#include "support/lstrings.h"
#include "support/convert.h"
+#include "support/debug.h"
+#include "support/lyxlib.h"
#include "support/qstring_helpers.h"
-#include "support/textutils.h"
-#include <boost/tokenizer.hpp>
#include "support/lassert.h"
#include <QString>
-#include <QVector>
#include <cstdio>
+#include <cstring>
#include <algorithm>
+#include <iomanip>
+#include <sstream>
+#include <typeinfo>
using namespace std;
// without #include "support/docstring" there.
docstring const & empty_docstring()
{
- static docstring s;
+ static const docstring s;
return s;
}
// without #include <string>
string const & empty_string()
{
- static string s;
+ static const string s;
return s;
}
*/
inline char_type qchar_to_ucs4(QChar const & qchar)
{
- LASSERT(is_utf16(static_cast<char_type>(qchar.unicode())), /**/);
+ LASSERT(is_utf16(static_cast<char_type>(qchar.unicode())), return '?');
return static_cast<char_type>(qchar.unicode());
}
*/
inline QChar const ucs4_to_qchar(char_type const ucs4)
{
- LASSERT(is_utf16(ucs4), /**/);
+ LASSERT(is_utf16(ucs4), return QChar('?'));
return QChar(static_cast<unsigned short>(ucs4));
}
// assume that all non-utf16 characters are printable
return true;
}
+ // Not yet recognized by QChar::isPrint()
+ // See https://bugreports.qt-project.org/browse/QTBUG-12144
+ // LATIN CAPITAL LETTER SHARP S
+ else if (c == 0x1e9e)
+ return true;
return ucs4_to_qchar(c).isPrint();
}
}
-bool isDigit(char_type c)
+bool isNumber(char_type c)
{
if (!is_utf16(c))
- // assume that no non-utf16 character is a digit
+ // assume that no non-utf16 character is a numeral
// c outside the UCS4 range is catched as well
return false;
- return ucs4_to_qchar(c).isDigit();
+ return ucs4_to_qchar(c).isNumber();
}
bool isAlnumASCII(char_type c)
{
- return ('0' <= c && c <= '9')
- || ('a' <= c && c <= 'z') || ('A' <= c && c <= 'Z');
+ return isAlphaASCII(c) || isDigitASCII(c);
+}
+
+
+bool isASCII(char_type c)
+{
+ return c < 0x80;
+}
+
+
+bool isOpenPunctuation(char_type c)
+{
+ if (!is_utf16(c)) {
+ // assume that no non-utf16 character is an op
+ // c outside the UCS4 range is catched as well
+ return false;
+ }
+ QChar const qc = ucs4_to_qchar(c);
+ return qc.category() == QChar::Punctuation_Open;
}
}
+int compare_locale(docstring const & s, docstring const & s2)
+{
+ return QString::localeAwareCompare(toqstr(s), toqstr(s2));
+}
+
+
namespace {
template<typename Char>
string::const_iterator end = tmpstr.end();
for (; cit != end; ++cit)
- if (!isdigit((*cit)))
+ if (!isDigitASCII(*cit))
return false;
return true;
string::const_iterator cit = tmpstr.begin();
string::const_iterator end = tmpstr.end();
for (; cit != end; ++cit)
- if (!isdigit((*cit)))
+ if (!isDigitASCII(*cit))
return false;
return true;
++cit;
string::const_iterator end = tmpstr.end();
for (; cit != end; ++cit) {
- if (!isdigit(*cit) && *cit != '.')
