Add binary and character literals in CBOT

po/colobot.pot

@@ -1795,6 +1795,9 @@ msgstr ""
 msgid "Invalid universal character name"
 msgstr ""
 
+msgid "Empty character constant"
+msgstr ""
+
 msgid "Dividing by zero"
 msgstr ""
 

po/cs.po

@@ -507,6 +507,9 @@ msgstr "Upravit vybraný program"
 msgid "Egg"
 msgstr "Vejce"
 
+msgid "Empty character constant"
+msgstr ""
+
 msgid "End of block missing"
 msgstr "Chybí konec bloku"
 

po/de.po

@@ -508,6 +508,9 @@ msgstr "Gewähltes Programm bearbeiten"
 msgid "Egg"
 msgstr "Ei"
 
+msgid "Empty character constant"
+msgstr ""
+
 msgid "End of block missing"
 msgstr "Es fehlt eine geschlossene geschweifte Klammer \"}\" (Ende des Blocks)"
 

po/fr.po

@@ -510,6 +510,9 @@ msgstr "Éditer le programme sélectionné"
 msgid "Egg"
 msgstr "Oeuf"
 
+msgid "Empty character constant"
+msgstr ""
+
 msgid "End of block missing"
 msgstr "Il manque la fin du bloc"
 

po/pl.po

@@ -506,6 +506,9 @@ msgstr "Edytuj zaznaczony program"
 msgid "Egg"
 msgstr "Jajo"
 
+msgid "Empty character constant"
+msgstr ""
+
 msgid "End of block missing"
 msgstr "Brak końca bloku"
 

po/pt.po

@@ -505,6 +505,9 @@ msgstr "Alterar o programa selecionado"
 msgid "Egg"
 msgstr "Ovo"
 
+msgid "Empty character constant"
+msgstr ""
+
 msgid "End of block missing"
 msgstr "Fim do bloco ausente"
 

po/ru.po

@@ -514,6 +514,9 @@ msgstr "Изменить выбранную программу"
 msgid "Egg"
 msgstr "Яйцо"
 
+msgid "Empty character constant"
+msgstr ""
+
 msgid "End of block missing"
 msgstr "Отсутствует конец блока"
 

src/CBot/CBotEnums.h

@@ -182,7 +182,8 @@ enum TokenType
     TokenTypNum = 2,     //!< number
     TokenTypString = 3,  //!< string
     TokenTypVar = 4,     //!< a variable name
-    TokenTypDef = 5      //!< value according DefineNum
+    TokenTypDef = 5,     //!< value according DefineNum
+    TokenTypChar = 6,    //!< character literal
 };
 
 /**
@@ -252,6 +253,7 @@ enum CBotError : int
     CBotErrHexDigits     = 5052, //!< missing hex digits after escape sequence
     CBotErrHexRange      = 5053, //!< hex value out of range
     CBotErrUnicodeName   = 5054, //!< invalid universal character name
+    CBotErrCharEmpty     = 5055, //!< empty character constant
 
