#include "support/lstrings.h"
#include "support/convert.h"
+#include "support/debug.h"
+#include "support/lyxlib.h"
#include "support/qstring_helpers.h"
#include "support/lassert.h"
#include <QString>
#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));
}
/// Maximum valid UCS4 code point
char_type const ucs4_max = 0x10ffff;
-} // anon namespace
+} // namespace
bool isLetterChar(char_type c)
{
if (!is_utf16(c)) {
// assume that no non-utf16 character is a space
- // c outside the UCS4 range is catched as well
+ // c outside the UCS4 range is caught as well
return false;
}
QChar const qc = ucs4_to_qchar(c);
{
if (!is_utf16(c))
// assume that no non-utf16 character is a numeral
- // c outside the UCS4 range is catched as well
+ // c outside the UCS4 range is caught as well
return false;
return ucs4_to_qchar(c).isNumber();
}
+bool isCommonNumberSeparator(char_type c)
+{
+ if (!is_utf16(c))
+ // assume that no non-utf16 character is a numeral
+ // c outside the UCS4 range is caught as well
+ return false;
+ return ucs4_to_qchar(c).direction() == QChar::DirCS;
+}
+
+
+bool isEuropeanNumberTerminator(char_type c)
+{
+ if (!is_utf16(c))
+ // assume that no non-utf16 character is a numeral
+ // c outside the UCS4 range is caught as well
+ return false;
+ return ucs4_to_qchar(c).direction() == QChar::DirET;
+}
+
+
bool isDigitASCII(char_type c)
{
return '0' <= c && c <= '9';
}
+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 caught as well
+ return false;
+ }
+ QChar const qc = ucs4_to_qchar(c);
+ return qc.category() == QChar::Punctuation_Open;
+}
+
+
namespace support {
int compare_no_case(docstring const & s, docstring const & s2)
}
+int compare_locale(docstring const & s, docstring const & s2)
+{
+ return QString::localeAwareCompare(toqstr(s), toqstr(s2));
+}
+
+
namespace {
template<typename Char>
return c;
}
-}
+} // namespace
int compare_ascii_no_case(string const & s, string const & s2)
bool isHex(docstring const & str)
{
- int index = 0;
+ size_t index = 0;
if (str.length() > 2 && str[0] == '0' &&
(str[1] == 'x' || str[1] == 'X'))
index = 2;
- int const len = str.length();
+ size_t const len = str.length();
for (; index < len; ++index) {
if (!isHexChar(str[index]))
}
-int hexToInt(docstring const & str)
+unsigned int hexToInt(docstring const & str)
{
string s = to_ascii(str);
- int h;
+ unsigned int h;
sscanf(s.c_str(), "%x", &h);
return h;
}
bool isAscii(docstring const & str)
{
- int const len = str.length();
- for (int i = 0; i < len; ++i)
+ size_t const len = str.length();
+ for (size_t i = 0; i < len; ++i)
if (str[i] >= 0x80)
return false;
return true;
bool isAscii(string const & str)
{
- int const len = str.length();
- for (int i = 0; i < len; ++i)
+ size_t const len = str.length();
+ for (size_t i = 0; i < len; ++i)
if (static_cast<unsigned char>(str[i]) >= 0x80)
return false;
return true;
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));
}
Char operator()(Char c) const { return ascii_tolower(c); }
};
-} // end of anon namespace
+} // namespace
docstring const lowercase(docstring const & a)
}
+/* 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);
}
+docstring capitalize(docstring const & s) {
+ docstring ret = s;
+ char_type t = uppercase(ret[0]);
+ ret[0] = t;
+ return ret;
+}
+
+
string const ascii_lowercase(string const & a)
{
string 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();
while ((i = lstr.find(oldstr, i)) != string::npos) {
lstr.replace(i, olen, newstr);
- i += newstr.length(); // We need to be sure that we dont
+ i += newstr.length(); // We need to be sure that we don't
// use the same i over and over again.
}
return lstr;
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();
while ((i = lstr.find(oldstr, i)) != string::npos) {
lstr.replace(i, olen, newstr);
- i += newstr.length(); // We need to be sure that we dont
+ i += newstr.length(); // We need to be sure that we don't
// use the same i over and over again.
