#ifndef TEXTUTILS_H
#define TEXTUTILS_H
-/// return true if the char is a word separator
-inline
-bool IsSeparatorChar(char c)
-{
- return (c == ' ');
-}
+#include "support/types.h"
+#ifdef LIBC_WCTYPE_USES_UCS4
+// We can use the libc ctype functions because we unset the LC_CTYPE
+// category of the current locale in gettext.C
+#include <wctype.h>
+#else
+// Steal some code from somewhere else, e.g. glib (look at gunicode.h)
+// The code that we currently use does not really work.
+#endif
-/// return true if the char is a line separator
-inline
-bool IsLineSeparatorChar(char c)
-{
- return (c == ' ');
-}
+namespace lyx {
-/// return true if the char is "punctuation"
+/// return true if the char is a line separator
inline
-bool IsKommaChar(char c)
+bool isLineSeparatorChar(char_type c)
{
- return (c == ','
- || c == '('
- || c == ')'
- || c == '['
- || c == ']'
- || c == '{'
- || c == '}'
- || c == ';'
- || c == '.'
- || c == ':'
- || c == '-'
- || c == '?'
- || c == '!'
- || c == '&'
- || c == '@'
- || c == '+'
- || c == '-'
- || c == '~'
- || c == '#'
- || c == '%'
- || c == '^'
- || c == '/'
- || c == '\\'
- );
+ return c == ' ';
}
/// return true if a char is alphabetical (including accented chars)
inline
-bool IsLetterChar(unsigned char c)
+bool isLetterChar(char_type c)
{
- return ((c >= 'A' && c <= 'Z')
+#ifdef LIBC_WCTYPE_USES_UCS4
+ return iswalpha(c);
+#else
+ // FIXME UNICODE This is wrong!
+ return (c >= 'A' && c <= 'Z')
|| (c >= 'a' && c <= 'z')
- || (c >= 192)); // in iso-8859-x these are accented chars
+ || (c >= 192 && c < 256); // in iso-8859-x these are accented chars
+#endif
}
-/// return true if the char is printable (masked to 7-bit ASCII)
+/// return true if the char is printable
inline
-bool IsPrintable(unsigned char c)
+bool isPrintable(char_type c)
{
- return ((c & 127) >= ' ');
+#ifdef LIBC_WCTYPE_USES_UCS4
+ return iswprint(c);
+#else
+ // FIXME UNICODE This is wrong!
+ return (c & 127) >= ' ';
+#endif
}
-/// return true if the char is printable and not a space (masked to 7-bit ASCII)
+/// return true if the char is printable and not a space
inline
-bool IsPrintableNonspace(unsigned char c)
+bool isPrintableNonspace(char_type c)
{
- return IsPrintable(c) && (c != ' ');
+#ifdef LIBC_WCTYPE_USES_UCS4
+ return iswprint(c) && !iswspace(c);
+#else
+ // FIXME UNICODE This is wrong!
+ return (c & 127) > ' ';
+#endif
}
-/// completely pointless FIXME
+/// return true if a unicode char is a digit.
inline
-bool IsDigit(unsigned char ch)
+bool isDigit(char_type c)
{
- return ch >= '0' && ch <= '9';
+#ifdef LIBC_WCTYPE_USES_UCS4
+ return iswdigit(c);
+#else
+ // FIXME UNICODE This is wrong!
+ return c >= '0' && c <= '9';
+#endif
}
-/// return true if the char is alphanumeric
-inline
-bool IsLetterCharOrDigit(unsigned char ch)
-{
- return IsLetterChar(ch) || IsDigit(ch);
-}
+
+} // namespace lyx
#endif // TEXTUTILS_H