Mercurial > hgrepos > Python2 > PyMuPDF

comparison mupdf-source/source/tools/pdfpages.c @ 2:b50eed0cc0ef upstream

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
ADD: MuPDF v1.26.7: the MuPDF source as downloaded by a default build of PyMuPDF 1.26.4. The directory name has changed: no version number in the expanded directory now.
author Franz Glasner <fzglas.hg@dom66.de>
date Mon, 15 Sep 2025 11:43:07 +0200
parents
children
comparison
equal deleted inserted replaced
1:1d09e1dec1d9 2:b50eed0cc0ef
1 // Copyright (C) 2004-2021 Artifex Software, Inc.
2 //
3 // This file is part of MuPDF.
4 //
5 // MuPDF is free software: you can redistribute it and/or modify it under the
6 // terms of the GNU Affero General Public License as published by the Free
7 // Software Foundation, either version 3 of the License, or (at your option)
8 // any later version.
9 //
10 // MuPDF is distributed in the hope that it will be useful, but WITHOUT ANY
11 // WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
12 // FOR A PARTICULAR PURPOSE. See the GNU Affero General Public License for more
13 // details.
14 //
15 // You should have received a copy of the GNU Affero General Public License
16 // along with MuPDF. If not, see <https://www.gnu.org/licenses/agpl-3.0.en.html>
17 //
18 // Alternative licensing terms are available from the licensor.
19 // For commercial licensing, see <https://www.artifex.com/> or contact
20 // Artifex Software, Inc., 39 Mesa Street, Suite 108A, San Francisco,
21 // CA 94129, USA, for further information.
22
23 /*
24 * Information tool.
25 * Print information about pages of a pdf.
26 */
27
28 #include "mupdf/fitz.h"
29 #include "mupdf/pdf.h"
30
31 #include <stdlib.h>
32 #include <stdio.h>
33
34 static int
35 infousage(void)
36 {
37 fprintf(stderr,
38 "usage: mutool pages [options] file.pdf [pages]\n"
39 "\t-p -\tpassword for decryption\n"
40 "\tpages\tcomma separated list of page numbers and ranges\n"
41 );
42 return 1;
43 }
44
45 static int
46 showbox(fz_context *ctx, fz_output *out, pdf_obj *page, char *text, pdf_obj *name)
47 {
48 fz_rect bbox;
49 pdf_obj *obj;
50 int failed = 0;
51
52 fz_try(ctx)
53 {
54 obj = pdf_dict_get(ctx, page, name);
55 if (!pdf_is_array(ctx, obj))
56 break;
57
58 bbox = pdf_to_rect(ctx, obj);
59
60 fz_write_printf(ctx, out, "<%s l=\"%g\" b=\"%g\" r=\"%g\" t=\"%g\" />\n", text, bbox.x0, bbox.y0, bbox.x1, bbox.y1);
61 }
62 fz_catch(ctx)
63 {
64 failed = 1;
65 }
66
67 return failed;
68 }
69
70 static int
71 shownum(fz_context *ctx, fz_output *out, pdf_obj *page, char *text, pdf_obj *name)
72 {
73 pdf_obj *obj;
74 int failed = 0;
75
76 fz_try(ctx)
77 {
78 obj = pdf_dict_get(ctx, page, name);
79 if (!pdf_is_number(ctx, obj))
80 break;
81
82 fz_write_printf(ctx, out, "<%s v=\"%g\" />\n", text, pdf_to_real(ctx, obj));
83 }
84 fz_catch(ctx)
85 {
86 failed = 1;
87 }
88
89 return failed;
90 }
91
92 static int
93 showpage(fz_context *ctx, pdf_document *doc, fz_output *out, int page)
94 {
95 pdf_obj *pageref;
96 int failed = 0;
97
98 fz_write_printf(ctx, out, "<page pagenum=\"%d\">\n", page);
99 fz_try(ctx)
100 {
101 pageref = pdf_lookup_page_obj(ctx, doc, page-1);
102 if (!pageref)
103 fz_throw(ctx, FZ_ERROR_GENERIC, "cannot retrieve info from page %d", page);
104 }
105 fz_catch(ctx)
106 {
107 fz_write_printf(ctx, out, "Failed to gather information for page %d\n", page);
