Merge branch 'master' into devv

README.md

@@ -1,4 +1,4 @@
-# pdf2html**EX** 
+# pdf2htmlEX
 
 A beautiful demo is worth a thousand words:
 
@@ -149,11 +149,12 @@ pdf2htmlEX is inspired by the following projects:
 
 ## Contact
 
-* Lu Wang <coolwanglu@gmail.com>
+* Mailing list <pdf2htmlex@googlegroups.com>
-  * Suggestions and questions are **welcome**. 
+  * Please read [**FAQ**](https://github.com/coolwanglu/pdf2htmlEX/wiki/FAQ) before sending emails. Or your message might be ignored.
-  * Please read [**FAQ**](https://github.com/coolwanglu/pdf2htmlEX/wiki/FAQ) before sending an email to me. Or your message might be ignored.
   * Please use the **latest master branch**.
-  * Expect me to be much more user-friendly than pdf2htmlEX.
+
+* Lu Wang <coolwanglu@gmail.com>
+  * Please use the mailing list above unless for personal enquiries.
   * Accepting messages in **Chinese**, **English** or **Japanese**.
 
 

src/HTMLRenderer/general.cc

@@ -47,42 +47,6 @@ HTMLRenderer::HTMLRenderer(const Param * param)
         setErrorCallback(&dummy, nullptr);
     }
 
-    /*
-     * determine scale factors
-     */
-    {
-        double zoom = 1.0;
-
-        vector<double> zoom_factors;
-        
-        if(_is_positive(param->zoom))
-        {
-            zoom_factors.push_back(param->zoom);
-        }
-
-        if(_is_positive(param->fit_width))
-        {
-            zoom_factors.push_back((param->fit_width) / preprocessor.get_max_width());
-        }
-
-        if(_is_positive(param->fit_height))
-        {
-            zoom_factors.push_back((param->fit_height) / preprocessor.get_max_height());
-        }
-
-        if(zoom_factors.empty())
-        {
-            zoom = 1.0;
-        }
-        else
-        {
-            zoom = *min_element(zoom_factors.begin(), zoom_factors.end());
-        }
-        
-        text_scale_factor1 = max<double>(zoom, param->font_size_multiplier);  
-        text_scale_factor2 = zoom / text_scale_factor1;
-    }
-
     ffw_init(param->debug);
     cur_mapping = new int32_t [0x10000];
     cur_mapping2 = new char* [0x100];
@@ -103,12 +67,8 @@ void HTMLRenderer::process(PDFDoc *doc)
     cur_doc = doc;
     xref = doc->getXRef();
 
-    cerr << "Preprocessing: ";
+    pre_process(doc);
-    preprocessor.process(doc);
 
-
-
-    cerr << "Working: ";
     BackgroundRenderer * bg_renderer = nullptr;
     if(param->process_nontext)
     {
@@ -116,10 +76,11 @@ void HTMLRenderer::process(PDFDoc *doc)
         bg_renderer->startDoc(doc);
     }
 
-    pre_process();
+    int page_count = (param->last_page - param->first_page);
-
     for(int i = param->first_page; i <= param->last_page ; ++i) 
     {
+        cerr << "Working: " << (i-param->first_page) << "/" << page_count << '\r' << flush;
+
         if(param->split_pages)
         {
             auto page_fn = str_fmt("%s/%s%d.page", param->dest_dir.c_str(), param->output_filename.c_str(), i);
@@ -147,9 +108,10 @@ void HTMLRenderer::process(PDFDoc *doc)
         {
             html_fout.close();
         }
-
-        cerr << "." << flush;
     }
+    if(page_count >= 0)
+        cerr << "Working: " << page_count << "/" << page_count;
+    cerr << endl;
 
     post_process();
 
@@ -258,8 +220,46 @@ void HTMLRenderer::endPage() {
     html_fout << "</div></div>" << endl;
 }
 
-void HTMLRenderer::pre_process()
+void HTMLRenderer::pre_process(PDFDoc * doc)
 {
+    preprocessor.process(doc);
+
+    /*
+     * determine scale factors
+     */
+    {
+        double zoom = 1.0;
+
+        vector<double> zoom_factors;
+        
+        if(_is_positive(param->zoom))
+        {
+            zoom_factors.push_back(param->zoom);
+        }
+
+        if(_is_positive(param->fit_width))
+        {
+            zoom_factors.push_back((param->fit_width) / preprocessor.get_max_width());
+        }
+
+        if(_is_positive(param->fit_height))
+        {
+            zoom_factors.push_back((param->fit_height) / preprocessor.get_max_height());
+        }
+
+        if(zoom_factors.empty())
+        {
+            zoom = 1.0;
+        }
+        else
+        {
+            zoom = *min_element(zoom_factors.begin(), zoom_factors.end());
+        }
+        
+        text_scale_factor1 = max<double>(zoom, param->font_size_multiplier);  
+        text_scale_factor2 = zoom / text_scale_factor1;
+    }
+
     // we may output utf8 characters, so always use binary
     {
         /*

src/Preprocessor.cc

@@ -41,14 +41,17 @@ Preprocessor::~Preprocessor(void)
 
 void Preprocessor::process(PDFDoc * doc)
 {
+    int page_count = (param->last_page - param->first_page);
     for(int i = param->first_page; i <= param->last_page ; ++i) 
     {
+        cerr << "Preprocessing: " << (i-param->first_page) << "/" << page_count << '\r' << flush;
+
         doc->displayPage(this, i, DEFAULT_DPI, DEFAULT_DPI,
                 0, true, false, false,
                 nullptr, nullptr, nullptr, nullptr);
-
-        cerr << "." << flush;
     }
+    if(page_count >= 0)
+        cerr << "Preprocessing: " << page_count << "/" << page_count;
     cerr << endl;
 }
 

src/include/HTMLRenderer.h

@@ -150,7 +150,7 @@ class HTMLRenderer : public OutputDev
         ////////////////////////////////////////////////////
         // misc
         ////////////////////////////////////////////////////
-        void pre_process();
+        void pre_process(PDFDoc * doc);
         void post_process();
 
         // set flags