     // Runtime errors
     CBotErrZeroDiv       = 6000, //!< division by zero

src/CBot/CBotInstr/CBotExprLitChar.cpp

@@ -0,0 +1,151 @@
+/*
+ * This file is part of the Colobot: Gold Edition source code
+ * Copyright (C) 2001-2018, Daniel Roux, EPSITEC SA & TerranovaTeam
+ * http://epsitec.ch; http://colobot.info; http://github.com/colobot
+ *
+ * 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, see http://gnu.org/licenses
+ */
+
+#include "CBot/CBotInstr/CBotExprLitChar.h"
+
+#include "CBot/CBotStack.h"
+#include "CBot/CBotCStack.h"
+
+#include "CBot/CBotVar/CBotVar.h"
+
+namespace CBot
+{
+
+CBotExprLitChar::CBotExprLitChar()
+{
+}
+
+CBotExprLitChar::~CBotExprLitChar()
+{
+}
+
+CBotInstr* CBotExprLitChar::Compile(CBotToken* &p, CBotCStack* pStack)
+{
+    CBotCStack* pStk = pStack->TokenStack();
+
+    const auto& s = p->GetString();
+
+    auto it = s.cbegin();
+    if (++it != s.cend())
+    {
+        if (*it != '\'') // not empty quotes ?
+        {
+            uint32_t valchar = 0;
+            int pos = p->GetStart() + 1;
+
+            if (*it != '\\') valchar = *(it++); // not escape sequence ?
+            else if (++it != s.cend())
+            {
+                pStk->SetStartError(pos++);
+                unsigned char c = *(it++);
+                if (c == '\"' || c == '\'' || c == '\\') valchar = c;
+                else if (c == 'a') valchar = '\a'; // alert bell
+                else if (c == 'b') valchar = '\b'; // backspace
+                else if (c == 'f') valchar = '\f'; // form feed
+                else if (c == 'n') valchar = '\n'; // new line
+                else if (c == 'r') valchar = '\r'; // carriage return
+                else if (c == 't') valchar = '\t'; // horizontal tab
+                else if (c == 'v') valchar = '\v'; // vertical tab
+                else if (c == 'u' || c == 'U') // unicode escape
+                {
+                    if (it != s.cend())
+                    {
+                        std::string hex = "";
+                        size_t maxlen = (c == 'u') ? 4 : 8;
+
+                        for (size_t i = 0; i < maxlen; i++)
+                        {
+                            if (!CharInList(*it, "0123456789ABCDEFabcdef")) break;
+                            ++pos;
+                            hex += *it;
+                            if (++it == s.cend()) break;
+                        }
+
+                        if (maxlen == hex.length()) // unicode character
+                        {
+                            try
+                            {
+                                valchar = std::stoi(hex, nullptr, 16);
+                                if (0x10FFFF < valchar || (0xD7FF < valchar && valchar < 0xE000))
+                                    pStk->SetError(CBotErrUnicodeName, pos + 1);
+                            }
+                            catch (const std::out_of_range& e)
+                            {
+                                pStk->SetError(CBotErrHexRange, pos + 1);
+                            }
+                        }
+                        else
+                            pStk->SetError(CBotErrHexDigits, pos + 1);
+                    }
+                    else
+                        pStk->SetError(CBotErrHexDigits, pos + 1);
+                }
+                else
+                    pStk->SetError(CBotErrBadEscape, pos + 1);
+            }
+
+            if (it == s.cend() || *it != '\'')
+                pStk->SetError(CBotErrEndQuote, p);
+
+            if (pStk->IsOk())
+            {
+                CBotExprLitChar* inst = new CBotExprLitChar();
+                inst->m_valchar = valchar;
+                inst->SetToken(p);
+                p = p->GetNext();
+
+                CBotVar* var = CBotVar::Create("", CBotTypChar);
+                pStk->SetVar(var);
+
+                return pStack->Return(inst, pStk);
+            }
+        }
+        pStk->SetError(CBotErrCharEmpty, p);
+    }
+
+    pStk->SetError(CBotErrEndQuote, p);
+    return pStack->Return(nullptr, pStk);
+}
+
+bool CBotExprLitChar::Execute(CBotStack* &pj)
+{
+    CBotStack*    pile = pj->AddStack(this);
+
+    if (pile->IfStep()) return false;
+
+    CBotVar* var = CBotVar::Create("", CBotTypChar);
+
+    var->SetValChar(m_valchar);
+
+    pile->SetVar(var);
+
+    return pj->Return(pile);
+}
+
+void CBotExprLitChar::RestoreState(CBotStack* &pj, bool bMain)
+{
+    if (bMain) pj->RestoreStack(this);
+}
+
+std::string CBotExprLitChar::GetDebugData()
+{
+    return m_token.GetString();
+}
+
+} // namespace CBot

src/CBot/CBotInstr/CBotExprLitChar.h

@@ -0,0 +1,60 @@
+/*
+ * This file is part of the Colobot: Gold Edition source code
+ * Copyright (C) 2001-2018, Daniel Roux, EPSITEC SA & TerranovaTeam
+ * http://epsitec.ch; http://colobot.info; http://github.com/colobot
+ *
+ * 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, see http://gnu.org/licenses
+ */
+
+#pragma once
+
+#include "CBot/CBotInstr/CBotInstr.h"
+
+namespace CBot
+{
+
+/**
+ * \brief A character literal
+ * \verbatim 'a', '\n', '\t', '\uFFFD', '\U0000FFFD', etc. \endverbatim
+ */
+class CBotExprLitChar : public CBotInstr
+{
+public:
+    CBotExprLitChar();
+    ~CBotExprLitChar();
+
+    /*!
+     * \brief Compile a character literal
+     */
+    static CBotInstr* Compile(CBotToken* &p, CBotCStack* pStack);
+
+    /*!
+     * \brief Execute, returns the corresponding char.
+     */
+    bool Execute(CBotStack* &pj) override;
+
+    /*!
+     * \brief RestoreState
+     */
+    void RestoreState(CBotStack* &pj, bool bMain) override;
+
+protected:
+    virtual const std::string GetDebugName() override { return "CBotExprLitChar"; }
+    virtual std::string GetDebugData() override;
+
+private:
+    uint32_t m_valchar = 0;
+};
+
+} // namespace CBot

src/CBot/CBotInstr/CBotExprLitString.cpp

@@ -42,7 +42,7 @@ CBotInstr* CBotExprLitString::Compile(CBotToken* &p, CBotCStack* pStack)
 {
     CBotCStack* pStk = pStack->TokenStack();
 
