DenysMedvid/pdf2htmlEX
1
0
Fork 0
mirror of https://github.com/pdf2htmlEX/pdf2htmlEX.git synced 2024-12-22 04:50:09 +00:00
Code

do not reencode external fonts

Browse Source
This commit is contained in:
Lu Wang 2013-05-03 01:47:55 +08:00
parent 7f8bd3b5b5
commit 9d69539fe5
4 changed files with 21 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
TODO
View File

@ -1,7 +1,4 @@
pc1.pdf
jyb.pdf
cjkmix2*.pdf
Sample4.pdf
- optimization levels
- don't dump image when it is empty

25
src/HTMLRenderer/font.cc
View File

@ -45,7 +45,7 @@ string HTMLRenderer::dump_embedded_font (GfxFont * font, long long fn_id)
try
{
// mupdf consulted
// inspired by mupdf
string subtype;
auto * id = font->getID();
@ -448,6 +448,13 @@ void HTMLRenderer::embed_font(const string & filepath, GfxFont * font, FontInfo
ffw_set_widths(width_list, max_key + 1, param.stretch_narrow_glyph, param.squeeze_wide_glyph, param.remove_unused_glyph);
/*
* Reencoding is not likely to work for external fonts,
* Just hope that we can get correct Unicode values, and let the browser choose the correct glyphs
*
* TODO: maybe add an option here, but anyway according to the DPF spec, this is implement-dependent
*/
if(info.is_embeded)
ffw_reencode_raw(cur_mapping, max_key + 1, 1);
// In some space offsets in HTML, we insert a ' ' there in order to improve text copy&paste
@ -467,7 +474,7 @@ void HTMLRenderer::embed_font(const string & filepath, GfxFont * font, FontInfo
ffw_add_empty_char((int32_t)' ', (int)floor(info.space_width * info.em_size + 0.5));
if(param.debug)
{
cerr << "Missing space width in font: " << hex << info.id << " set to " << dec << info.space_width << endl;
cerr << "Missing space width in font " << hex << info.id << ": set to " << dec << info.space_width << endl;
}
}
@ -556,6 +563,7 @@ const FontInfo * HTMLRenderer::install_font(GfxFont * font)
FontInfo & new_font_info = cur_info_iter->second;
new_font_info.id = new_fn_id;
new_font_info.use_tounicode = true;
new_font_info.is_embeded = false;
if(font == nullptr)
{
@ -582,12 +590,12 @@ const FontInfo * HTMLRenderer::install_font(GfxFont * font)
if(font->getType() == fontType3) {
cerr << "Type 3 fonts are unsupported and will be rendered as Image" << endl;
export_remote_default_font(new_fn_id);
return &(cur_info_iter->second);
return &new_font_info;
}
if(font->getWMode()) {
cerr << "Writing mode is unsupported and will be rendered as Image" << endl;
export_remote_default_font(new_fn_id);
return &(cur_info_iter->second);
return &new_font_info;
}
if(auto * font_loc = font->locateFont(xref, gTrue))
@ -595,13 +603,16 @@ const FontInfo * HTMLRenderer::install_font(GfxFont * font)
switch(font_loc -> locType)
{
case gfxFontLocEmbedded:
install_embedded_font(font, cur_info_iter->second);
new_font_info.is_embeded = true;
install_embedded_font(font, new_font_info);
break;
case gfxFontLocExternal:
install_external_font(font, cur_info_iter->second);
new_font_info.is_embeded = false;
install_external_font(font, new_font_info);
break;
case gfxFontLocResident:
install_base_font(font, font_loc, cur_info_iter->second);
new_font_info.is_embeded = false;
install_base_font(font, font_loc, new_font_info);
break;
default:
cerr << "TODO: other font loc" << endl;

1
src/HTMLState.h
View File

@ -17,6 +17,7 @@ struct FontInfo
double space_width;
double ascent, descent;
bool is_type3;
bool is_embeded;
};
struct HTMLTextState

2
test/test.py
View File

@ -13,7 +13,7 @@ with open('out.html','w') as outf:
if not f.lower().endswith('.pdf'):
continue
print f
if os.system('pdf2htmlEX -l 10 --no-drm 1 --fit-width 1024 --dest-dir html --auto-hint=1 --external-hint-tool="ttfautohint" "%s/%s"' % (DIR,f)) != 0:
if os.system('pdf2htmlEX -l 10 --no-drm 1 --fit-width 1024 --dest-dir html --external-hint-tool="ttfautohint" "%s/%s"' % (DIR,f)) != 0:
print "error on ", f
sys.exit(-1)