forked from coolwanglu/pdf2htmlEX
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathpdf2htmlEX.cc
More file actions
297 lines (252 loc) · 10.2 KB
/
Copy pathpdf2htmlEX.cc
File metadata and controls
297 lines (252 loc) · 10.2 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
// pdftohtmlEX.cc
//
// Copyright (C) 2012,2013 Lu Wang <coolwanglu@gmail.com>
#include <cstdio>
#include <cstdlib>
#include <cstddef>
#include <cstring>
#include <ctime>
#include <string>
#include <limits>
#include <iostream>
#include <getopt.h>
#include <poppler-config.h>
#include <goo/GooString.h>
#include <Object.h>
#include <PDFDoc.h>
#include <PDFDocFactory.h>
#include <GlobalParams.h>
#include "Param.h"
#include "pdf2htmlEX-config.h"
#include "HTMLRenderer_mp.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] <input.pdf> [<output.html>]" << endl;
argparser.show_usage(cerr);
exit(EXIT_FAILURE);
}
void show_version_and_exit(const char * dummy = nullptr)
{
cerr << "pdftohtmlEX version " << PDF2HTMLEX_VERSION << endl;
cerr << "Copyright 2012,2013 Lu Wang <coolwanglu@gmail.com>" << endl;
cerr << "Libraries: ";
cerr << "poppler " << POPPLER_VERSION << ", ";
cerr << "libfontforge " << ffw_get_version() << endl;
cerr << "Default data-dir: " << PDF2HTMLEX_DATA_PATH << endl;
exit(EXIT_SUCCESS);
}
void parse_options (int argc, char **argv)
{
string deprecated_string;
argparser
// pages
.add("first-page,f", ¶m.first_page, 1, "first page to convert")
.add("last-page,l", ¶m.last_page, numeric_limits<int>::max(), "last page to convert")
// dimensions
.add("zoom", ¶m.zoom, 0, "zoom ratio", nullptr, true)
.add("fit-width", ¶m.fit_width, 0, "fit width to <fp> pixels", nullptr, true)
.add("fit-height", ¶m.fit_height, 0, "fit height to <fp> pixels", nullptr, true)
.add("use-cropbox", ¶m.use_cropbox, 0, "use CropBox instead of MediaBox")
.add("hdpi", ¶m.h_dpi, 144.0, "horizontal resolution for graphics in DPI")
.add("vdpi", ¶m.v_dpi, 144.0, "vertical resolution for graphics in DPI")
// output files
.add("single-html", ¶m.single_html, 1, "generate a single HTML file")
.add("split-pages", ¶m.split_pages, 0, "split pages into separate files")
.add("dest-dir", ¶m.dest_dir, ".", "specify destination directory")
.add("css-filename", ¶m.css_filename, "", "filename of the generated css file")
.add("outline-filename", ¶m.outline_filename, "", "filename of the generated outline file")
// fonts
.add("embed-base-font", ¶m.embed_base_font, 0, "embed local match for standard 14 fonts")
.add("embed-external-font", ¶m.embed_external_font, 0, "embed local match for external fonts")
.add("font-suffix", ¶m.font_suffix, ".ttf", "suffix for embedded font files (.ttf,.otf,.woff,.svg)")
.add("decompose-ligature", ¶m.decompose_ligature, 0, "decompose ligatures, such as \uFB01 -> fi")
.add("remove-unused-glyph", ¶m.remove_unused_glyph, 1, "remove unused glyphs in embedded fonts")
.add("auto-hint", ¶m.auto_hint, 0, "use fontforge autohint on fonts without hints")
.add("external-hint-tool", ¶m.external_hint_tool, "", "external tool for hinting fonts (overrides --auto-hint)")
.add("stretch-narrow-glyph", ¶m.stretch_narrow_glyph, 0, "stretch narrow glyphs instead of padding them")
.add("squeeze-wide-glyph", ¶m.squeeze_wide_glyph, 1, "shrink wide glyphs instead of truncating them")
// text
.add("heps", ¶m.h_eps, 1.0, "horizontal threshold for merging text, in pixels")
.add("veps", ¶m.v_eps, 1.0, "vertical threshold for merging text, in pixels")
.add("space-threshold", ¶m.space_threshold, (1.0/8), "word break threshold (threshold * em)")
.add("font-size-multiplier", ¶m.font_size_multiplier, 4.0, "a value greater than 1 increases the rendering accuracy")
.add("space-as-offset", ¶m.space_as_offset, 0, "treat space characters as offsets")
.add("tounicode", ¶m.tounicode, 0, "how to handle ToUnicode CMaps (0=auto, 1=force, -1=ignore)")
// encryption
.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")
// misc.
.add("clean-tmp", ¶m.clean_tmp, 1, "remove temporary files after conversion")
.add("process-nontext", ¶m.process_nontext, 1, "render graphics in addition to text")
.add("data-dir", ¶m.data_dir, PDF2HTMLEX_DATA_PATH, "specify data directory")
.add("css-draw", ¶m.css_draw, 0, "[experimental and unsupported] CSS drawing")
.add("debug", ¶m.debug, 0, "print debugging information")
// meta
.add("version,v", "print copyright and version info", &show_version_and_exit)
.add("help,h", "print usage information", &show_usage_and_exit)
// multipages
.add("dump-mediabox", ¶m.dump_mediabox, 0, "dump mediaboxes of each page")
.add("set-mediabox", ¶m.set_mediabox, "", "specify new mediabox for each page, format \"x1 y1 x2 y2\"")
.add("group-by-outline", ¶m.group_by_outline, 0, "group pages according to the outline")
.add("", ¶m.input_filename, "", "")
.add("", ¶m.output_filename, "", "")
// deprecated
.add("font-format", &deprecated_string, "", "", [] (const char*) {
cerr << "warning: --font-format is deprecated, @font-face format is inferred from --font-suffix" << endl;
})
;
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 == "")
{
show_usage_and_exit();
}
//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<int>(max<int>(param.first_page, 1), doc->getNumPages());
param.last_page = min<int>(max<int>(param.last_page, param.first_page), doc->getNumPages());
if(param.output_filename.empty())
{
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.empty())
{
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";
}
}
if(param.outline_filename.empty())
{
const string s = get_filename(param.input_filename);
if(get_suffix(param.input_filename) == ".pdf")
{
param.outline_filename = s.substr(0, s.size() - 4) + ".outline";
}
else
{
if(!param.split_pages)
param.outline_filename = s + ".outline";
}
}
HTMLRenderer_mp * htmlOut = new HTMLRenderer_mp(¶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;
}