCode; }
bool operator< (const event_id& id) const
{
@@ -126,7 +141,7 @@
if ( m_id > id.m_id ) return false;
// m_id are equal, check key code
- if ( m_key_code < id.m_key_code ) return true;
+ if ( keyCode < id.keyCode ) return true;
return false;
}
Index: server/gnash.h
===================================================================
RCS file: /sources/gnash/gnash/server/gnash.h,v
retrieving revision 1.113
retrieving revision 1.114
diff -u -b -r1.113 -r1.114
--- server/gnash.h 21 Jan 2008 20:55:51 -0000 1.113
+++ server/gnash.h 5 Feb 2008 12:01:51 -0000 1.114
@@ -637,7 +637,15 @@
KEYCOUNT
};
-const unsigned char codeMap[KEYCOUNT][3] = {
+enum type
+{
+ SWF,
+ KEY,
+ ASCII,
+ TYPES
+};
+
+const unsigned char codeMap[KEYCOUNT][TYPES] = {
//{swfKeyCode, keycode, asciiKeyCode}
{0, 0, 0}, // INVALID = 0
{0, 0, 0}, // UNKNOWN1
Index: server/movie_root.cpp
===================================================================
RCS file: /sources/gnash/gnash/server/movie_root.cpp,v
retrieving revision 1.157
retrieving revision 1.158
diff -u -b -r1.157 -r1.158
--- server/movie_root.cpp 31 Jan 2008 13:41:32 -0000 1.157
+++ server/movie_root.cpp 5 Feb 2008 12:01:51 -0000 1.158
@@ -1133,7 +1133,8 @@
{
// KEY_UP and KEY_DOWN events are unrelated to
any key!
ch->on_event(event_id(event_id::KEY_DOWN,
key::INVALID));
- ch->on_event(event_id(event_id::KEY_PRESS,
key::codeMap[k][0]));
+ // Pass the unique Gnash key code!
+ ch->on_event(event_id(event_id::KEY_PRESS, k));
}
else
{
Index: libbase/utf8.cpp
===================================================================
RCS file: /sources/gnash/gnash/libbase/utf8.cpp,v
retrieving revision 1.7
retrieving revision 1.8
diff -u -b -r1.7 -r1.8
--- libbase/utf8.cpp 4 Feb 2008 15:16:54 -0000 1.7
+++ libbase/utf8.cpp 5 Feb 2008 12:01:51 -0000 1.8
@@ -1,15 +1,58 @@
-// utf8.cpp -- Thatcher Ulrich 2004 -*- coding: utf-8;-*-
-
-// This source code has been donated to the Public Domain. Do
-// whatever you want with it. THE AUTHOR DOES NOT WARRANT THIS CODE.
-
-// Utility code for dealing with UTF-8 encoded text.
+// utf8.cpp: utilities for converting to and from UTF-8
+//
+// Copyright (C) 2008 Free Software Foundation, Inc.
+//
+// This program is free software; you can redistribute it and/or modify
+// it under the terms of the GNU General Public License as published by
+// the Free Software Foundation; either version 3 of the License, or
+// (at your option) any later version.
+//
+// This program is distributed in the hope that it will be useful,
+// but WITHOUT ANY WARRANTY; without even the implied warranty of
+// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+// GNU General Public License for more details.
+//
+// You should have received a copy of the GNU General Public License
+// along with this program; if not, write to the Free Software
+// Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
+//
+// Based on the public domain work of Thatcher Ulrich <[EMAIL PROTECTED]> 2004
//
// Much useful info at "UTF-8 and Unicode FAQ"
http://www.cl.cam.ac.uk/~mgk25/unicode.html
#include "utf8.h"
+std::wstring
+utf8::decodeCanonicalString(const std::string& str)
+{
+ std::wstring wstr = L"";
+
+ std::string::const_iterator it = str.begin();
+ while (boost::uint32_t code = utf8::decodeNextUnicodeCharacter(it))
+ {
+ wstr.push_back((wchar_t) code);
+ }
+
+ return wstr;
+
+}
+
+std::string
+utf8::encodeCanonicalString(const std::wstring& wstr)
+{
+ std::string str = "";
+
+ std::wstring::const_iterator it = wstr.begin();
+ while ( it != wstr.end())
+ {
+ str.append(utf8::encodeUnicodeCharacter(*it++));
+ }
+
+ return str;
+
+}
+
boost::uint32_t
utf8::decodeNextUnicodeCharacter(std::string::const_iterator& it)
{
boost::uint32_t uc;
@@ -104,6 +147,7 @@
else
{
// Invalid.