+ if (!isDigitASCII(*cit) && *cit != '.')
return false;
if ('.' == (*cit)) {
if (found_dot)
}
-bool hasDigit(docstring const & str)
+bool hasDigitASCII(docstring const & str)
{
- if (str.empty())
- return false;
-
docstring::const_iterator cit = str.begin();
docstring::const_iterator const end = str.end();
- for (; cit != end; ++cit) {
- if (*cit == ' ')
- continue;
- if (isdigit((*cit)))
+ for (; cit != end; ++cit)
+ if (isDigitASCII(*cit))
return true;
- }
return false;
}
-static bool isHexChar(char_type c)
+bool isHexChar(char_type c)
{
return c == '0' ||
c == '1' ||
char lowercase(char c)
{
- LASSERT(static_cast<unsigned char>(c) < 0x80, /**/);
+ LASSERT(isASCII(c), return '?');
return char(tolower(c));
}
char uppercase(char c)
{
- LASSERT(static_cast<unsigned char>(c) < 0x80, /**/);
+ LASSERT(isASCII(c), return '?');
return char(toupper(c));
}
}
+/* Uncomment here and in lstrings.h if you should need this.
+string const lowercase(string const & a)
+{
+ string tmp(a);
+ transform(tmp.begin(), tmp.end(), tmp.begin(), local_lowercase());
+ return tmp;
+}
+*/
+
+
docstring const uppercase(docstring const & a)
{
docstring tmp(a);
}
+bool containsOnly(docstring const & s, string const & cset)
+{
+ return s.find_first_not_of(from_ascii(cset)) == string::npos;
+}
+
+
// ale970405+lasgoutt-970425
// rewritten to use new string (Lgb)
string const token(string const & a, char delim, int n)
String const subst_string(String const & a,
String const & oldstr, String const & newstr)
{
- LASSERT(!oldstr.empty(), /**/);
+ LASSERT(!oldstr.empty(), return a);
String lstr = a;
size_t i = 0;
size_t const olen = oldstr.length();
docstring const subst_string(docstring const & a,
docstring const & oldstr, docstring const & newstr)
{
- LASSERT(!oldstr.empty(), /**/);
+ LASSERT(!oldstr.empty(), return a);
docstring lstr = a;
size_t i = 0;
size_t const olen = oldstr.length();
}
+int count_char(string const & str, char chr)
+{
+ int count = 0;
+ string::const_iterator lit = str.begin();
+ string::const_iterator end = str.end();
+ for (; lit != end; ++lit)
+ if ((*lit) == chr)
+ count++;
+ return count;
+}
+
+
/// Count all occurences of char \a chr inside \a str
int count_char(docstring const & str, docstring::value_type chr)
{
}
+int count_bin_chars(string const & str)
+{
+ QString const qstr = toqstr(str).simplified();
+ int count = 0;
+ QString::const_iterator cit = qstr.begin();
+ QString::const_iterator end = qstr.end();
+ for (; cit != end; ++cit) {
+ switch (cit->category()) {
+ case QChar::Separator_Line:
+ case QChar::Separator_Paragraph:
+ case QChar::Other_Control:
+ case QChar::Other_Format:
+ case QChar::Other_Surrogate:
+ case QChar::Other_PrivateUse:
+ case QChar::Other_NotAssigned:
+ ++count;
+ break;
+ default:
+ break;
+ }
+ }
+ return count;
+}
+
+
docstring const trim(docstring const & a, char const * p)
{
- LASSERT(p, /**/);
+ LASSERT(p, return a);
if (a.empty() || !*p)
return a;
string const trim(string const & a, char const * p)
{
- LASSERT(p, /**/);
+ LASSERT(p, return a);
if (a.empty() || !*p)
return a;
string const rtrim(string const & a, char const * p)
{
- LASSERT(p, /**/);
+ LASSERT(p, return a);
if (a.empty() || !*p)
return a;
docstring const rtrim(docstring const & a, char const * p)
{
- LASSERT(p, /**/);
+ LASSERT(p, return a);
if (a.empty() || !*p)
return a;
string const ltrim(string const & a, char const * p)
{
- LASSERT(p, /**/);
+ LASSERT(p, return a);
if (a.empty() || !*p)
return a;
size_t l = a.find_first_not_of(p);
docstring const ltrim(docstring const & a, char const * p)
{
- LASSERT(p, /**/);
+ LASSERT(p, return a);
if (a.empty() || !*p)
return a;
size_t l = a.find_first_not_of(from_ascii(p));
size_t i = a.find(delim);
if (i == a.length() - 1) {
piece = a.substr(0, i);
- } else if (i != String::npos) {
- piece = a.substr(0, i);
- tmp = a.substr(i + 1);
} else if (i == 0) {
piece.erase();
tmp = a.substr(i + 1);
+ } else if (i != String::npos) {
+ piece = a.substr(0, i);
+ tmp = a.substr(i + 1);
} else {
piece = a;
}
return tmp;
}
+
+// FIXME: why is this specialization needed?
