X-Git-Url: https://git.lyx.org/gitweb/?a=blobdiff_plain;f=src%2FLexer.cpp;h=098faa9737282c3fc40458ec67665b26b8b881ef;hb=4ea6d81437ec7b5bea165d78ca37cb163e262042;hp=778a0f2218338df5e781a6feacb35da599752eee;hpb=62ca7f3ae55ad2e0c395cb554d71afab87de1ee3;p=lyx.git

diff --git a/src/Lexer.cpp b/src/Lexer.cpp
index 778a0f2218..098faa9737 100644
--- a/src/Lexer.cpp
+++ b/src/Lexer.cpp
@@ -14,6 +14,7 @@
 #include <config.h>
 
 #include "Lexer.h"
+#include "Format.h"
 
 #include "support/convert.h"
 #include "support/debug.h"
@@ -147,7 +148,7 @@ public:
 	}
 };
 
-} // end of anon namespace
+} // namespace
 
 
 Lexer::Pimpl::Pimpl(LexerKeyword * tab, int num)
@@ -238,9 +239,7 @@ void Lexer::Pimpl::popTable()
 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
@@ -274,9 +273,9 @@ bool Lexer::Pimpl::setFile(FileName const & filename)
 
 	// Skip byte order mark.
 	if (is.peek() == 0xef) {
-		int c = is.get();
+		is.get();
 		if (is.peek() == 0xbb) {
-			c = is.get();
+			is.get();
 			LASSERT(is.get() == 0xbf, /**/);
 		} else
 			is.unget();
@@ -321,12 +320,11 @@ bool Lexer::Pimpl::next(bool esc /* = false */)
 	}
 
 
-	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 :-)
@@ -349,9 +347,8 @@ bool Lexer::Pimpl::next(bool esc /* = false */)
 
 			if (esc) {
 
-				bool escaped = false;
 				do {
-					escaped = false;
+					bool escaped = false;
 					is.get(cc);
 					c = cc;
 					if (c == '\r') continue;
@@ -473,7 +470,7 @@ bool Lexer::Pimpl::eatLine()
 		is.get(cc);
 		c = cc;
 		//LYXERR(Debug::LYXLEX, "Lexer::EatLine read char: `" << c << '\'');
-		if (c != '\r')
+		if (c != '\r' && is)
 			buff.push_back(c);
 	}
 
@@ -570,7 +567,7 @@ void Lexer::Pimpl::pushToken(string const & pt)
 //////////////////////////////////////////////////////////////////////
 
 Lexer::Lexer()
-	: pimpl_(new Pimpl(0, 0))
+	: pimpl_(new Pimpl(0, 0)), lastReadOk_(false)
 {}
 
 
@@ -696,23 +693,23 @@ double Lexer::getFloat() const
 }
 
 
-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();
 }
@@ -721,28 +718,27 @@ docstring const Lexer::getDocString() const
 // 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;
@@ -751,14 +747,14 @@ string const Lexer::getLongString(string const & endtoken)
 
 		// 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;
 }
@@ -766,7 +762,7 @@ string const Lexer::getLongString(string const & endtoken)
 
 bool Lexer::getBool() const
 {
-	string const s = pimpl_->getString();	
+	string const s = pimpl_->getString();
 	if (s == "false" || s == "0") {
 		lastReadOk_ = true;
 		return false;
@@ -921,7 +917,7 @@ docstring Lexer::quoteString(docstring const & arg)
 {
 	docstring res;
 	res += '"';
-	res += subst(subst(arg, from_ascii("\\"), from_ascii("\\\\")), 
+	res += subst(subst(arg, from_ascii("\\"), from_ascii("\\\\")),
 		     from_ascii("\""), from_ascii("\\\""));
 	res += '"';
 	return res;
@@ -933,7 +929,7 @@ 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);
 	}