// pdftohtmlEX.cc
//
// Copyright (C) 2012,2013 Lu Wang
#include
#include
#include
#include
#include
#include
#include
#include
#include
#include
#include
#include
#include
#include
#include
#include "Param.h"
#include "pdf2htmlEX-config.h"
#include "HTMLRenderer/HTMLRenderer.h"
#include "util/ArgParser.h"
#include "util/path.h"
#include "util/ffw.h"
using namespace std;
using namespace pdf2htmlEX;
Param param;
ArgParser argparser;
void show_usage_and_exit(const char * dummy = nullptr)
{
cerr << "Usage: pdf2htmlEX [Options] []" << endl;
cerr << endl;
cerr << "Options:" << endl;
argparser.show_usage(cerr);
cerr << endl;
cerr << "Run 'man pdf2htmlEX' for detailed information" << endl;
cerr << endl;
exit(EXIT_FAILURE);
}
void show_version_and_exit(const char * dummy = nullptr)
{
cerr << "pdftohtmlEX version " << PDF2HTMLEX_VERSION << endl;
cerr << "Copyright 2012,2013 Lu Wang " << endl;
cerr << "Libraries: ";
cerr << "poppler " << POPPLER_VERSION << ", ";
cerr << "libfontforge " << ffw_get_version() << endl;
exit(EXIT_FAILURE);
}
void parse_options (int argc, char **argv)
{
argparser
.add("help,h", "show all options", &show_usage_and_exit)
.add("version,v", "show copyright and version info", &show_version_and_exit)
.add("owner-password,o", ¶m.owner_password, "", "owner password (for encrypted files)", nullptr, true)
.add("user-password,u", ¶m.user_password, "", "user password (for encrypted files)", nullptr, true)
.add("no-drm", ¶m.no_drm, 0, "override document DRM settings")
.add("dest-dir", ¶m.dest_dir, ".", "specify destination directory")
.add("data-dir", ¶m.data_dir, PDF2HTMLEX_DATA_PATH, "specify data directory")
.add("first-page,f", ¶m.first_page, 1, "first page to process")
.add("last-page,l", ¶m.last_page, numeric_limits::max(), "last page to process")
.add("zoom", ¶m.zoom, 0, "zoom ratio", nullptr, true)
.add("fit-width", ¶m.fit_width, 0, "fit width to pixels", nullptr, true)
.add("fit-height", ¶m.fit_height, 0, "fit height to pixels", nullptr, true)
.add("hdpi", ¶m.h_dpi, 144.0, "horizontal DPI for non-text")
.add("vdpi", ¶m.v_dpi, 144.0, "vertical DPI for non-text")
.add("use-cropbox", ¶m.use_cropbox, 0, "use CropBox instead of MediaBox")
.add("process-nontext", ¶m.process_nontext, 1, "process nontext objects")
.add("single-html", ¶m.single_html, 1, "combine everything into one single HTML file")
.add("split-pages", ¶m.split_pages, 0, "split pages into separated files")
.add("embed-base-font", ¶m.embed_base_font, 0, "embed local matched font for base 14 fonts in the PDF file")
.add("embed-external-font", ¶m.embed_external_font, 0, "embed local matched font for external fonts in the PDF file")
.add("decompose-ligature", ¶m.decompose_ligature, 0, "decompose ligatures, for example 'fi' -> 'f''i'")
.add("heps", ¶m.h_eps, 1.0, "max tolerated horizontal offset (in pixels)")
.add("veps", ¶m.v_eps, 1.0, "max tolerated vertical offset (in pixels)")
.add("space-threshold", ¶m.space_threshold, (1.0/8), "distance no thiner than (threshold * em) will be considered as a space character")
.add("font-size-multiplier", ¶m.font_size_multiplier, 4.0, "setting a value greater than 1 would increase the rendering accuracy")
.add("auto-hint", ¶m.auto_hint, 0, "Whether to generate hints for fonts")
.add("tounicode", ¶m.tounicode, 0, "Specify how to deal with ToUnicode map, 0 for auto, 1 for forced, -1 for disabled")
.add("space-as-offset", ¶m.space_as_offset, 0, "treat space characters as offsets")
.add("stretch-narrow-glyph", ¶m.stretch_narrow_glyph, 0, "stretch narrow glyphs instead of padding space")
.add("squeeze-wide-glyph", ¶m.squeeze_wide_glyph, 1, "squeeze wide glyphs instead of truncating")
