Removed TABs that had gotten in to the source

[wxWidgets.git] / src / common / encconv.cpp

diff --git a/src/common/encconv.cpp b/src/common/encconv.cpp
index 85acc2143a910b39bb6ef176393a4380377971b7..7a288485d40f66f4dec86d84b28d5b939cce904f 100644 (file)
--- a/src/common/encconv.cpp
+++ b/src/common/encconv.cpp
@@ -22,15 +22,24 @@
 
 #include <stdlib.h>
 
 
 #include <stdlib.h>
 

-#include "unictabl.inc" 
-// conversion tables, generated by scripts in $(WXWIN)/misc/unictabl
+// conversion tables, generated by scripts in $(WXWIN)/misc/unictabl:
+#ifdef __BORLANDC__
+#include "../common/unictabl.inc"
+#else
+#include "unictabl.inc"
+#endif

 
 

+#if wxUSE_WCHAR_T
+typedef wchar_t tchar;
+#else
+typedef char tchar;
+#endif

 
 

-static wxUint16 *GetEncTable(wxFontEncoding enc)
+static wxUint16* LINKAGEMODE GetEncTable(wxFontEncoding enc)

 {
     for (int i = 0; encodings_list[i].table != NULL; i++)
     {
 {
     for (int i = 0; encodings_list[i].table != NULL; i++)
     {

-        if (encodings_list[i].encoding == enc) 
+        if (encodings_list[i].encoding == enc)

             return encodings_list[i].table;
     }
     return NULL;
             return encodings_list[i].table;
     }
     return NULL;


@@ -43,21 +52,21 @@ typedef struct {
 
 
 
 
 
 

-static int CompareCharsetItems(const void *i1, const void *i2)
+static int LINKAGEMODE CompareCharsetItems(const void *i1, const void *i2)

 {
     return ( ((CharsetItem*)i1) -> u - ((CharsetItem*)i2) -> u );
 }
 
 
 {
     return ( ((CharsetItem*)i1) -> u - ((CharsetItem*)i2) -> u );
 }
 
 

-static CharsetItem* BuildReverseTable(wxUint16 *tbl)
+static CharsetItem* LINKAGEMODE BuildReverseTable(wxUint16 *tbl)

 {
     CharsetItem *rev = new CharsetItem[128];
 {
     CharsetItem *rev = new CharsetItem[128];

-    
+

     for (int i = 0; i < 128; i++)
         rev[i].c = 128 + i, rev[i].u = tbl[i];
 
     qsort(rev, 128, sizeof(CharsetItem), CompareCharsetItems);
     for (int i = 0; i < 128; i++)
         rev[i].c = 128 + i, rev[i].u = tbl[i];
 
     qsort(rev, 128, sizeof(CharsetItem), CompareCharsetItems);

-    
+

     return rev;
 }
 
     return rev;
 }
 


@@ -66,7 +75,7 @@ static CharsetItem* BuildReverseTable(wxUint16 *tbl)
 wxEncodingConverter::wxEncodingConverter()
 {
     m_Table = NULL;
 wxEncodingConverter::wxEncodingConverter()
 {
     m_Table = NULL;

-    m_UnicodeInput = FALSE;
+    m_UnicodeInput = m_UnicodeOutput = FALSE;

     m_JustCopy = FALSE;
 }
 
     m_JustCopy = FALSE;
 }
 


@@ -79,36 +88,37 @@ bool wxEncodingConverter::Init(wxFontEncoding input_enc, wxFontEncoding output_e
 
     if (m_Table) {delete[] m_Table; m_Table = NULL;}
 
 
     if (m_Table) {delete[] m_Table; m_Table = NULL;}
 

-#if !wxUSE_UNICODE
+#if !wxUSE_WCHAR_T

     if (input_enc == wxFONTENCODING_UNICODE || output_enc == wxFONTENCODING_UNICODE) return FALSE;
 #endif
 
     if (input_enc == output_enc) {m_JustCopy = TRUE; return TRUE;}
     if (input_enc == wxFONTENCODING_UNICODE || output_enc == wxFONTENCODING_UNICODE) return FALSE;
 #endif
 
     if (input_enc == output_enc) {m_JustCopy = TRUE; return TRUE;}

-    
+
+    m_UnicodeOutput = (output_enc == wxFONTENCODING_UNICODE);

     m_JustCopy = FALSE;
     m_JustCopy = FALSE;

