* This file is part of LyX, the document processor.
* Licence details can be found in the file COPYING.
*
- * \author Lars Gullik Bjønnes
+ * \author Lars Gullik Bjønnes
* \author Jean-Marc Lasgouttes
+ * \author Dekel Tsur
*
* Full author contact details are available in file CREDITS.
*/
#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 <boost/assert.hpp>
+#include "support/lassert.h"
-#include <cctype>
-#include <cstdlib>
+#include <QString>
+#include <QVector>
+#include <cstdio>
#include <algorithm>
-#include <sstream>
using namespace std;
return s;
}
-// Using this allows us to have std::string default arguments in headers
+// Using this allows us to have string default arguments in headers
// without #include <string>
-std::string const & empty_string()
+string const & empty_string()
{
- static std::string s;
+ static string s;
return s;
}
*/
static inline char_type qchar_to_ucs4(QChar const & qchar)
{
- BOOST_ASSERT(is_utf16(static_cast<char_type>(qchar.unicode())));
+ LASSERT(is_utf16(static_cast<char_type>(qchar.unicode())), /**/);
return static_cast<char_type>(qchar.unicode());
}
*/
static inline QChar const ucs4_to_qchar(char_type const ucs4)
{
- BOOST_ASSERT(is_utf16(ucs4));
+ LASSERT(is_utf16(ucs4), /**/);
return QChar(static_cast<unsigned short>(ucs4));
}
}
+bool isLower(char_type c)
+{
+ if (!is_utf16(c))
+ return false;
+ return ucs4_to_qchar(c).isLower();
+}
+
+
bool isAlphaASCII(char_type c)
{
return ('a' <= c && c <= 'z') || ('A' <= c && c <= 'Z');
}
+bool hasDigit(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)))
+ return true;
+ }
+ return false;
+}
+
+
static bool isHexChar(char_type c)
{
return c == '0' ||
char lowercase(char c)
{
- BOOST_ASSERT(static_cast<unsigned char>(c) < 0x80);
+ LASSERT(static_cast<unsigned char>(c) < 0x80, /**/);
return char(tolower(c));
}
char uppercase(char c)
{
- BOOST_ASSERT(static_cast<unsigned char>(c) < 0x80);
+ LASSERT(static_cast<unsigned char>(c) < 0x80, /**/);
return char(toupper(c));
}
}
+bool isLowerCase(char_type ch) {
+ return lowercase(ch) == ch;
+}
+
+
+bool isUpperCase(char_type ch) {
+ return uppercase(ch) == ch;
+}
+
+
namespace {
-// since we cannot use std::tolower and std::toupper directly in the
-// calls to std::transform yet, we use these helper clases. (Lgb)
+// since we cannot use tolower and toupper directly in the
+// calls to transform yet, we use these helper clases. (Lgb)
struct local_lowercase {
char_type operator()(char_type c) const {
{
size_t const prelen = pre.length();
size_t const alen = a.length();
-
- if (prelen > alen || a.empty())
- return false;
-#if defined(STD_STRING_IS_GOOD)
- return a.compare(0, prelen, pre) == 0;
-#else
- return ::strncmp(a.c_str(), pre.c_str(), prelen) == 0;
-#endif
+ return prelen <= alen && !a.empty() && a.compare(0, prelen, pre) == 0;
}
{
size_t const prelen = pre.length();
size_t const alen = a.length();
-
- if (prelen > alen || a.empty())
- return false;
- else
- return a.compare(0, prelen, pre) == 0;
+ return prelen <= alen && !a.empty() && a.compare(0, prelen, pre) == 0;
}
bool suffixIs(string const & a, char c)
{
- if (a.empty()) return false;
+ if (a.empty())
+ return false;
return a[a.length() - 1] == c;
}
{
size_t const suflen = suf.length();
size_t const alen = a.length();
+ return suflen <= alen && a.compare(alen - suflen, suflen, suf) == 0;
+}
- if (suflen > alen)
- return false;
-#if !defined(USE_INCLUDED_STRING) && !defined(STD_STRING_IS_GOOD)
- string tmp(a, alen - suflen);
- return ::strncmp(tmp.c_str(), suf.c_str(), suflen) == 0;
-#else