template<typename Char> inline
docstring const doSplit(docstring const & a, docstring & piece, Char delim)
{
size_t i = a.find(delim);
if (i == a.length() - 1) {
piece = a.substr(0, i);
- } else if (i != docstring::npos) {
- piece = a.substr(0, i);
- tmp = a.substr(i + 1);
} else if (i == 0) {
piece.erase();
tmp = a.substr(i + 1);
+ } else if (i != docstring::npos) {
+ piece = a.substr(0, i);
+ tmp = a.substr(i + 1);
} else {
piece = a;
}
}
+docstring const rsplit(docstring const & a, docstring & piece, char_type delim)
+{
+ docstring tmp;
+ size_t i = a.rfind(delim);
+ if (i != string::npos) { // delimiter was found
+ piece = a.substr(0, i);
+ tmp = a.substr(i + 1);
+ } else { // delimiter was not found
+ piece.erase();
+ }
+ return tmp;
+}
+
+
docstring const rsplit(docstring const & a, char_type delim)
{
docstring tmp;
docstring enc;
for (size_t i = 0; i < lab.length(); ++i) {
char_type c = lab[i];
- if (c >= 128 || c == '=' || c == '%') {
+ if (c >= 128 || c == '=' || c == '%' || c == '#' || c == '$'
+ || c == '}' || c == '{' || c == ']' || c == '[' || c == '&') {
// Although char_type is a 32 bit type we know that
// UCS4 occupies only 21 bits, so we don't need to
// encode bigger values. Test for 2^24 because we
// can encode that with the 6 hex digits that are
// needed for 21 bits anyway.
- LASSERT(c < (1 << 24), /**/);
+ LASSERT(c < (1 << 24), continue);
enc += '=';
enc += hexdigit[(c>>20) & 15];
enc += hexdigit[(c>>16) & 15];
}
+bool truncateWithEllipsis(docstring & str, size_t const len)
+{
+ if (str.size() <= len)
+ return false;
+ str.resize(len);
+ if (len > 0)
+ str[len - 1] = 0x2026;// HORIZONTAL ELLIPSIS
+ return true;
+}
+
+
namespace {
// this doesn't check whether str is empty, so do that first.
size_t const i = s.find_last_of(' ', width - 1);
if (i == docstring::npos || i <= size_t(ind)) {
// no space found
- s = s.substr(0, width - 3) + "...";
+ truncateWithEllipsis(s, width);
break;
}
retval.push_back(s.substr(0, i));
if (nlines == 0)
continue;
size_t const curlines = retval.size();
- if (maxlines > 0 && curlines + nlines >= maxlines) {
- tmp.resize(maxlines - curlines - 1);
- tmp.push_back(from_ascii("..."));
+ if (maxlines > 0 && curlines + nlines > maxlines) {
+ tmp.resize(maxlines - curlines);
+ docstring last = tmp.back();
+ size_t const lsize = last.size();
+ if (lsize > width - 1) {
+ size_t const i = last.find_last_of(' ', width - 1);
+ if (i == docstring::npos || i <= size_t(indent))
+ // no space found
+ truncateWithEllipsis(last, lsize);
+ else
+ truncateWithEllipsis(last, i);
+ } else
+ last.push_back(0x2026);//HORIZONTAL ELLIPSIS
+ tmp.pop_back();
+ tmp.push_back(last);
}
retval.insert(retval.end(), tmp.begin(), tmp.end());
if (maxlines > 0 && retval.size() >= maxlines)
}
-template<>
+std::string formatFPNumber(double x)
+{
+ // Need manual tweaking, QString::number(x, 'f', 16) does not work either
+ ostringstream os;
+ os << std::fixed;
+ // Prevent outputs of 23.4200000000000017 but output small numbers
+ // with at least 6 significant digits.
