[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[Lost] [Patch] UTF8-Unterstützung in vterm
+ vterm: UTF8-Unterstuetzung bei der Ausgabe
Index: src/modules/vterm/output.c
===================================================================
--- src/modules/vterm/output.c (Revision 767)
+++ src/modules/vterm/output.c (Arbeitskopie)
@@ -151,9 +151,16 @@
void vterm_process_output(vterminal_t* vterm, char* data, size_t length)
{
vterm_output_t* out = &(vterm->output);
+ char cpdata[length + vterm->utf8_buffer_offset];
+ int len;
+ if ((len = utf8_to_cp437(vterm, data, length, cpdata)) == 0) {
+ return;
+ }
+
// Ausgaben durch vt100-Emulation taetigen
- vt100_process_output(vterm, data, length);
+ vt100_process_output(vterm, cpdata, len);
+ free(cpdata);
// Anzeige aktualisieren falls es sich um aenderungen auf dem aktiven
// Terminal handelt.
Index: src/modules/vterm/vterm.h
===================================================================
--- src/modules/vterm/vterm.h (Revision 767)
+++ src/modules/vterm/vterm.h (Arbeitskopie)
@@ -151,6 +151,12 @@
/// Anzahl der Zeichen im vt100-Puffer
size_t vt100_buffer_offset;
+
+ /// UTF-8 Puffer
+ char utf8_buffer[4];
+
+ /// Anzahl der Zeichen im utf-8 Puffer
+ size_t utf8_buffer_offset;
} vterminal_t;
@@ -204,3 +210,6 @@
/// Ausgabe in vt100-Emulation verarbeiten
void vt100_process_output(vterminal_t* vterm, char* data, size_t length);
+/// UTF8-String in Codepage437-String verwandeln
+int utf8_to_cp437(vterminal_t* vterm, const char* str, size_t len, char* buf);
+
Index: src/modules/vterm/utf8.c
===================================================================
--- src/modules/vterm/utf8.c (Revision 0)
+++ src/modules/vterm/utf8.c (Revision 0)
@@ -0,0 +1,140 @@
+/*
+ * Copyright (c) 2007 The LOST Project. All rights reserved.
+ *
+ * This code is derived from software contributed to the LOST Project
+ * by Antoine Kaufmann.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * 3. All advertising materials mentioning features or use of this software
+ * must display the following acknowledgement:
+ * This product includes software developed by the LOST Project
+ * and its contributors.
+ * 4. Neither the name of the LOST Project nor the names of its
+ * contributors may be used to endorse or promote products derived
+ * from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * ``AS IS'' AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
+ * TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
+ * PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDERS OR
+ * CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
+ * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
+ * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS;
+ * OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+ * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
+ * OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
+ * ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <stddef.h>
+#include <stdlib.h>
+#include <string.h>
+#include "vterm.h"
+
+/**
+ * Zeichentabelle um Unicode-Zeichen in CP437 zu ersetzen
+ */
+struct {
+ wchar_t uc;
+ char cp;
+} uc_to_cp [] = {
+ {L'ä', 0x84}, // ä
+ {L'ö', 0x94}, // ö
+ {L'ü', 0x81}, // ü
+ {L'Ä', 0x8E}, // Ä
+ {L'Ö', 0x99}, // Ö
+ {L'Ü', 0x9A}, // Ü
+ {L'ß', 0xE1}, // ß
+
+ {L'«', 0xAE}, // «
+ {L'»', 0xAF}, // »
+};
+
+/**
+ * Unicode-Zeichen in der Tabelle nachschlagen und in cp437 umwandeln
+ *
+ * @param wc Unicode-Zeichen
+ *
+ * @return cp437-Zeichen oder 0 wenn keines gefunden wurde
+ */
+static char to_cp437(wchar_t wc)
+{
+ int i;
+
+ // ASCII
+ if (wc <= 0x7F) {
+ return (char) wc;
+ }
+
+ // Tabelle durchsuchen
+ for (i = 0; i < sizeof(uc_to_cp) / sizeof(uc_to_cp[0]); i++) {
+ if (wc == uc_to_cp[i].uc) {
+ return uc_to_cp[i].cp;
+ }
+ }
+ return 0x00;
+}
+
+/**
+ * Wandelt das Zeichen in cp437 um oder legt es in den utf8 Buffer, falls es
+ * ein Teil eines Zeichens ist, das mehrere Bytes belegt
+ *
+ * @param c Das Zeichen
+ * @param dest Pointer auf die Speicherstelle in der das cp437-Zeichen
+ * abgelegt wird
+ *
+ * @return TRUE wenn das Zeichen umgewandelt wurde, FALSE sonst
+ */
+static bool convert_char(vterminal_t* vterm, char c, char* dest)
+{
+ int len = vterm->utf8_buffer_offset + 1;
+ char buf[len];
+ wchar_t wc;
+
+ // Zeichen aus dem Unicode-Puffer kopieren
+ memcpy(buf, vterm->utf8_buffer, vterm->utf8_buffer_offset);
+ buf[len - 1] = c;
+
+ // Versuchen ein Zeichen zu konvertieren
+ if (mbtowc(&wc, buf, len) == -1) {
+ char* p = buf;
+
+ // Wenn das nicht klappt, wird das ganze in den Buffer kopiert
+ if (len > 4) {
+ // Erstes Zeichen abschneiden bei mehr als 4
+ len--;
+ p++;
+ }
+
+ memcpy(vterm->utf8_buffer, p, len);
+ vterm->utf8_buffer_offset = len;
+ return FALSE;
+ } else {
+ *dest = to_cp437(wc);
+ vterm->utf8_buffer_offset = 0;
+ return (*dest != 0);
+ }
+
+}
+
+int utf8_to_cp437(vterminal_t* vterm, const char* str, size_t len, char* buf)
+{
+ int l = 0;
+ int i;
+
+ for (i = 0; i < len; i++) {
+ if (convert_char(vterm, str[i], buf + l)) {
+ l++;
+ }
+ }
+ return l;
+}
+
+