- return a.compare(alen - suflen, suflen, suf) == 0;
-#endif
+bool suffixIs(docstring const & a, docstring const & suf)
+{
+ size_t const suflen = suf.length();
+ size_t const alen = a.length();
+ return suflen <= alen && a.compare(alen - suflen, suflen, suf) == 0;
}
}
+// this could probably be faster and/or cleaner, but it seems to work (JMarc)
+// rewritten to use new string (Lgb)
+int tokenPos(docstring const & a, char_type delim, docstring const & tok)
+{
+ int i = 0;
+ docstring str = a;
+ docstring tmptok;
+
+ while (!str.empty()) {
+ str = split(str, tmptok, delim);
+ if (tok == tmptok)
+ return i;
+ ++i;
+ }
+ return -1;
+}
+
+
namespace {
/// Substitute all \a oldchar with \a newchar
template<typename Ch> inline
-std::basic_string<Ch> const subst_char(std::basic_string<Ch> const & a,
+basic_string<Ch> const subst_char(basic_string<Ch> const & a,
Ch oldchar, Ch newchar)
{
- typedef std::basic_string<Ch> String;
+ typedef basic_string<Ch> String;
String tmp(a);
typename String::iterator lit = tmp.begin();
typename String::iterator end = tmp.end();
return tmp;
}
+
/// Substitute all \a oldchar with \a newchar
docstring const subst_char(docstring const & a,
docstring::value_type oldchar, docstring::value_type newchar)
String const subst_string(String const & a,
String const & oldstr, String const & newstr)
{
- BOOST_ASSERT(!oldstr.empty());
+ LASSERT(!oldstr.empty(), /**/);
String lstr = a;
size_t i = 0;
size_t const olen = oldstr.length();
return lstr;
}
+
docstring const subst_string(docstring const & a,
docstring const & oldstr, docstring const & newstr)
{
- BOOST_ASSERT(!oldstr.empty());
+ LASSERT(!oldstr.empty(), /**/);
docstring lstr = a;
size_t i = 0;
size_t const olen = oldstr.length();
}
+/// Count all occurences of char \a chr inside \a str
+int count_char(docstring const & str, docstring::value_type chr)
+{
+ int count = 0;
+ docstring::const_iterator lit = str.begin();
+ docstring::const_iterator end = str.end();
+ for (; lit != end; ++lit)
+ if ((*lit) == chr)
+ count++;
+ return count;
+}
+
+
docstring const trim(docstring const & a, char const * p)
{
- BOOST_ASSERT(p);
+ LASSERT(p, /**/);
if (a.empty() || !*p)
return a;
string const trim(string const & a, char const * p)
{
- BOOST_ASSERT(p);
+ LASSERT(p, /**/);
if (a.empty() || !*p)
return a;
string const rtrim(string const & a, char const * p)
{
- BOOST_ASSERT(p);
+ LASSERT(p, /**/);
if (a.empty() || !*p)
return a;
docstring const rtrim(docstring const & a, char const * p)
{
- BOOST_ASSERT(p);
+ LASSERT(p, /**/);
if (a.empty() || !*p)
return a;
string const ltrim(string const & a, char const * p)
{
- BOOST_ASSERT(p);
+ LASSERT(p, /**/);
if (a.empty() || !*p)
return a;
size_t l = a.find_first_not_of(p);
docstring const ltrim(docstring const & a, char const * p)
{
- BOOST_ASSERT(p);
+ LASSERT(p, /**/);
if (a.empty() || !*p)
return a;
size_t l = a.find_first_not_of(from_ascii(p));
}
+docstring const rsplit(docstring const & a, char_type delim)
+{
+ docstring tmp;
+ size_t i = a.rfind(delim);
+ if (i != string::npos)
+ tmp = a.substr(i + 1);
+ return tmp;
+}
+
+
docstring const escape(docstring const & lab)
{
char_type hexdigit[16] = { '0', '1', '2', '3', '4', '5', '6', '7',
// encode bigger values. Test for 2^24 because we
// can encode that with the 6 hex digits that are
// needed for 21 bits anyway.
- BOOST_ASSERT(c < (1 << 24));
+ LASSERT(c < (1 << 24), /**/);
enc += '=';
enc += hexdigit[(c>>20) & 15];
enc += hexdigit[(c>>16) & 15];
}
+namespace {
+
+// this doesn't check whether str is empty, so do that first.