+ it++;
return INVALID;
}
}
@@ -119,47 +163,47 @@
if (ucs_character <= 0x7F)
{
// Plain single-byte ASCII.
- text += (char) ucs_character;
+ text.push_back(ucs_character);
}
else if (ucs_character <= 0x7FF)
{
// Two bytes.
- text += 0xC0 | (ucs_character >> 6);
- text += 0x80 | ((ucs_character >> 0) & 0x3F);
+ text.push_back(0xC0 | (ucs_character >> 6));
+ text.push_back(0x80 | ((ucs_character >> 0) & 0x3F));
}
else if (ucs_character <= 0xFFFF)
{
// Three bytes.
- text += 0xE0 | (ucs_character >> 12);
- text += 0x80 | ((ucs_character >> 6) & 0x3F);
- text += 0x80 | ((ucs_character >> 0) & 0x3F);
+ text.push_back(0xE0 | (ucs_character >> 12));
+ text.push_back(0x80 | ((ucs_character >> 6) & 0x3F));
+ text.push_back(0x80 | ((ucs_character >> 0) & 0x3F));
}
else if (ucs_character <= 0x1FFFFF)
{
// Four bytes.
- text += 0xF0 | (ucs_character >> 18);
- text += 0x80 | ((ucs_character >> 12) & 0x3F);
- text += 0x80 | ((ucs_character >> 6) & 0x3F);
- text += 0x80 | ((ucs_character >> 0) & 0x3F);
+ text.push_back(0xF0 | (ucs_character >> 18));
+ text.push_back(0x80 | ((ucs_character >> 12) & 0x3F));
+ text.push_back(0x80 | ((ucs_character >> 6) & 0x3F));
+ text.push_back(0x80 | ((ucs_character >> 0) & 0x3F));
}
else if (ucs_character <= 0x3FFFFFF)
{
// Five bytes.
- text += 0xF8 | (ucs_character >> 24);
- text += 0x80 | ((ucs_character >> 18) & 0x3F);
- text += 0x80 | ((ucs_character >> 12) & 0x3F);
- text += 0x80 | ((ucs_character >> 6) & 0x3F);
- text += 0x80 | ((ucs_character >> 0) & 0x3F);
+ text.push_back(0xF8 | (ucs_character >> 24));
+ text.push_back(0x80 | ((ucs_character >> 18) & 0x3F));
+ text.push_back(0x80 | ((ucs_character >> 12) & 0x3F));
+ text.push_back(0x80 | ((ucs_character >> 6) & 0x3F));
+ text.push_back(0x80 | ((ucs_character >> 0) & 0x3F));
}
else if (ucs_character <= 0x7FFFFFFF)
{
// Six bytes.
- text += 0xFC | (ucs_character >> 30);
- text += 0x80 | ((ucs_character >> 24) & 0x3F);
- text += 0x80 | ((ucs_character >> 18) & 0x3F);
- text += 0x80 | ((ucs_character >> 12) & 0x3F);
- text += 0x80 | ((ucs_character >> 6) & 0x3F);
- text += 0x80 | ((ucs_character >> 0) & 0x3F);
+ text.push_back(0xFC | (ucs_character >> 30));
+ text.push_back(0x80 | ((ucs_character >> 24) & 0x3F));
+ text.push_back(0x80 | ((ucs_character >> 18) & 0x3F));
+ text.push_back(0x80 | ((ucs_character >> 12) & 0x3F));
+ text.push_back(0x80 | ((ucs_character >> 6) & 0x3F));
+ text.push_back(0x80 | ((ucs_character >> 0) & 0x3F));
}
else
{
@@ -169,199 +213,6 @@
return text;
}
-
-#ifdef UTF8_UNIT_TEST
-
-// Compile this test case with something like:
-//
-// c++ utf8.cpp -g -I.. -DUTF8_UNIT_TEST -o utf8_test
-//
-// or
-//
-// cl utf8.cpp -Zi -Od -DUTF8_UNIT_TEST -I..