-    
+

     if (input_enc == wxFONTENCODING_UNICODE)
     {
         if ((out_tbl = GetEncTable(output_enc)) == NULL) return FALSE;
 
     if (input_enc == wxFONTENCODING_UNICODE)
     {
         if ((out_tbl = GetEncTable(output_enc)) == NULL) return FALSE;
 

-        m_Table = new wxChar[65536];
-        for (i = 0; i < 128; i++)  m_Table[i] = (wxChar)i; // 7bit ASCII
-        for (i = 128; i < 65536; i++)  m_Table[i] = (wxChar)'?'; 
+        m_Table = new tchar[65536];
+        for (i = 0; i < 128; i++)  m_Table[i] = (tchar)i; // 7bit ASCII
+        for (i = 128; i < 65536; i++)  m_Table[i] = (tchar)'?';

                 // FIXME - this should be character that means `unicode to charset' impossible, not '?'
 
         if (method == wxCONVERT_SUBSTITUTE)
         {
             for (i = 0; i < encoding_unicode_fallback_count; i++)
                 // FIXME - this should be character that means `unicode to charset' impossible, not '?'
 
         if (method == wxCONVERT_SUBSTITUTE)
         {
             for (i = 0; i < encoding_unicode_fallback_count; i++)

-                m_Table[encoding_unicode_fallback[i].c] = (wxChar) encoding_unicode_fallback[i].s;
+                m_Table[encoding_unicode_fallback[i].c] = (tchar) encoding_unicode_fallback[i].s;

         }
 
         for (i = 0; i < 128; i++)
         }
 
         for (i = 0; i < 128; i++)

-            m_Table[out_tbl[i]] = (wxChar)(128 + i);
+            m_Table[out_tbl[i]] = (tchar)(128 + i);

 
         m_UnicodeInput = TRUE;
         return TRUE;
     }
 
         m_UnicodeInput = TRUE;
         return TRUE;
     }

-    
+

     else
     {
         if ((in_tbl = GetEncTable(input_enc)) == NULL) return FALSE;
     else
     {
         if ((in_tbl = GetEncTable(input_enc)) == NULL) return FALSE;


@@ -116,33 +126,38 @@ bool wxEncodingConverter::Init(wxFontEncoding input_enc, wxFontEncoding output_e
             if ((out_tbl = GetEncTable(output_enc)) == NULL) return FALSE;
 
         m_UnicodeInput = FALSE;
             if ((out_tbl = GetEncTable(output_enc)) == NULL) return FALSE;
 
         m_UnicodeInput = FALSE;

-        
-        m_Table = new wxChar[256];
-        for (i = 0; i < 128; i++)  m_Table[i] = (wxChar)i; // 7bit ASCII
-        
+
+        m_Table = new tchar[256];
+        for (i = 0; i < 128; i++)  m_Table[i] = (tchar)i; // 7bit ASCII
+

         if (output_enc == wxFONTENCODING_UNICODE)
         {
         if (output_enc == wxFONTENCODING_UNICODE)
         {

-            for (i = 0; i < 128; i++)  m_Table[128 + i] = (wxChar)in_tbl[i]; // wxChar is 2byte now
+            for (i = 0; i < 128; i++)  m_Table[128 + i] = (tchar)in_tbl[i];

             return TRUE;
         }
             return TRUE;
         }

-        else 
+        else

         {
             CharsetItem *rev = BuildReverseTable(out_tbl);
         {
             CharsetItem *rev = BuildReverseTable(out_tbl);

-            CharsetItem *item, key;
-            
-            for (i = 0; i < 128; i++)  
+            CharsetItem *item;
+            CharsetItem key;
+
+            for (i = 0; i < 128; i++)

             {
                 key.u = in_tbl[i];
                 item = (CharsetItem*) bsearch(&key, rev, 128, sizeof(CharsetItem), CompareCharsetItems);
                 if (item == NULL && method == wxCONVERT_SUBSTITUTE)
             {
                 key.u = in_tbl[i];
                 item = (CharsetItem*) bsearch(&key, rev, 128, sizeof(CharsetItem), CompareCharsetItems);
                 if (item == NULL && method == wxCONVERT_SUBSTITUTE)

-                    item = (CharsetItem*) bsearch(&key, encoding_unicode_fallback, 
+                    item = (CharsetItem*) bsearch(&key, encoding_unicode_fallback,

                                 encoding_unicode_fallback_count, sizeof(CharsetItem), CompareCharsetItems);
                 if (item)
                                 encoding_unicode_fallback_count, sizeof(CharsetItem), CompareCharsetItems);
                 if (item)