+vector<docstring> wrapToVec(docstring const & str, int ind,
+ size_t const width)
+{
+ docstring s = trim(str);
+ if (s.empty())
+ return vector<docstring>();
+
+ docstring indent;
+ if (ind < 0) {
+ indent.insert(0, -ind, ' ');
+ ind = 0;
+ } else if (ind > 0)
+ s.insert(0, ind, ' ');
+
+ vector<docstring> retval;
+ while (s.size() > width) {
+ // find the last space within the first 'width' chars
+ 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) + "...";
+ break;
+ }
+ retval.push_back(s.substr(0, i));
+ s = indent + s.substr(i);
+ ind = indent.size();
+ }
+ if (!s.empty())
+ retval.push_back(s);
+ return retval;
+}
+
+}
+
+
+docstring wrap(docstring const & str, int const ind, size_t const width)
+{
+ docstring s = trim(str);
+ if (s.empty())
+ return docstring();
+
+ vector<docstring> const svec = wrapToVec(str, ind, width);
+ return getStringFromVector(svec, from_ascii("\n"));
+}
+
+
+docstring wrapParas(docstring const & str, int const indent,
+ size_t const width, size_t const maxlines)
+{
+ if (str.empty())
+ return docstring();
+
+ vector<docstring> const pars = getVectorFromString(str, from_ascii("\n"), true);
+ vector<docstring> retval;
+
+ vector<docstring>::const_iterator it = pars.begin();
+ vector<docstring>::const_iterator const en = pars.end();
+ for (; it != en; ++it) {
+ vector<docstring> tmp = wrapToVec(*it, indent, width);
+ size_t const nlines = tmp.size();
+ 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("..."));
+ }
+ retval.insert(retval.end(), tmp.begin(), tmp.end());
+ if (maxlines > 0 && retval.size() >= maxlines)
+ break;
+ }
+ return getStringFromVector(retval, from_ascii("\n"));
+}
+
+
namespace {
template<typename String> vector<String> const
-getVectorFromStringT(String const & str, String const & delim)
+getVectorFromStringT(String const & str, String const & delim, bool keepempty)
{
// Lars would like this code to go, but for now his replacement (below)
// doesn't fullfil the same function. I have, therefore, reactivated the
break;
}
String const key = trim(keys.substr(0, idx));
- if (!key.empty())
+ if (!key.empty() || keepempty)
vec.push_back(key);
size_t const start = idx + delim.size();
keys = keys.substr(start);
#endif
}
+
+template<typename String> const String
+ getStringFromVector(vector<String> const & vec, String const & delim)
+{
+ String str;
+ typename vector<String>::const_iterator it = vec.begin();
+ typename vector<String>::const_iterator en = vec.end();
+ for (; it != en; ++it) {
+ String item = trim(*it);
+ if (item.empty())
+ continue;
+ if (!str.empty())
+ str += delim;
+ str += item;
+ }
+ return str;
+}
+
} // namespace anon
vector<string> const getVectorFromString(string const & str,
- string const & delim)
+ string const & delim,
+ bool keepempty)
{
- return getVectorFromStringT<string>(str, delim);
+ return getVectorFromStringT<string>(str, delim, keepempty);
}
vector<docstring> const getVectorFromString(docstring const & str,
- docstring const & delim)
+ docstring const & delim,
+ bool keepempty)
{
- return getVectorFromStringT<docstring>(str, delim);
+ return getVectorFromStringT<docstring>(str, delim, keepempty);
}
-// the same vice versa
string const getStringFromVector(vector<string> const & vec,
string const & delim)
{
- string str;
- int i = 0;
- for (vector<string>::const_iterator it = vec.begin();
- it != vec.end(); ++it) {
- string item = trim(*it);
- if (item.empty())
- continue;
- if (i++ > 0)
- str += delim;
- str += item;
- }
- return str;
+ return getStringFromVector<string>(vec, delim);
+}
+
+
+docstring const getStringFromVector(vector<docstring> const & vec,
+ docstring const & delim)
+{
+ return getStringFromVector<docstring>(vec, delim);
}
}
-docstring const externalLineEnding(docstring const & str)
-{
-#if defined(__APPLE__)
- // The MAC clipboard uses \r for lineendings, and we use \n
- return subst(str, '\n', '\r');
-#elif defined (_WIN32) || (defined (__CYGWIN__) && defined (X_DISPLAY_MISSING))