}
return lstr;
}
-}
+} // namespace
string const subst(string const & a, char oldchar, char newchar)
}
-/// Count all occurences of char \a chr inside \a str
+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 occurrences of char \a chr inside \a str
int count_char(docstring const & str, docstring::value_type chr)
{
int count = 0;
}
+int wordCount(docstring const & d)
+{
+ docstring dt = trim(d);
+ if (dt.empty())
+ return 0;
+ int words = 1;
+ for (auto const & c : dt) {
+ if (isSpace(c))
+ words++;
+ }
+ return words;
+}
+
+
+
+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;
}
return tmp;
}
-} // anon
+} // namespace
string const split(string const & a, string & piece, char delim)
}
+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;
char_type hexdigit[16] = { '0', '1', '2', '3', '4', '5', '6', '7',
'8', '9', 'A', 'B', 'C', 'D', 'E', 'F' };
docstring enc;
- for (size_t i = 0; i < lab.length(); ++i) {
- char_type c = lab[i];
+ for (char_type const c : lab) {
if (c >= 128 || c == '=' || c == '%' || c == '#' || c == '$'
- || c == '}' || c == '{' || 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];
}
+docstring const protectArgument(docstring & arg, char const l,
+ char const r)
+{
+ if (contains(arg, l) || contains(arg, r))
+ // protect brackets
+ arg = '{' + arg + '}';
+ return arg;
+}
+
+
+bool truncateWithEllipsis(docstring & str, size_t const len, bool const mid)
+{
+ if (str.size() <= len)
+ return false;
+ if (mid && len > 0) {
+ size_t const hlen = len / 2;
+ docstring suffix = str.substr(str.size() - hlen);
+ str.resize(hlen);
+ str[hlen - 1] = 0x2026;// HORIZONTAL ELLIPSIS
+ str += suffix;
+ } else {
+ 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));
return retval;
}
-}
+} // namespace
docstring wrap(docstring const & str, int const ind, size_t const width)
docstring wrapParas(docstring const & str, int const indent,
size_t const width, size_t const maxlines)
{
- docstring const dots = from_ascii("...");
if (str.empty())
return docstring();
tmp.resize(maxlines - curlines);
docstring last = tmp.back();
size_t const lsize = last.size();
- if (lsize > width - 3) {
- size_t const i = last.find_last_of(' ', width - 3);
+ 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
- last = last.substr(0, lsize - 3) + dots;
+ truncateWithEllipsis(last, lsize);
else
- last = last.substr(0, i) + dots;
+ truncateWithEllipsis(last, i);
} else
- last += dots;
+ last.push_back(0x2026);//HORIZONTAL ELLIPSIS
tmp.pop_back();
tmp.push_back(last);
}
namespace {
template<typename String> vector<String> const
-getVectorFromStringT(String const & str, String const & delim, bool keepempty)
+getVectorFromStringT(String const & str, String const & delim,
+ bool keepempty, bool trimit)
{
// Lars would like this code to go, but for now his replacement (below)
// doesn't fullfil the same function. I have, therefore, reactivated the
vector<String> vec;
if (str.empty())
return vec;
- String keys = rtrim(str);
+ String keys = trimit ? rtrim(str) : str;
while (true) {
size_t const idx = keys.find(delim);
if (idx == String::npos) {
- vec.push_back(ltrim(keys));
+ vec.push_back(trimit ? ltrim(keys) : keys);
break;
}
- String const key = trim(keys.substr(0, idx));
+ String const key = trimit ?
+ trim(keys.substr(0, idx)) : keys.substr(0, idx);
if (!key.empty() || keepempty)
vec.push_back(key);
size_t const start = idx + delim.size();
return str;
}
-} // namespace anon
+} // namespace
vector<string> const getVectorFromString(string const & str,
- string const & delim,
- bool keepempty)
+ string const & delim, bool keepempty, bool trimit)
{
- return getVectorFromStringT<string>(str, delim, keepempty);
+ return getVectorFromStringT<string>(str, delim, keepempty, trimit);
}
vector<docstring> const getVectorFromString(docstring const & str,
- docstring const & delim,
- bool keepempty)
+ docstring const & delim, bool keepempty, bool trimit)
{
- return getVectorFromStringT<docstring>(str, delim, keepempty);
+ return getVectorFromStringT<docstring>(str, delim, keepempty, trimit);
}
}
-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.
+ int const precision = (x == 0.0) ? 0 : max(6 - iround(log10(fabs(x))), 0);
+ os << std::setprecision(precision) << 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 to_percent_encoding(docstring const & in, docstring const & ex)
+{
+ QByteArray input = to_utf8(in).c_str();
+ QByteArray excludes = to_utf8(ex).c_str();
+ return from_utf8(string(input.toPercentEncoding(excludes).data()));
+}
+
+
+string from_percent_encoding(string const & in)
+{
+ return QByteArray::fromPercentEncoding(in.c_str()).data();
+}
+
+
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$d"), convert<docstring>(arg1));
return subst(str, from_ascii("%%"), from_ascii("%"));
}
-template<>
+#ifdef HAVE_LONG_LONG_INT
+docstring bformat(docstring const & fmt, long long arg1)
+{
+ LATTEST(contains(fmt, from_ascii("%1$d")));
+ docstring const str = subst(fmt, from_ascii("%1$d"), convert<docstring>(arg1));
+ return subst(str, from_ascii("%%"), from_ascii("%"));
+}
+#endif
+
+
docstring bformat(docstring const & fmt, unsigned int arg1)
{
- LASSERT(contains(fmt, from_ascii("%1$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")), /**/);
- docstring str = subst(fmt, from_ascii("%1$s"), from_ascii(arg1));
- str = subst(fmt, from_ascii("%2$s"), arg2);
- return subst(str, from_ascii("%%"), from_ascii("%"));
+ return bformat(fmt, from_ascii(arg1), arg2);
}
-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$s"), arg3);
}
-template<>
docstring bformat(docstring const & fmt,
- docstring arg1, docstring arg2, docstring arg3, docstring arg4)
+ docstring const & arg1, docstring const & arg2, docstring const & arg3, docstring const & arg4)
+{
+ LATTEST(contains(fmt, from_ascii("%1$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);
+ str = subst(str, from_ascii("%4$s"), arg4);
+ return subst(str, from_ascii("%%"), from_ascii("%"));
+}
+
+docstring bformat(docstring const & fmt, docstring const & arg1,
+ docstring const & arg2, docstring const & arg3,
+ docstring const & arg4, docstring const & arg5)
{
- LASSERT(contains(fmt, from_ascii("%1$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$s")));
+ LATTEST(contains(fmt, from_ascii("%5$s")));
docstring str = subst(fmt, from_ascii("%1$s"), arg1);
str = subst(str, from_ascii("%2$s"), arg2);
str = subst(str, from_ascii("%3$s"), arg3);
str = subst(str, from_ascii("%4$s"), arg4);
+ str = subst(str, from_ascii("%5$s"), arg5);
return subst(str, from_ascii("%%"), from_ascii("%"));
}