-//
-// If possible, try running the test program with the first arg
-// pointing at the file:
-//
-// http://www.cl.cam.ac.uk/~mgk25/ucs/examples/UTF-8-test.txt
-//
-// and examine the results by eye to make sure they are acceptable to
-// you.
-
-
-#include "utility.h"
-#include <cstdio>
-
-
-bool check_equal(const char* utf8_in, const boost::uint32_t* ucs_in)
-{
- for (;;)
- {
- boost::uint32_t next_ucs = *ucs_in++;
- boost::uint32_t next_ucs_from_utf8 =
utf8::decode_next_unicode_character(&utf8_in);
- if (next_ucs != next_ucs_from_utf8)
- {
- return false;
- }
- if (next_ucs == 0)
- {
- assert(next_ucs_from_utf8 == 0);
- break;
- }
- }
-
- return true;
-}
-
-
-void log_ascii(const char* line)
-{
- for (;;)
- {
- unsigned char c = (unsigned char) *line++;
- if (c == 0)
- {
- // End of line.
- return;
- }
- else if (c != '\n'
- && (c < 32 || c > 127))
- {
- // Non-printable as plain ASCII.
- printf("<0x%02X>", (int) c);
- }
- else
- {
- printf("%c", c);
- }
- }
-}
-
-
-void log_ucs(const boost::uint32_t* line)
-{
- for (;;)
- {
- boost::uint32_t uc = *line++;
- if (uc == 0)
- {
- // End of line.
- return;
- }
- else if (uc != '\n'
- && (uc < 32 || uc > 127))
- {
- // Non-printable as plain ASCII.
- printf("<U-%04X>", uc);
- }
- else
- {
- printf("%c", (char) uc);
- }
- }
-}
-
-
-int main(int argc, const char* argv[])
-{
- // Simple canned test.
- {
- const char* test8 = "Ignacio Castaño";
- const boost::uint32_t test32[] =
- {
- 0x49, 0x67, 0x6E, 0x61, 0x63,
- 0x69, 0x6F, 0x20, 0x43, 0x61,
- 0x73, 0x74, 0x61, 0xF1, 0x6F,
- 0x00
- };
-
- assert(check_equal(test8, test32));
- }
-
- // If user passed an arg, try reading the file as UTF-8 encoded text.
- if (argc > 1)
- {
- const char* filename = argv[1];
- FILE* fp = fopen(filename, "rb");
- if (fp == NULL)
- {
- printf("Can't open file '%s'\n", filename);
- return 1;
- }
-
- // Read lines from the file, encode/decode them, and highlight
discrepancies.
- const int LINE_SIZE = 200; // max line size
- char line_buffer_utf8[LINE_SIZE];
- char reencoded_utf8[6 * LINE_SIZE];
- boost::uint32_t line_buffer_ucs[LINE_SIZE];
-
- int byte_counter = 0;
- for (;;)
- {
- int c = fgetc(fp);
- if (c == EOF)
- {
- // Done.
- break;
- }
- line_buffer_utf8[byte_counter++] = c;
- if (c == '\n' || byte_counter >= LINE_SIZE - 2)
- {
- // End of line. Process the line.
- line_buffer_utf8[byte_counter++] = '\0';
// terminate.
-
- // Decode into UCS.
- const char* p = line_buffer_utf8;
- boost::uint32_t* q = line_buffer_ucs;
- for (;;)
- {
- boost::uint32_t uc =
utf8::decode_next_unicode_character(&p);
- *q++ = uc;
-
- assert(q < line_buffer_ucs + LINE_SIZE);
- assert(p < line_buffer_utf8 +
LINE_SIZE);
-
- if (uc == 0) break;
- }
-
- // Encode back into UTF-8.