- // Windows clipboard uses \r\n for lineendings, and we use \n
- return subst(str, from_ascii("\n"), from_ascii("\r\n"));
-#else
- return str;
-#endif
-}
-
-
-docstring const internalLineEnding(docstring const & str)
-{
- docstring const s = subst(str, from_ascii("\r\n"), from_ascii("\n"));
- return subst(s, '\r', '\n');
-}
-
-
template<>
docstring bformat(docstring const & fmt, int arg1)
{
- BOOST_ASSERT(contains(fmt, from_ascii("%1$d")));
+ LASSERT(contains(fmt, from_ascii("%1$d")), /**/);
docstring const str = subst(fmt, from_ascii("%1$d"), convert<docstring>(arg1));
return subst(str, from_ascii("%%"), from_ascii("%"));
}
template<>
docstring bformat(docstring const & fmt, long arg1)
{
- BOOST_ASSERT(contains(fmt, from_ascii("%1$d")));
+ LASSERT(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, unsigned int arg1)
{
- BOOST_ASSERT(contains(fmt, from_ascii("%1$d")));
+ LASSERT(contains(fmt, from_ascii("%1$d")), /**/);
docstring const str = subst(fmt, from_ascii("%1$d"), convert<docstring>(arg1));
return subst(str, from_ascii("%%"), from_ascii("%"));
}
template<>
docstring bformat(docstring const & fmt, docstring arg1)
{
- BOOST_ASSERT(contains(fmt, from_ascii("%1$s")));
+ LASSERT(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)
{
- BOOST_ASSERT(contains(fmt, from_ascii("%1$s")));
+ LASSERT(contains(fmt, from_ascii("%1$s")), /**/);
docstring const str = subst(fmt, from_ascii("%1$s"), from_ascii(arg1));
return subst(str, from_ascii("%%"), from_ascii("%"));
}
template<>
docstring bformat(docstring const & fmt, docstring arg1, docstring arg2)
{
- BOOST_ASSERT(contains(fmt, from_ascii("%1$s")));
- BOOST_ASSERT(contains(fmt, from_ascii("%2$s")));
+ LASSERT(contains(fmt, from_ascii("%1$s")), /**/);
+ LASSERT(contains(fmt, from_ascii("%2$s")), /**/);
docstring str = subst(fmt, from_ascii("%1$s"), arg1);
str = subst(str, from_ascii("%2$s"), arg2);
return subst(str, from_ascii("%%"), from_ascii("%"));
}
+template<>
+docstring bformat(docstring const & fmt, docstring arg1, int arg2)
+{
+ LASSERT(contains(fmt, from_ascii("%1$s")), /**/);
+ LASSERT(contains(fmt, from_ascii("%2$d")), /**/);
+ docstring str = subst(fmt, from_ascii("%1$s"), arg1);
+ str = subst(str, from_ascii("%2$d"), convert<docstring>(arg2));
+ return subst(str, from_ascii("%%"), from_ascii("%"));
+}
+
+
template<>
docstring bformat(docstring const & fmt, char const * arg1, docstring arg2)
{
- BOOST_ASSERT(contains(fmt, from_ascii("%1$s")));
- BOOST_ASSERT(contains(fmt, from_ascii("%2$s")));
+ LASSERT(contains(fmt, from_ascii("%1$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$s"), arg2);
return subst(str, from_ascii("%%"), from_ascii("%"));
template<>
docstring bformat(docstring const & fmt, int arg1, int arg2)
{
- BOOST_ASSERT(contains(fmt, from_ascii("%1$d")));
- BOOST_ASSERT(contains(fmt, from_ascii("%2$d")));
+ LASSERT(contains(fmt, from_ascii("%1$d")), /**/);
+ LASSERT(contains(fmt, from_ascii("%2$d")), /**/);
docstring str = subst(fmt, from_ascii("%1$d"), convert<docstring>(arg1));
str = subst(str, from_ascii("%2$d"), convert<docstring>(arg2));
return subst(str, from_ascii("%%"), from_ascii("%"));
template<>
docstring bformat(docstring const & fmt, docstring arg1, docstring arg2, docstring arg3)
{
- BOOST_ASSERT(contains(fmt, from_ascii("%1$s")));
- BOOST_ASSERT(contains(fmt, from_ascii("%2$s")));
- BOOST_ASSERT(contains(fmt, from_ascii("%3$s")));
+ LASSERT(contains(fmt, from_ascii("%1$s")), /**/);
+ LASSERT(contains(fmt, from_ascii("%2$s")), /**/);
+ LASSERT(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);
docstring bformat(docstring const & fmt,
docstring arg1, docstring arg2, docstring arg3, docstring arg4)
{
- BOOST_ASSERT(contains(fmt, from_ascii("%1$s")));
- BOOST_ASSERT(contains(fmt, from_ascii("%2$s")));
- BOOST_ASSERT(contains(fmt, from_ascii("%3$s")));
- BOOST_ASSERT(contains(fmt, from_ascii("%4$s")));
+ 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")), /**/);
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);