108 failed = 1;
109 }
110
111 if (!failed)
112 {
113 failed |= showbox(ctx, out, pageref, "MediaBox", PDF_NAME(MediaBox));
114 failed |= showbox(ctx, out, pageref, "CropBox", PDF_NAME(CropBox));
115 failed |= showbox(ctx, out, pageref, "ArtBox", PDF_NAME(ArtBox));
116 failed |= showbox(ctx, out, pageref, "BleedBox", PDF_NAME(BleedBox));
117 failed |= showbox(ctx, out, pageref, "TrimBox", PDF_NAME(TrimBox));
118 failed |= shownum(ctx, out, pageref, "Rotate", PDF_NAME(Rotate));
119 failed |= shownum(ctx, out, pageref, "UserUnit", PDF_NAME(UserUnit));
120 }
121
122 fz_write_printf(ctx, out, "</page>\n");
123
124 return failed;
125 }
126
127 static int
128 showpages(fz_context *ctx, pdf_document *doc, fz_output *out, const char *pagelist)
129 {
130 int page, spage, epage;
131 int pagecount;
132 int ret = 0;
133
134 if (!doc)
135 return infousage();
136
137 pagecount = pdf_count_pages(ctx, doc);
138 while ((pagelist = fz_parse_page_range(ctx, pagelist, &spage, &epage, pagecount)))
139 {
140 int fail;
141 if (spage > epage)
142 page = spage, spage = epage, epage = page;
143 for (page = spage; page <= epage; page++)
144 {
145 fail = showpage(ctx, doc, out, page);
146 /* On the first failure, check for the pagecount having changed. */
147 if (fail && !ret)
148 {
149 pagecount = pdf_count_pages(ctx, doc);
150 if (epage > pagecount)
151 epage = pagecount;
152 }
153 ret |= fail;
154 }
155 }
156
157 return ret;
158 }
159
160 static int
161 pdfpages_pages(fz_context *ctx, fz_output *out, char *filename, char *password, char *argv[], int argc)
162 {
163 enum { NO_FILE_OPENED, NO_INFO_GATHERED, INFO_SHOWN } state;
164 int argidx = 0;
165 pdf_document *doc = NULL;
166 int ret = 0;
167
168 state = NO_FILE_OPENED;
169 while (argidx < argc)
170 {
171 if (state == NO_FILE_OPENED || !fz_is_page_range(ctx, argv[argidx]))
172 {
173 if (state == NO_INFO_GATHERED)
174 {
175 showpages(ctx, doc, out, "1-N");
176 }
177
178 pdf_drop_document(ctx, doc);
179
180 filename = argv[argidx];
181 fz_write_printf(ctx, out, "%s:\n", filename);
182 doc = pdf_open_document(ctx, filename);
183 if (pdf_needs_password(ctx, doc))
184 if (!pdf_authenticate_password(ctx, doc, password))
185 fz_throw(ctx, FZ_ERROR_ARGUMENT, "cannot authenticate password: %s", filename);
186
187 state = NO_INFO_GATHERED;
188 }
189 else
190 {
191 ret |= showpages(ctx, doc, out, argv[argidx]);
192 state = INFO_SHOWN;
193 }
194
195 argidx++;
196 }
197
198 if (state == NO_INFO_GATHERED)
199 showpages(ctx, doc, out, "1-N");
200
201 pdf_drop_document(ctx, doc);
202
203 return ret;
204 }
205
206 int pdfpages_main(int argc, char **argv)
207 {
208 char *filename = "";
209 char *password = "";
210 int c;
211 int ret;
212 fz_context *ctx;
213
214 while ((c = fz_getopt(argc, argv, "p:")) != -1)
215 {
216 switch (c)
217 {
218 case 'p': password = fz_optarg; break;
219 default:
220 return infousage();
221 }
222 }
223
224 if (fz_optind == argc)
225 return infousage();
226
227 ctx = fz_new_context(NULL, NULL, FZ_STORE_UNLIMITED);
228 if (!ctx)
229 {
230 fprintf(stderr, "cannot initialise context\n");
231 exit(1);
232 }
233
234 ret = 0;
235 fz_try(ctx)
236 ret = pdfpages_pages(ctx, fz_stdout(ctx), filename, password, &argv[fz_optind], argc-fz_optind);
237 fz_catch(ctx)
238 {
239 fz_report_error(ctx);
240 ret = 1;
241 }
242 fz_drop_context(ctx);
243 return ret;
244 }