.add("remove-unused-glyph", ¶m.remove_unused_glyph, 1, "remove unused glyphs in embedded fonts")
.add("font-suffix", ¶m.font_suffix, ".ttf", "suffix for extracted font files")
.add("font-format", ¶m.font_format, "opentype", "format for extracted font files")
.add("external-hint-tool", ¶m.external_hint_tool, "", "external tool for hintting fonts.(overrides --auto-hint)")
.add("css-filename", ¶m.css_filename, "", "Specify the file name of the generated css file")
.add("debug", ¶m.debug, 0, "output debug information")
.add("clean-tmp", ¶m.clean_tmp, 1, "clean temporary files after processing")
.add("css-draw", ¶m.css_draw, 0, "[Experimental and Unsupported] CSS Drawing")
.add("", ¶m.input_filename, "", "")
.add("", ¶m.output_filename, "", "")
;
try
{
argparser.parse(argc, argv);
}
catch(const char * s)
{
// if s == "", getopt_long would have printed the error message
if(s && s[0])
{
cerr << "Error when parsing the arguments:" << endl;
cerr << s << endl;
}
exit(EXIT_FAILURE);
}
catch(const std::string & s)
{
// if s == "", getopt_long would have printed the error message
if(s != "")
{
cerr << "Error when parsing the arguments:" << endl;
cerr << s << endl;
}
exit(EXIT_FAILURE);
}
}
int main(int argc, char **argv)
{
parse_options(argc, argv);
if (param.input_filename == "")
{
cerr << "Missing input filename" << endl;
exit(EXIT_FAILURE);
}
//prepare the directories
{
char buf[] = "/tmp/pdf2htmlEX-XXXXXX";
auto p = mkdtemp(buf);
if(p == nullptr)
{
cerr << "Cannot create temp directory" << endl;
exit(EXIT_FAILURE);
}
param.tmp_dir = buf;
}
if(param.debug)
cerr << "temporary dir: " << (param.tmp_dir) << endl;
try
{
create_directories(param.dest_dir);
}
catch (const string & s)
{
cerr << s << endl;
exit(EXIT_FAILURE);
}
bool finished = false;
// read config file
globalParams = new GlobalParams();
// open PDF file
PDFDoc *doc = nullptr;
try
{
{
GooString * ownerPW = (param.owner_password == "") ? (nullptr) : (new GooString(param.owner_password.c_str()));
GooString * userPW = (param.user_password == "") ? (nullptr) : (new GooString(param.user_password.c_str()));
GooString fileName(param.input_filename.c_str());
doc = PDFDocFactory().createPDFDoc(fileName, ownerPW, userPW);
delete userPW;
delete ownerPW;
}
if (!doc->isOk()) {
throw "Cannot read the file";
}
// check for copy permission
if (!doc->okToCopy()) {
if (param.no_drm == 0) {
throw "Copying of text from this document is not allowed.";
}
cerr << "Document has copy-protection bit set." << endl;
}
param.first_page = min(max(param.first_page, 1), doc->getNumPages());
param.last_page = min(max(param.last_page, param.first_page), doc->getNumPages());
if(param.output_filename == "")
{
const string s = get_filename(param.input_filename);
if(get_suffix(param.input_filename) == ".pdf")
{
if(param.split_pages)
param.output_filename = s.substr(0, s.size() - 4);
else
param.output_filename = s.substr(0, s.size() - 4) + ".html";
}
else
{
if(param.split_pages)
param.output_filename = s;
else
param.output_filename = s + ".html";
}
}
if(param.css_filename == "")
{
const string s = get_filename(param.input_filename);
if(get_suffix(param.input_filename) == ".pdf")
{
param.css_filename = s.substr(0, s.size() - 4) + ".css";
}
else
{
if(!param.split_pages)
param.css_filename = s + ".css";
}
}
HTMLRenderer * htmlOut = new HTMLRenderer(¶m);
htmlOut->process(doc);
delete htmlOut;
finished = true;
}
catch (const char * s)
{
cerr << "Error: " << s << endl;
}
catch (const string & s)
{
cerr << "Error: " << s << endl;
}
// clean up
if(doc) delete doc;
if(globalParams) delete globalParams;
// check for memory leaks
Object::memCheck(stderr);
gMemReport(stderr);
exit(finished ? (EXIT_SUCCESS) : (EXIT_FAILURE));
return 0;
}