-                    m_Table[128 + i] = (wxChar)item -> c;
+                    m_Table[128 + i] = (tchar)item -> c;

                 else
                 else

-                    m_Table[128 + i] = 128 + i; // don't know => don't touch
+#if wxUSE_WCHAR_T
+                    m_Table[128 + i] = (wchar_t)(128 + i);
+#else
+                    m_Table[128 + i] = (char)(128 + i);
+#endif                                 

             }
             }

-            
+

             delete[] rev;
             return TRUE;
         }
             delete[] rev;
             return TRUE;
         }


@@ -150,39 +165,117 @@ bool wxEncodingConverter::Init(wxFontEncoding input_enc, wxFontEncoding output_e
 }
 
 
 }
 
 

-void wxEncodingConverter::Convert(const wxChar* input, wxChar* output)
+
+void wxEncodingConverter::Convert(const char* input, char* output)

 {
 {

+    wxASSERT_MSG(!m_UnicodeOutput, wxT("You cannot convert to unicode if output is const char*!"));
+    wxASSERT_MSG(!m_UnicodeInput, wxT("You cannot convert from unicode if input is const char*!"));
+
+    const char *i;
+    char *o;
+

     if (m_JustCopy)
     {
     if (m_JustCopy)
     {

-        wxStrcpy(output, input);
+        strcpy(output, input);

         return;
     }
         return;
     }

-    
+

     wxASSERT_MSG(m_Table != NULL, wxT("You must call wxEncodingConverter::Init() before actually converting!"));
     wxASSERT_MSG(m_Table != NULL, wxT("You must call wxEncodingConverter::Init() before actually converting!"));

-    
-    const wxChar *i;
-    wxChar *o;
-    
-    if (m_UnicodeInput)
-        for (i = input, o = output; *i != 0; i++, o++)
-            *o = (wxChar)(m_Table[(wxUint16)*i]);
-    else
-        for (i = input, o = output; *i != 0; i++, o++)
-            *o = (wxChar)(m_Table[(wxUint8)*i]);
+
+    for (i = input, o = output; *i != 0;)
+        *(o++) = (char)(m_Table[(wxUint8)*(i++)]);
+    *o = 0;
+}
+
+
+#if wxUSE_WCHAR_T
+
+void wxEncodingConverter::Convert(const char* input, wchar_t* output)
+{
+    wxASSERT_MSG(m_UnicodeOutput, wxT("You cannot convert to 8-bit if output is const wchar_t*!"));
+    wxASSERT_MSG(!m_UnicodeInput, wxT("You cannot convert from unicode if input is const char*!"));
+
+    const char *i;
+    wchar_t *o;
+
+    if (m_JustCopy)
+    {
+        for (i = input, o = output; *i != 0;)
+            *(o++) = (wchar_t)(*(i++));
+        *o = 0;
+        return;
+    }
+
+    wxASSERT_MSG(m_Table != NULL, wxT("You must call wxEncodingConverter::Init() before actually converting!"));
+
+    for (i = input, o = output; *i != 0;)
+        *(o++) = (wchar_t)(m_Table[(wxUint8)*(i++)]);
+    *o = 0;
+}
+
+
+
+void wxEncodingConverter::Convert(const wchar_t* input, char* output)
+{
+    wxASSERT_MSG(!m_UnicodeOutput, wxT("You cannot convert to unicode if output is const char*!"));
+    wxASSERT_MSG(m_UnicodeInput, wxT("You cannot convert from 8-bit if input is const wchar_t*!"));
+
+    const wchar_t *i;
+    char *o;
+
+    if (m_JustCopy)
+    {
+        for (i = input, o = output; *i != 0;)
+            *(o++) = (char)(*(i++));
+        *o = 0;
+        return;
+    }
+
+    wxASSERT_MSG(m_Table != NULL, wxT("You must call wxEncodingConverter::Init() before actually converting!"));
+
+    for (i = input, o = output; *i != 0;)
+        *(o++) = (char)(m_Table[(wxUint16)*(i++)]);

     *o = 0;
 }
 
 
 
     *o = 0;
 }
 
 
 

