Merge branch 'devv' of github.com:coolwanglu/pdf2htmlEX into devv

CMakeLists.txt

@@ -39,5 +39,5 @@ add_executable(pdf2htmlEX
 target_link_libraries(pdf2htmlEX poppler boost_program_options boost_filesystem boost_system)
 
 install (TARGETS pdf2htmlEX DESTINATION bin)
-file (GLOB libfiles lib/*)
+file (GLOB datafiles share/*)
-install (FILES ${libfiles} DESTINATION lib/pdf2htmlEX)
+install (FILES ${datafiles} DESTINATION share/pdf2htmlEX)

README.md

@@ -4,6 +4,10 @@ pdf2html**EX**
 
 [**View Demo**](http://coolwanglu.github.com/pdf2htmlEX/demo/demo.html)
 
+**WINDOWS XP USERS: Please make sure ClearType is turned on** 
+
+(Control Panel -> Display -> Appearance -> Effects -> "Use the following method to smooth edges of screen fonts" -> ClearType)
+
 Introduction
 -----------------------------
 pdf2htmlEX renders PDF files in HTML, utilizing modern Web technologies, aims to provide an accuracy rendering, while keeping optimized for Web display.

src/HTMLRenderer/general.cc

@@ -112,19 +112,19 @@ void HTMLRenderer::pre_process()
         html_fout.open(dest_dir / param->output_filename, ofstream::binary); 
         allcss_fout.open(dest_dir / CSS_FILENAME, ofstream::binary);
 
-        html_fout << ifstream(PDF2HTMLEX_LIB_PATH / HEAD_HTML_FILENAME, ifstream::binary).rdbuf();
+        html_fout << ifstream(PDF2HTMLEX_DATA_PATH / HEAD_HTML_FILENAME, ifstream::binary).rdbuf();
         html_fout << "<link rel=\"stylesheet\" type=\"text/css\" href=\"" << CSS_FILENAME << "\"/>" << endl;
-        html_fout << ifstream(PDF2HTMLEX_LIB_PATH / NECK_HTML_FILENAME, ifstream::binary).rdbuf();
+        html_fout << ifstream(PDF2HTMLEX_DATA_PATH / NECK_HTML_FILENAME, ifstream::binary).rdbuf();
     }
 
-    allcss_fout << ifstream(PDF2HTMLEX_LIB_PATH / CSS_FILENAME, ifstream::binary).rdbuf();
+    allcss_fout << ifstream(PDF2HTMLEX_DATA_PATH / CSS_FILENAME, ifstream::binary).rdbuf();
 }
 
 void HTMLRenderer::post_process()
 {
     if(!param->single_html)
     {
-        html_fout << ifstream(PDF2HTMLEX_LIB_PATH / TAIL_HTML_FILENAME, ifstream::binary).rdbuf();
+        html_fout << ifstream(PDF2HTMLEX_DATA_PATH / TAIL_HTML_FILENAME, ifstream::binary).rdbuf();
     }
 
     html_fout.close();
@@ -195,17 +195,17 @@ void HTMLRenderer::process_single_html()
 {
     ofstream out (dest_dir / param->output_filename, ofstream::binary);
 
-    out << ifstream(PDF2HTMLEX_LIB_PATH / HEAD_HTML_FILENAME , ifstream::binary).rdbuf();
+    out << ifstream(PDF2HTMLEX_DATA_PATH / HEAD_HTML_FILENAME , ifstream::binary).rdbuf();
 
     out << "<style type=\"text/css\">" << endl;
     out << ifstream(tmp_dir / CSS_FILENAME, ifstream::binary).rdbuf();
     out << "</style>" << endl;
 
-    out << ifstream(PDF2HTMLEX_LIB_PATH / NECK_HTML_FILENAME, ifstream::binary).rdbuf();
+    out << ifstream(PDF2HTMLEX_DATA_PATH / NECK_HTML_FILENAME, ifstream::binary).rdbuf();
 
     out << ifstream(tmp_dir / (param->output_filename + ".part"), ifstream::binary).rdbuf();
 
-    out << ifstream(PDF2HTMLEX_LIB_PATH / TAIL_HTML_FILENAME, ifstream::binary).rdbuf();
+    out << ifstream(PDF2HTMLEX_DATA_PATH / TAIL_HTML_FILENAME, ifstream::binary).rdbuf();
 }
 
 void HTMLRenderer::add_tmp_file(const string & fn)

src/config.h.in

@@ -14,7 +14,7 @@
 
 static const std::string PDF2HTMLEX_VERSION = "@PDF2HTMLEX_VERSION@";
 static const std::string PDF2HTMLEX_PREFIX = "@CMAKE_INSTALL_PREFIX@";
-static const boost::filesystem::path PDF2HTMLEX_LIB_PATH = boost::filesystem::path(PDF2HTMLEX_PREFIX) / "lib" / "pdf2htmlEX";
+static const boost::filesystem::path PDF2HTMLEX_DATA_PATH = boost::filesystem::path(PDF2HTMLEX_PREFIX) / "share" / "pdf2htmlEX";
 
 
 #endif //CONFIG_H__

src/pdf2htmlEX.cc

@@ -172,7 +172,7 @@ int main(int argc, char **argv)
     //prepare the directories
     for(const auto & p : {param.dest_dir, param.tmp_dir})
     {
-        if(equivalent(PDF2HTMLEX_LIB_PATH, p))
+        if(equivalent(PDF2HTMLEX_DATA_PATH, p))
         {
             cerr << "The specified directory \"" << p << "\" is the library path for pdf2htmlEX. Please use another one." << endl;
             return -1;

src/util.h

@@ -43,6 +43,28 @@ static inline bool _tm_equal(const double * tm1, const double * tm2, int size =
     return true;
 }
 
+/*
+ * http://en.wikipedia.org/wiki/HTML_decimal_character_rendering
+ */
+static inline bool isLegalUnicode(Unicode u)
+{
+    /*
+    if((u == 9) || (u == 10) || (u == 13))
+        return true;
+        */
+
+    if(u <= 31) 
+        return false;
+
+    if((u >= 127) && (u <= 159))
+        return false;
+
+    if((u >= 0xd800) && (u <= 0xdfff))
+        return false;
+
+    return true;
+}
+
 static inline void outputUnicodes(std::ostream & out, const Unicode * u, int uLen)
 {
     for(int i = 0; i < uLen; ++i)