-    std::string s = p->GetString();
+    const auto& s = p->GetString();
 
     auto it = s.cbegin();
     if (++it != s.cend())
@@ -51,7 +51,7 @@ CBotInstr* CBotExprLitString::Compile(CBotToken* &p, CBotCStack* pStack)
         std::string valstring = "";
         while (it != s.cend() && *it != '\"')
         {
-            pStk->SetStartError(++pos);
+            ++pos;
             if (*it != '\\') // not escape sequence ?
             {
                 valstring += *(it++);
@@ -59,6 +59,7 @@ CBotInstr* CBotExprLitString::Compile(CBotToken* &p, CBotCStack* pStack)
             }
 
             if (++it == s.cend()) break;
+            pStk->SetStartError(pos);
 
             if (CharInList(*it, "01234567"))          // octal
             {

src/CBot/CBotInstr/CBotParExpr.cpp

@@ -21,6 +21,7 @@
 
 #include "CBot/CBotInstr/CBotExpression.h"
 #include "CBot/CBotInstr/CBotExprLitBool.h"
+#include "CBot/CBotInstr/CBotExprLitChar.h"
 #include "CBot/CBotInstr/CBotExprLitNan.h"
 #include "CBot/CBotInstr/CBotExprLitNull.h"
 #include "CBot/CBotInstr/CBotExprLitNum.h"
@@ -169,6 +170,13 @@ CBotInstr* CBotParExpr::CompileLitExpr(CBotToken* &p, CBotCStack* pStack)
         return pStack->Return(inst, pStk);
     }
 
+    // is this a character?
+    if (p->GetType() == TokenTypChar)
+    {
+        CBotInstr* inst = CBotExprLitChar::Compile(p, pStk);
+        return pStack->Return(inst, pStk);
+    }
+
     // is this a chaine?
     if (p->GetType() == TokenTypString)
     {

src/CBot/CBotToken.cpp

@@ -304,12 +304,53 @@ CBotToken*  CBotToken::NextToken(const char*& program, bool first)
             stop = true;
         }
 
+        // special case for characters
+        if (token[0] == '\'')
+        {
+            if (c == '\\')       // escape sequence
+            {
+                token += c;
+                c = *(program++);
+
+                if (c == 'u' || c == 'U') // unicode escape
+                {
+                    int maxlen = (c == 'u') ? 4 : 8;
+                    token += c;
+                    c = *(program++);
+                    for (int i = 0; i < maxlen; i++)
+                    {
+                        if (c == 0 || !CharInList(c, hexnum)) break;
+                        token += c;
+                        c = *(program++);
+                    }
+                }
+                else if (c != 0 && !CharInList(c, nch)) // other escape char
+                {
+                    token += c;
+                    c = *(program++);
+                }
+            }
+            else if (c != 0 && c != '\'' && !CharInList(c, nch)) // single character
+            {
+                token += c;
+                c = *(program++);
+            }
+
+            if (c == '\'') // close quote
+            {
+                token += c;
+                c = *(program++);
+            }
+            stop = true;
+        }
+
         // special case for numbers
         if ( CharInList(token[0], num ))
         {
             bool    bdot = false;   // found a point?
             bool    bexp = false;   // found an exponent?
 
+            char    bin[] = "01";
             char*   liste = num;
             if (token[0] == '0' && c == 'x')          // hexadecimal value?
             {
@@ -317,6 +358,12 @@ CBotToken*  CBotToken::NextToken(const char*& program, bool first)
                 c   = *(program++);                 // next character
                 liste = hexnum;
             }
+            else if (token[0] == '0' && c == 'b')   // binary literal
+            {
+                liste = bin;
+                token += c;
+                c = *(program++);
+            }
 cw:
             while (c != 0 && CharInList(c, liste))
             {
@@ -399,6 +446,7 @@ bis:
 