+void wxEncodingConverter::Convert(const wchar_t* input, wchar_t* output)
+{
+    wxASSERT_MSG(m_UnicodeOutput, wxT("You cannot convert to 8-bit if output is const wchar_t*!"));
+    wxASSERT_MSG(m_UnicodeInput, wxT("You cannot convert from 8-bit if input is const wchar_t*!"));
+
+    const wchar_t *i;
+    wchar_t *o;
+
+    if (m_JustCopy)
+    {
+        // wcscpy() is not guaranteed to exist
+        for (i = input, o = output; *i != 0;)
+            *(o++) = (*(i++));
+        *o = 0;
+        return;
+    }
+
+    wxASSERT_MSG(m_Table != NULL, wxT("You must call wxEncodingConverter::Init() before actually converting!"));
+
+    for (i = input, o = output; *i != 0;)
+        *(o++) = (wchar_t)(m_Table[(wxUint8)*(i++)]);
+    *o = 0;
+}
+
+#endif // wxUSE_WCHAR_T
+
+

 wxString wxEncodingConverter::Convert(const wxString& input)
 {
     if (m_JustCopy) return input;
 wxString wxEncodingConverter::Convert(const wxString& input)
 {
     if (m_JustCopy) return input;

-    
+

     wxString s;
     const wxChar *i;
     wxString s;
     const wxChar *i;

-    
+

     wxASSERT_MSG(m_Table != NULL, wxT("You must call wxEncodingConverter::Init() before actually converting!"));
     wxASSERT_MSG(m_Table != NULL, wxT("You must call wxEncodingConverter::Init() before actually converting!"));

-    
+

     if (m_UnicodeInput)
         for (i = input.c_str(); *i != 0; i++)
             s << (wxChar)(m_Table[(wxUint16)*i]);
     if (m_UnicodeInput)
         for (i = input.c_str(); *i != 0; i++)
             s << (wxChar)(m_Table[(wxUint16)*i]);


@@ -195,33 +288,86 @@ wxString wxEncodingConverter::Convert(const wxString& input)
 
 
 
 
 
 

+
+
+

 // Following tables describe classes of encoding equivalence.
 // Following tables describe classes of encoding equivalence.

-// 
+//

 
 #define STOP wxFONTENCODING_SYSTEM
 
 #define NUM_OF_PLATFORMS  4 /*must conform to enum wxPLATFORM_XXXX !!!*/
 
 #define STOP wxFONTENCODING_SYSTEM
 
 #define NUM_OF_PLATFORMS  4 /*must conform to enum wxPLATFORM_XXXX !!!*/

-#define ENC_PER_PLATFORM  3
+#define ENC_PER_PLATFORM  5

            // max no. of encodings for one language used on one platform
            // max no. of encodings for one language used on one platform

-           // Anybody thinks 3 is not enough? ;-)
+           // Anybody thinks 5 is not enough? ;-)

 
 

-static wxFontEncoding 
+static wxFontEncoding

     EquivalentEncodings[][NUM_OF_PLATFORMS][ENC_PER_PLATFORM+1] = {
 
     EquivalentEncodings[][NUM_OF_PLATFORMS][ENC_PER_PLATFORM+1] = {
 

-    // West European (Latin1)
+    // *** Please put more common encodings as first! ***
+
+    // Western European

     {
         /* unix    */ {wxFONTENCODING_ISO8859_1, wxFONTENCODING_ISO8859_15, STOP},
         /* windows */ {wxFONTENCODING_CP1252, STOP},
         /* os2     */ {STOP},
     {
         /* unix    */ {wxFONTENCODING_ISO8859_1, wxFONTENCODING_ISO8859_15, STOP},
         /* windows */ {wxFONTENCODING_CP1252, STOP},
         /* os2     */ {STOP},

-        /* mac     */ {STOP}   
+        /* mac     */ {STOP}

     },
 
     },
 

-    // Central European (Latin2)
+    // Central European

     {
         /* unix    */ {wxFONTENCODING_ISO8859_2, STOP},
         /* windows */ {wxFONTENCODING_CP1250, STOP},
         /* os2     */ {STOP},
     {
         /* unix    */ {wxFONTENCODING_ISO8859_2, STOP},
         /* windows */ {wxFONTENCODING_CP1250, STOP},
         /* os2     */ {STOP},

