* Licence details can be found in the file COPYING.
*
* \author Alejandro Aguilar Sierra
- * \author Lars Gullik Bjønnes
+ * \author Lars Gullik Bjønnes
* \author Jean-Marc Lasgouttes
* \author John Levon
*
#include <config.h>
#include "Lexer.h"
+#include "Format.h"
#include "support/convert.h"
#include "support/debug.h"
#include "support/FileName.h"
#include "support/filetools.h"
#include "support/gzstream.h"
+#include "support/lassert.h"
#include "support/lstrings.h"
#include "support/lyxalgo.h"
#include "support/types.h"
}
};
-} // end of anon namespace
+} // namespace
Lexer::Pimpl::Pimpl(LexerKeyword * tab, int num)
bool Lexer::Pimpl::setFile(FileName const & filename)
{
// Check the format of the file.
- string const format = filename.guessFormatFromContents();
-
- if (format == "gzip" || format == "zip" || format == "compress") {
+ if (theFormats().isZippedFile(filename)) {
LYXERR(Debug::LYXLEX, "lyxlex: compressed");
// The check only outputs a debug message, because it triggers
// a bug in compaq cxx 6.2, where is_open() returns 'true' for
"file or stream already set.");
gz_.open(filename.toFilesystemEncoding().c_str(), ios::in);
is.rdbuf(&gz_);
- name = filename.absFilename();
+ name = filename.absFileName();
lineno = 0;
- return gz_.is_open() && is.good();
+ if (!gz_.is_open() || !is.good())
+ return false;
} else {
LYXERR(Debug::LYXLEX, "lyxlex: UNcompressed");
LYXERR(Debug::LYXLEX, "Error in Lexer::setFile: "
"file or stream already set.");
}
- fb_.open(filename.toFilesystemEncoding().c_str(), ios::in);
+ fb_.open(filename.toSafeFilesystemEncoding().c_str(), ios::in);
is.rdbuf(&fb_);
- name = filename.absFilename();
+ name = filename.absFileName();
lineno = 0;
- return fb_.is_open() && is.good();
+ if (!fb_.is_open() || !is.good())
+ return false;
+ }
+
+ // Skip byte order mark.
+ if (is.peek() == 0xef) {
+ is.get();
+ if (is.peek() == 0xbb) {
+ is.get();
+ LASSERT(is.get() == 0xbf, /**/);
+ } else
+ is.unget();
}
+
+ return true;
}
}
- unsigned char c = 0; // getc() returns an int
char cc = 0;
status = 0;
while (is && !status) {
is.get(cc);
- c = cc;
+ unsigned char c = cc;
if (c == commentChar) {
// Read rest of line (fast :-)
if (esc) {
- bool escaped = false;
do {
- escaped = false;
+ bool escaped = false;
is.get(cc);
c = cc;
if (c == '\r') continue;
is.get(cc);
c = cc;
//LYXERR(Debug::LYXLEX, "Lexer::EatLine read char: `" << c << '\'');
- if (c != '\r')
+ if (c != '\r' && is)
buff.push_back(c);
}
char cc = 0;
is.get(cc);
c = cc;
- if (c >= ' ' && is) {
+ if ((c >= ' ' || c == '\t') && is) {
buff.clear();
if (c == '\\') { // first char == '\\'
buff.push_back(c);
is.get(cc);
c = cc;
- } while (c >= ' ' && c != '\\' && is);
+ } while ((c >= ' ' || c == '\t') && c != '\\' && is);
}
if (c == '\\')
//////////////////////////////////////////////////////////////////////
Lexer::Lexer()
- : pimpl_(new Pimpl(0, 0))
+ : pimpl_(new Pimpl(0, 0)), lastReadOk_(false)
{}
pimpl_->setCommentChar(c);
}
+
int Lexer::lex()
{
return pimpl_->lex();
}
-string const Lexer::getString() const
+string const Lexer::getString(bool trim) const
{
lastReadOk_ = pimpl_->status == LEX_DATA || pimpl_->status == LEX_TOKEN;
if (lastReadOk_)
- return pimpl_->getString();
+ return trim ? support::trim(pimpl_->getString(), "\t ") : pimpl_->getString();
return string();
}
-docstring const Lexer::getDocString() const
+docstring const Lexer::getDocString(bool trim) const
{
lastReadOk_ = pimpl_->status == LEX_DATA || pimpl_->status == LEX_TOKEN;
if (lastReadOk_)
- return pimpl_->getDocString();
+ return trim ? support::trim(pimpl_->getDocString(), "\t ") : pimpl_->getDocString();
return docstring();
}
// I would prefer to give a tag number instead of an explicit token
// here, but it is not possible because Buffer::readDocument uses
// explicit tokens (JMarc)
-string const Lexer::getLongString(string const & endtoken)
+docstring Lexer::getLongString(docstring const & endtoken)
{
- string str;
- string prefix;
+ docstring str;
+ docstring prefix;
bool firstline = true;
while (pimpl_->is) { //< eatLine only reads from is, not from pushTok
if (!eatLine())
// blank line in the file being read
continue;
+ docstring tmpstr = getDocString();
+ docstring const token = trim(tmpstr, " \t");
- string const token = trim(getString(), " \t");
-
- LYXERR(Debug::PARSER, "LongString: `" << getString() << '\'');
+ LYXERR(Debug::PARSER, "LongString: `" << tmpstr << '\'');
// We do a case independent comparison, like searchKeyword does.
- if (compare_ascii_no_case(token, endtoken) == 0)
+ if (compare_no_case(token, endtoken) == 0)
break;
- string tmpstr = getString();
if (firstline) {
- size_t i = tmpstr.find_first_not_of(' ');
+ size_t i = tmpstr.find_first_not_of(from_ascii(" \t"));
if (i != string::npos)
prefix = tmpstr.substr(0, i);
firstline = false;
// further lines in long strings may have the same
// whitespace prefix as the first line. Remove it.
- if (prefix.length() && prefixIs(tmpstr, prefix))
- tmpstr.erase(0, prefix.length() - 1);
+ if (!prefix.empty() && prefixIs(tmpstr, prefix))
+ tmpstr.erase(0, prefix.length());
- str += ltrim(tmpstr, "\t") + '\n';
+ str += tmpstr + '\n';
}
if (!pimpl_->is)
- printError("Long string not ended by `" + endtoken + '\'');
+ printError("Long string not ended by `" + to_utf8(endtoken) + '\'');
return str;
}
bool Lexer::getBool() const
{
- string const s = pimpl_->getString();
+ string const s = pimpl_->getString();
if (s == "false" || s == "0") {
lastReadOk_ = true;
return false;
}
+// same for docstring
+docstring Lexer::quoteString(docstring const & arg)
+{
+ docstring res;
+ res += '"';
+ res += subst(subst(arg, from_ascii("\\"), from_ascii("\\\\")),
+ from_ascii("\""), from_ascii("\\\""));
+ res += '"';
+ return res;
+}
+
+
Lexer & Lexer::operator>>(char const * required)
{
string token;
*this >> token;
if (token != required) {
- LYXERR0("Missing '" << required << "'-tag in " << pimpl_->context
+ LYXERR0("Missing '" << required << "'-tag in " << pimpl_->context
<< ". Got " << token << " instead. Line: " << lineNumber());
pushToken(token);
}
projects / lyx.git / blobdiff