             if (CharInList(token[0], num )) t->m_type = TokenTypNum;
             if (token[0] == '\"') t->m_type = TokenTypString;
+            if (token[0] == '\'') t->m_type = TokenTypChar;
             if (first) t->m_type = TokenTypNone;
 
             t->m_keywordId = GetKeyWord(token);

src/CBot/CBotUtils.cpp

@@ -155,6 +155,18 @@ long GetNumInt(const std::string& str)
             break;
         }
     }
+    else if (*p == 'b')
+    {
+        while (*++p != 0)
+        {
+            if (*p == '0' || *p == '1')
+            {
+                num = (num << 1) + *p - '0';
+                continue;
+            }
+            break;
+        }
+    }
     return num;
 }
 

src/CBot/CMakeLists.txt

@@ -44,6 +44,8 @@ set(SOURCES
     CBotInstr/CBotEmpty.h
     CBotInstr/CBotExprLitBool.cpp
     CBotInstr/CBotExprLitBool.h
+    CBotInstr/CBotExprLitChar.cpp
+    CBotInstr/CBotExprLitChar.h
     CBotInstr/CBotExprLitNan.cpp
     CBotInstr/CBotExprLitNan.h
     CBotInstr/CBotExprLitNull.cpp

src/common/restext.cpp

@@ -742,6 +742,7 @@ void InitializeRestext()
     stringsCbot[CBot::CBotErrHexDigits]     = TR("Missing hex digits after escape sequence");
     stringsCbot[CBot::CBotErrHexRange]      = TR("Hex value out of range");
     stringsCbot[CBot::CBotErrUnicodeName]   = TR("Invalid universal character name");
+    stringsCbot[CBot::CBotErrCharEmpty]     = TR("Empty character constant");
 
     stringsCbot[CBot::CBotErrZeroDiv]       = TR("Dividing by zero");
     stringsCbot[CBot::CBotErrNotInit]       = TR("Variable not initialized");

src/script/script.cpp

@@ -589,16 +589,17 @@ void CScript::UpdateList(Ui::CList* list)
     list->SetState(Ui::STATE_ENABLE);
 }
 
-// Colorize a string literal with escape sequences also colored
+// Colorize a string or character literal with escape sequences also colored
 
 static void HighlightString(Ui::CEdit* edit, const std::string& s, int start)
 {
     edit->SetFormat(start, start + 1, Gfx::FONT_HIGHLIGHT_STRING);
 
-    auto it = s.cbegin() + 1;
+    auto it = s.cbegin();
+    char endQuote = *(it++);
 
     ++start;
-    while (it != s.cend() && *it != '\"')
+    while (it != s.cend() && *it != endQuote)
     {
         if (*(it++) != '\\') // not escape sequence
         {
@@ -697,7 +698,7 @@ void CScript::ColorizeScript(Ui::CEdit* edit, int rangeStart, int rangeEnd)
         {
             color = Gfx::FONT_HIGHLIGHT_STRING;
         }
-        else if (type == CBot::TokenTypString) // string literals
+        else if (type == CBot::TokenTypString || type == CBot::TokenTypChar) // string literals and character literals
         {
             HighlightString(edit, token, cursor1);
             bt = bt->GetNext();

test/unit/CBot/CBot_test.cpp

@@ -619,6 +619,27 @@ TEST_F(CBotUT, IntegerMathNearLimits_Issue993)
     );
 }
 
+TEST_F(CBotUT, BinaryLiterals)
+{
+    ExecuteTest(
+        "extern void TestBinaryLiterals() {\n"
+        "    ASSERT(  8 ==   0b00001000);\n"
+        "    ASSERT( 12 ==   0b00001100);\n"
+        "    ASSERT( 16 ==   0b00010000);\n"
+        "    ASSERT( 24 ==   0b00011000);\n"
+        "    ASSERT( 32 ==   0b00100000);\n"
+        "    ASSERT( 48 ==   0b00110000);\n"
+        "    ASSERT( 64 ==   0b01000000);\n"
+        "    ASSERT( 96 ==   0b01100000);\n"
+        "    ASSERT(128 ==   0b10000000);\n"
+        "    ASSERT(192 ==   0b11000000);\n"
+        "    ASSERT(256 ==  0b100000000);\n"
+        "    ASSERT(384 ==  0b110000000);\n"
+        "    ASSERT(512 == 0b1000000000);\n"
+        "}\n"
+    );
+}
+
 TEST_F(CBotUT, ToString)
 {
     ExecuteTest(
@@ -1752,6 +1773,107 @@ TEST_F(CBotUT, StringFunctions)
     );
 }
 