+ double const logarithm = log10(fabs(x));
+ os << std::setprecision(max(6 - iround(logarithm), 0)) << x;
+ string result = os.str();
+ if (result.find('.') != string::npos) {
+ result = rtrim(result, "0");
+ if (result[result.length()-1] == '.')
+ result = rtrim(result, ".");
+ }
+ return result;
+}
+
+
docstring bformat(docstring const & fmt, int arg1)
{
- LASSERT(contains(fmt, from_ascii("%1$d")), /**/);
+ LATTEST(contains(fmt, from_ascii("%1$d")));
docstring const str = subst(fmt, from_ascii("%1$d"), convert<docstring>(arg1));
return subst(str, from_ascii("%%"), from_ascii("%"));
}
-template<>
docstring bformat(docstring const & fmt, long arg1)
{
- LASSERT(contains(fmt, from_ascii("%1$d")), /**/);
+ LATTEST(contains(fmt, from_ascii("%1$d")));
+ docstring const str = subst(fmt, from_ascii("%1$d"), convert<docstring>(arg1));
+ return subst(str, from_ascii("%%"), from_ascii("%"));
+}
+
+
+#ifdef LYX_USE_LONG_LONG
+docstring bformat(docstring const & fmt, long long arg1)
+{
+ LATTEST(contains(fmt, from_ascii("%1$d")));
docstring const str = subst(fmt, from_ascii("%1$d"), convert<docstring>(arg1));
return subst(str, from_ascii("%%"), from_ascii("%"));
}
+#endif
-template<>
docstring bformat(docstring const & fmt, unsigned int arg1)
{
- LASSERT(contains(fmt, from_ascii("%1$d")), /**/);
+ LATTEST(contains(fmt, from_ascii("%1$d")));
docstring const str = subst(fmt, from_ascii("%1$d"), convert<docstring>(arg1));
return subst(str, from_ascii("%%"), from_ascii("%"));
}
-template<>
-docstring bformat(docstring const & fmt, docstring arg1)
+docstring bformat(docstring const & fmt, docstring const & arg1)
{
- LASSERT(contains(fmt, from_ascii("%1$s")), /**/);
+ LATTEST(contains(fmt, from_ascii("%1$s")));
docstring const str = subst(fmt, from_ascii("%1$s"), arg1);
return subst(str, from_ascii("%%"), from_ascii("%"));
}
-template<>
docstring bformat(docstring const & fmt, char * arg1)
{
- LASSERT(contains(fmt, from_ascii("%1$s")), /**/);
+ LATTEST(contains(fmt, from_ascii("%1$s")));
docstring const str = subst(fmt, from_ascii("%1$s"), from_ascii(arg1));
return subst(str, from_ascii("%%"), from_ascii("%"));
}
-template<>
-docstring bformat(docstring const & fmt, docstring arg1, docstring arg2)
+docstring bformat(docstring const & fmt, docstring const & arg1, docstring const & arg2)
{
- LASSERT(contains(fmt, from_ascii("%1$s")), /**/);
- LASSERT(contains(fmt, from_ascii("%2$s")), /**/);
+ LATTEST(contains(fmt, from_ascii("%1$s")));
+ LATTEST(contains(fmt, from_ascii("%2$s")));
docstring str = subst(fmt, from_ascii("%1$s"), arg1);
str = subst(str, from_ascii("%2$s"), arg2);
return subst(str, from_ascii("%%"), from_ascii("%"));
}
-template<>
-docstring bformat(docstring const & fmt, docstring arg1, int arg2)
+docstring bformat(docstring const & fmt, docstring const & arg1, int arg2)
{
