Mercurial > hgrepos > Python2 > PyMuPDF

comparison mupdf-source/thirdparty/gumbo-parser/examples/get_title.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 2013 Google Inc. All Rights Reserved.
2 //
3 // Licensed under the Apache License, Version 2.0 (the "License");
4 // you may not use this file except in compliance with the License.
5 // You may obtain a copy of the License at
6 //
7 // http://www.apache.org/licenses/LICENSE-2.0
8 //
9 // Unless required by applicable law or agreed to in writing, software
10 // distributed under the License is distributed on an "AS IS" BASIS,
11 // WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
12 // See the License for the specific language governing permissions and
13 // limitations under the License.
14 //
15 // Author: jdtang@google.com (Jonathan Tang)
16 //
17 // Retrieves the title of a page.
18
19 #include <assert.h>
20 #include <stdio.h>
21 #include <stdlib.h>
22 #include <sys/stat.h>
23
24 #include "gumbo.h"
25
26 static void read_file(FILE* fp, char** output, int* length) {
27 struct stat filestats;
28 int fd = fileno(fp);
29 fstat(fd, &filestats);
30 *length = filestats.st_size;
31 *output = malloc(*length + 1);
32 int start = 0;
33 int bytes_read;
34 while ((bytes_read = fread(*output + start, 1, *length - start, fp))) {
35 start += bytes_read;
36 }
37 }
38
39 static const char* find_title(const GumboNode* root) {
40 assert(root->type == GUMBO_NODE_ELEMENT);
41 assert(root->v.element.children.length >= 2);
42
43 const GumboVector* root_children = &root->v.element.children;
44 GumboNode* head = NULL;
45 for (int i = 0; i < root_children->length; ++i) {
46 GumboNode* child = root_children->data[i];
47 if (child->type == GUMBO_NODE_ELEMENT &&
48 child->v.element.tag == GUMBO_TAG_HEAD) {
49 head = child;
50 break;
51 }
52 }
53 assert(head != NULL);
54
55 GumboVector* head_children = &head->v.element.children;
56 for (int i = 0; i < head_children->length; ++i) {
57 GumboNode* child = head_children->data[i];
58 if (child->type == GUMBO_NODE_ELEMENT &&
59 child->v.element.tag == GUMBO_TAG_TITLE) {
60 if (child->v.element.children.length != 1) {
61 return "<empty title>";
62 }
63 GumboNode* title_text = child->v.element.children.data[0];
64 assert(title_text->type == GUMBO_NODE_TEXT || title_text->type == GUMBO_NODE_WHITESPACE);
65 return title_text->v.text.text;
66 }
67 }
68 return "<no title found>";
69 }
70
71 int main(int argc, const char** argv) {
72 if (argc != 2) {
73 printf("Usage: get_title <html filename>.\n");
74 exit(EXIT_FAILURE);
75 }
76 const char* filename = argv[1];
77
78 FILE* fp = fopen(filename, "r");
79 if (!fp) {
80 printf("File %s not found!\n", filename);
81 exit(EXIT_FAILURE);
82 }
83
84 char* input;
85 int input_length;
86 read_file(fp, &input, &input_length);
87 GumboOutput* output = gumbo_parse_with_options(
88 &kGumboDefaultOptions, input, input_length);
89 const char* title = find_title(output->root);
90 printf("%s\n", title);
91 gumbo_destroy_output(&kGumboDefaultOptions, output);
92 free(input);
93 }