+TEST_F(CBotUT, LiteralCharacters)
+{
+    ExecuteTest(
+        "extern void TestCharValue()\n"
+        "{\n"
+        "    ASSERT('A' == 65);\n"
+        "    ASSERT('B' == 66);\n"
+        "    ASSERT('C' == 67);\n"
+        "    ASSERT('\\a' == 0x07);\n"
+        "    ASSERT('\\b' == 0x08);\n"
+        "    ASSERT('\\t' == 0x09);\n"
+        "    ASSERT('\\n' == 0x0A);\n"
+        "    ASSERT('\\v' == 0x0B);\n"
+        "    ASSERT('\\f' == 0x0C);\n"
+        "    ASSERT('\\r' == 0x0D);\n"
+        "    ASSERT('\\\"' == 0x22);\n"
+        "    ASSERT('\\\'' == 0x27);\n"
+        "    ASSERT('\\\\' == 0x5C);\n"
+        "}\n"
+        "extern void TestCharUnicodeEscape()\n"
+        "{\n"
+        "    ASSERT('\\u0007' == '\\a');\n"
+        "    ASSERT('\\u0008' == '\\b');\n"
+        "    ASSERT('\\u0009' == '\\t');\n"
+        "    ASSERT('\\u000A' == '\\n');\n"
+        "    ASSERT('\\u000B' == '\\v');\n"
+        "    ASSERT('\\u000C' == '\\f');\n"
+        "    ASSERT('\\u000D' == '\\r');\n"
+        "    ASSERT('\\u0022' == '\\\"');\n"
+        "    ASSERT('\\u0027' == '\\\'');\n"
+        "    ASSERT('\\u005C' == '\\\\');\n"
+        "}\n"
+        "extern void AssignCharToString_ToUTF_8()\n"
+        "{\n"
+        "    string test = '\\u00A9';\n"
+        "    test += '\\u00AE';\n"
+        "    ASSERT(test == \"\\xC2\\xA9\\xC2\\xAE\");\n"
+        "}\n"
+        "extern void AddCharToString_ToUTF_8()\n"
+        "{\n"
+        "    ASSERT(\"\" + 'A' + 'B' + 'C' == \"ABC\");\n"
+        "    ASSERT(\"\" + '\\u00A9' == \"\\xC2\\xA9\");\n"
+        "    ASSERT(\"\" + '\\u00AE' == \"\\xC2\\xAE\");\n"
+        "    ASSERT(\"\" + '\\u262E' == \"\\xE2\\x98\\xAE\");\n"
+        "    ASSERT(\"\" + '\\u262F' == \"\\xE2\\x98\\xAF\");\n"
+        "    ASSERT(\"\" + '\\U0001F60E' == \"\\xF0\\x9F\\x98\\x8E\");\n"
+        "    ASSERT(\"\" + '\\U0001F61C' == \"\\xF0\\x9F\\x98\\x9C\");\n"
+        "    ASSERT(\"\" + '\\U0001F6E0' == \"\\xF0\\x9F\\x9B\\xA0\");\n"
+        "    ASSERT(\"\" + '\\U0010FFFF' == \"\\xF4\\x8F\\xBF\\xBF\");\n"
+        "}\n"
+    );
+
+    ExecuteTest(
+        "extern void MissingEndQuote()\n"
+        "{\n"
+        "    '\n"
+        "}\n",
+        CBotErrEndQuote
+    );
+
+    ExecuteTest(
+        "extern void MissingEndQuote()\n"
+        "{\n"
+        "    'a\n"
+        "}\n",
+        CBotErrEndQuote
+    );
+
+    ExecuteTest(
+        "extern void EmptyQuotes()\n"
+        "{\n"
+        "    '';\n"
+        "}\n",
+        CBotErrCharEmpty
+    );
+
+    ExecuteTest(
+        "extern void UnknownEscapeSequence()\n"
+        "{\n"
+        "    '\\p';\n"
+        "}\n",
+        CBotErrBadEscape
+    );
+
+    ExecuteTest(
+        "extern void MissingHexDigits()\n"
+        "{\n"
+        "    '\\u';\n"
+        "}\n",
+        CBotErrHexDigits
+    );
+
+    ExecuteTest(
+        "extern void BadUnicodeCharacterName()\n"
+        "{\n"
+        "    '\\U00110000';\n"
+        "}\n",
+        CBotErrUnicodeName
+    );
+}
+
 TEST_F(CBotUT, TestNANParam_Issue642)
 {
     ExecuteTest(