- q = line_buffer_ucs;
- int index = 0;
- for (;;)
- {
- boost::uint32_t uc = *q++;
- assert(index < LINE_SIZE * 6 - 6);
- int last_index = index;
-
utf8::encode_unicode_character(reencoded_utf8, &index, uc);
- assert(index <= last_index + 6);
- if (uc == 0) break;
- }
-
-// This can be useful for debugging.
-#if 0
- // Show the UCS and the re-encoded UTF-8.
- log_ucs(line_buffer_ucs);
- log_ascii(reencoded_utf8);
-#endif // 0
-
- assert(check_equal(line_buffer_utf8,
line_buffer_ucs));
- assert(check_equal(reencoded_utf8,
line_buffer_ucs));
-
- // Start next line.
- byte_counter = 0;
- }
- }
-
- fclose(fp);
- }
-
- return 0;
-}
-
-
-#endif // UTF8_UNIT_TEST
-
-
// Local Variables:
// mode: C++
// c-basic-offset: 8
Index: libbase/utf8.h
===================================================================
RCS file: /sources/gnash/gnash/libbase/utf8.h,v
retrieving revision 1.5
retrieving revision 1.6
diff -u -b -r1.5 -r1.6
--- libbase/utf8.h 4 Feb 2008 15:16:54 -0000 1.5
+++ libbase/utf8.h 5 Feb 2008 12:01:52 -0000 1.6
@@ -1,28 +1,46 @@
-// utf8.h -- Thatcher Ulrich <[EMAIL PROTECTED]> 2004
-
-// This source code has been donated to the Public Domain. Do
-// whatever you want with it. THE AUTHOR DOES NOT WARRANT THIS CODE.
-
-// Utility code for dealing with UTF-8 encoded text.
-
+// utf8.h: utilities for converting to and from UTF-8
+//
+// Copyright (C) 2008 Free Software Foundation, Inc.
+//
+// This program is free software; you can redistribute it and/or modify
+// it under the terms of the GNU General Public License as published by
+// the Free Software Foundation; either version 3 of the License, or
+// (at your option) any later version.
+//
+// This program is distributed in the hope that it will be useful,
+// but WITHOUT ANY WARRANTY; without even the implied warranty of
+// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+// GNU General Public License for more details.
+//
+// You should have received a copy of the GNU General Public License
+// along with this program; if not, write to the Free Software
+// Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
+//
+// Based on the public domain work of Thatcher Ulrich <[EMAIL PROTECTED]> 2004
#ifndef UTF8_H
#define UTF8_H
-#include "tu_config.h" // needed ?
+#include "tu_config.h" // For DSOEXPORT
#include <string>
-
#include <boost/cstdint.hpp> // for boost::?int??_t
namespace utf8
{
+ // Converts a UTF-8 encoded std::string with multibyte characters into
+ // a std::wstring.
+ DSOEXPORT std::wstring decodeCanonicalString(const std::string& str);
+
+ // Converts a std::wstring into a UTF-8 encoded std::string.
+ DSOEXPORT std::string encodeCanonicalString(const std::wstring& wstr);
+
// Return the next Unicode character in the UTF-8 encoded
// string. Invalid UTF-8 sequences produce a U+FFFD character
// as output. Advances string iterator past the character
// returned, unless the returned character is '\0', in which
// case the iterator does not advance.
- DSOEXPORT boost::uint32_t
decodeNextUnicodeCharacter(std::string::const_iterator& it);
+ boost::uint32_t decodeNextUnicodeCharacter(std::string::const_iterator&
it);
// Encodes the given UCS character into the given UTF-8
// buffer. Writes the data starting at buffer[offset], and
@@ -30,7 +48,7 @@
//
// May write up to 6 bytes, so make sure there's room in the
// buffer!
- DSOEXPORT std::string encodeUnicodeCharacter(boost::uint32_t
ucs_character);
+ std::string encodeUnicodeCharacter(boost::uint32_t ucs_character);
}
_______________________________________________
Gnash-commit mailing list
Gnash-commit@gnu.org
http://lists.gnu.org/mailman/listinfo/gnash-commit
