summaryrefslogtreecommitdiff
path: root/src/modules/filters/utf8latin1.cpp
diff options
context:
space:
mode:
Diffstat (limited to 'src/modules/filters/utf8latin1.cpp')
-rw-r--r--src/modules/filters/utf8latin1.cpp92
1 files changed, 92 insertions, 0 deletions
diff --git a/src/modules/filters/utf8latin1.cpp b/src/modules/filters/utf8latin1.cpp
new file mode 100644
index 0000000..1bf8d3b
--- /dev/null
+++ b/src/modules/filters/utf8latin1.cpp
@@ -0,0 +1,92 @@
+/******************************************************************************
+ *
+ * utf8latin1.cpp - SWFilter descendant to convert UTF-8 to Latin-1
+ *
+ * $Id: utf8latin1.cpp 2980 2013-09-14 21:51:47Z scribe $
+ *
+ * Copyright 2001-2013 CrossWire Bible Society (http://www.crosswire.org)
+ * CrossWire Bible Society
+ * P. O. Box 2528
+ * Tempe, AZ 85280-2528
+ *
+ * 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 version 2.
+ *
+ * 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.
+ *
+ */
+
+#include <stdlib.h>
+#include <stdio.h>
+
+#include <utf8latin1.h>
+#include <swbuf.h>
+
+
+SWORD_NAMESPACE_START
+
+
+UTF8Latin1::UTF8Latin1(char rchar) : replacementChar(rchar) {
+}
+
+
+char UTF8Latin1::processText(SWBuf &text, const SWKey *key, const SWModule *module)
+{
+ unsigned char *from;
+
+ unsigned long uchar;
+ unsigned char significantFirstBits, subsequent;
+
+ if ((unsigned long)key < 2) {// hack, we're en(1)/de(0)ciphering
+ return (char)-1;
+ }
+
+ SWBuf orig = text;
+ from = (unsigned char*)orig.c_str();
+
+
+ // -------------------------------
+
+ for (text = ""; *from; from++) {
+ uchar = 0;
+ if ((*from & 128) != 128) {
+ // if (*from != ' ')
+ uchar = *from;
+ }
+ else if ((*from & 128) && ((*from & 64) != 64)) {
+ // error, do nothing
+ continue;
+ }
+ else {
+ *from <<= 1;
+ for (subsequent = 1; (*from & 128); subsequent++) {
+ *from <<= 1;
+ from[subsequent] &= 63;
+ uchar <<= 6;
+ uchar |= from[subsequent];
+ }
+ subsequent--;
+ *from <<=1;
+ significantFirstBits = 8 - (2+subsequent);
+
+ uchar |= (((short)*from) << (((6*subsequent)+significantFirstBits)-8));
+ from += subsequent;
+ }
+
+ if (uchar < 0xff) {
+ text += (unsigned char)uchar;
+ }
+ else {
+ text += replacementChar;
+ }
+ }
+ return 0;
+}
+
+
+SWORD_NAMESPACE_END
+