-        /* mac     */ {STOP}   
+        /* mac     */ {STOP}
+    },
+
+    // Baltic
+    {
+        /* unix    */ {wxFONTENCODING_ISO8859_13, wxFONTENCODING_ISO8859_4, STOP},
+        /* windows */ {wxFONTENCODING_CP1257, STOP},
+        /* os2     */ {STOP},
+        /* mac     */ {STOP}
+    },
+
+    // Hebrew
+    {
+        /* unix    */ {wxFONTENCODING_ISO8859_8, STOP},
+        /* windows */ {wxFONTENCODING_CP1255, STOP},
+        /* os2     */ {STOP},
+        /* mac     */ {STOP}
+    },
+
+    // Greek
+    {
+        /* unix    */ {wxFONTENCODING_ISO8859_7, STOP},
+        /* windows */ {wxFONTENCODING_CP1253, STOP},
+        /* os2     */ {STOP},
+        /* mac     */ {STOP}
+    },
+
+    // Arabic
+    {
+        /* unix    */ {wxFONTENCODING_ISO8859_6, STOP},
+        /* windows */ {wxFONTENCODING_CP1256, STOP},
+        /* os2     */ {STOP},
+        /* mac     */ {STOP}
+    },
+
+    // Turkish
+    {
+        /* unix    */ {wxFONTENCODING_ISO8859_9, STOP},
+        /* windows */ {wxFONTENCODING_CP1254, STOP},
+        /* os2     */ {STOP},
+        /* mac     */ {STOP}
+    },
+
+    // Cyrillic
+    {
+        /* unix    */ {wxFONTENCODING_KOI8, wxFONTENCODING_ISO8859_5, STOP},
+        /* windows */ {wxFONTENCODING_CP1251, STOP},
+        /* os2     */ {STOP},
+        /* mac     */ {STOP}

     },
 
     {{STOP},{STOP},{STOP},{STOP}} /* Terminator */
     },
 
     {{STOP},{STOP},{STOP},{STOP}} /* Terminator */


@@ -245,7 +391,7 @@ wxFontEncodingArray wxEncodingConverter::GetPlatformEquivalents(wxFontEncoding e
         platform = wxPLATFORM_MAC;
 #endif
     }
         platform = wxPLATFORM_MAC;
 #endif
     }

-    
+

     int i, clas, e ;
     wxFontEncoding *f;
     wxFontEncodingArray arr;
     int i, clas, e ;
     wxFontEncoding *f;
     wxFontEncodingArray arr;


@@ -257,13 +403,15 @@ wxFontEncodingArray wxEncodingConverter::GetPlatformEquivalents(wxFontEncoding e
             for (e = 0; EquivalentEncodings[clas][i][e] != STOP; e++)
                 if (EquivalentEncodings[clas][i][e] == enc)
                 {
             for (e = 0; EquivalentEncodings[clas][i][e] != STOP; e++)
                 if (EquivalentEncodings[clas][i][e] == enc)
                 {

-                    for (f = EquivalentEncodings[clas][platform]; *f != STOP; f++) 
+                    for (f = EquivalentEncodings[clas][platform]; *f != STOP; f++)
+                        if (*f == enc) arr.Add(enc);
+                    for (f = EquivalentEncodings[clas][platform]; *f != STOP; f++)

                         if (arr.Index(*f) == wxNOT_FOUND) arr.Add(*f);
                         if (arr.Index(*f) == wxNOT_FOUND) arr.Add(*f);

-                    i = NUM_OF_PLATFORMS/*hack*/; break; 
+                    i = NUM_OF_PLATFORMS/*hack*/; break;

                 }
         clas++;
     }
                 }
         clas++;
     }

-    
+

     return arr;
 }
 
     return arr;
 }
 


@@ -275,6 +423,8 @@ wxFontEncodingArray wxEncodingConverter::GetAllEquivalents(wxFontEncoding enc)
     wxFontEncoding *f;
     wxFontEncodingArray arr;
 
     wxFontEncoding *f;
     wxFontEncodingArray arr;
 

+    arr = GetPlatformEquivalents(enc); // we want them to be first items in array
+

     clas = 0;
     while (EquivalentEncodings[clas][0][0] != STOP)
     {
     clas = 0;
     while (EquivalentEncodings[clas][0][0] != STOP)
     {


@@ -283,12 +433,12 @@ wxFontEncodingArray wxEncodingConverter::GetAllEquivalents(wxFontEncoding enc)
                 if (EquivalentEncodings[clas][i][e] == enc)
                 {
                     for (j = 0; j < NUM_OF_PLATFORMS; j++)
                 if (EquivalentEncodings[clas][i][e] == enc)
                 {
                     for (j = 0; j < NUM_OF_PLATFORMS; j++)

-                        for (f = EquivalentEncodings[clas][j]; *f != STOP; f++) 
-                            if (arr.Index(*f) == wxNOT_FOUND) arr.Add(*f);                            
-                    i = NUM_OF_PLATFORMS/*hack*/; break; 
+                        for (f = EquivalentEncodings[clas][j]; *f != STOP; f++)
+                            if (arr.Index(*f) == wxNOT_FOUND) arr.Add(*f);
+                    i = NUM_OF_PLATFORMS/*hack*/; break;

                 }
         clas++;
     }
                 }
         clas++;
     }

-    
+

     return arr;
 }
     return arr;
 }