- LASSERT(contains(fmt, from_ascii("%1$s")), /**/);
- LASSERT(contains(fmt, from_ascii("%2$d")), /**/);
+ LATTEST(contains(fmt, from_ascii("%1$s")));
+ LATTEST(contains(fmt, from_ascii("%2$d")));
docstring str = subst(fmt, from_ascii("%1$s"), arg1);
str = subst(str, from_ascii("%2$d"), convert<docstring>(arg2));
return subst(str, from_ascii("%%"), from_ascii("%"));
}
-template<>
-docstring bformat(docstring const & fmt, char const * arg1, docstring arg2)
+docstring bformat(docstring const & fmt, char const * arg1, docstring const & arg2)
{
- LASSERT(contains(fmt, from_ascii("%1$s")), /**/);
- LASSERT(contains(fmt, from_ascii("%2$s")), /**/);
+ LATTEST(contains(fmt, from_ascii("%1$s")));
+ LATTEST(contains(fmt, from_ascii("%2$s")));
docstring str = subst(fmt, from_ascii("%1$s"), from_ascii(arg1));
- str = subst(fmt, from_ascii("%2$s"), arg2);
+ str = subst(str, from_ascii("%2$s"), arg2);
return subst(str, from_ascii("%%"), from_ascii("%"));
}
-template<>
docstring bformat(docstring const & fmt, int arg1, int arg2)
{
- LASSERT(contains(fmt, from_ascii("%1$d")), /**/);
- LASSERT(contains(fmt, from_ascii("%2$d")), /**/);
+ LATTEST(contains(fmt, from_ascii("%1$d")));
+ LATTEST(contains(fmt, from_ascii("%2$d")));
docstring str = subst(fmt, from_ascii("%1$d"), convert<docstring>(arg1));
str = subst(str, from_ascii("%2$d"), convert<docstring>(arg2));
return subst(str, from_ascii("%%"), from_ascii("%"));
}
-template<>
-docstring bformat(docstring const & fmt, docstring arg1, docstring arg2, docstring arg3)
+docstring bformat(docstring const & fmt, docstring const & arg1, docstring const & arg2, docstring const & arg3)
{
- LASSERT(contains(fmt, from_ascii("%1$s")), /**/);
- LASSERT(contains(fmt, from_ascii("%2$s")), /**/);
- LASSERT(contains(fmt, from_ascii("%3$s")), /**/);
+ LATTEST(contains(fmt, from_ascii("%1$s")));
+ LATTEST(contains(fmt, from_ascii("%2$s")));
+ LATTEST(contains(fmt, from_ascii("%3$s")));
docstring str = subst(fmt, from_ascii("%1$s"), arg1);
str = subst(str, from_ascii("%2$s"), arg2);
str = subst(str, from_ascii("%3$s"), arg3);
}
-template<>
docstring bformat(docstring const & fmt,
- docstring arg1, docstring arg2, docstring arg3, docstring arg4)
+ docstring const & arg1, docstring const & arg2, docstring const & arg3, docstring const & arg4)
{
- LASSERT(contains(fmt, from_ascii("%1$s")), /**/);
- LASSERT(contains(fmt, from_ascii("%2$s")), /**/);
- LASSERT(contains(fmt, from_ascii("%3$s")), /**/);
- LASSERT(contains(fmt, from_ascii("%4$s")), /**/);
+ LATTEST(contains(fmt, from_ascii("%1$s")));
+ LATTEST(contains(fmt, from_ascii("%2$s")));
+ LATTEST(contains(fmt, from_ascii("%3$s")));
+ LATTEST(contains(fmt, from_ascii("%4$s")));
docstring str = subst(fmt, from_ascii("%1$s"), arg1);
str = subst(str, from_ascii("%2$s"), arg2);
str = subst(str, from_ascii("%3$s"), arg3);