Mercurial > hgrepos > Python2 > PyMuPDF

diff 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
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/mupdf-source/thirdparty/gumbo-parser/examples/get_title.c	Mon Sep 15 11:43:07 2025 +0200
@@ -0,0 +1,93 @@
+// Copyright 2013 Google Inc. All Rights Reserved.
+//
+// Licensed under the Apache License, Version 2.0 (the "License");
+// you may not use this file except in compliance with the License.
+// You may obtain a copy of the License at
+//
+//     http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing, software
+// distributed under the License is distributed on an "AS IS" BASIS,
+// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+// See the License for the specific language governing permissions and
+// limitations under the License.
+//
+// Author: jdtang@google.com (Jonathan Tang)
+//
+// Retrieves the title of a page.
+
+#include <assert.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <sys/stat.h>
+
+#include "gumbo.h"
+
+static void read_file(FILE* fp, char** output, int* length) {
+  struct stat filestats;
+  int fd = fileno(fp);
+  fstat(fd, &filestats);
+  *length = filestats.st_size;
+  *output = malloc(*length + 1);
+  int start = 0;
+  int bytes_read;
+  while ((bytes_read = fread(*output + start, 1, *length - start, fp))) {
+    start += bytes_read;
+  }
+}
+
+static const char* find_title(const GumboNode* root) {
+  assert(root->type == GUMBO_NODE_ELEMENT);
+  assert(root->v.element.children.length >= 2);
+
+  const GumboVector* root_children = &root->v.element.children;
+  GumboNode* head = NULL;
+  for (int i = 0; i < root_children->length; ++i) {
+    GumboNode* child = root_children->data[i];
+    if (child->type == GUMBO_NODE_ELEMENT &&
+        child->v.element.tag == GUMBO_TAG_HEAD) {
+      head = child;
+      break;
+    }
+  }
+  assert(head != NULL);
+
+  GumboVector* head_children = &head->v.element.children;
+  for (int i = 0; i < head_children->length; ++i) {
+    GumboNode* child = head_children->data[i];
+    if (child->type == GUMBO_NODE_ELEMENT &&
+        child->v.element.tag == GUMBO_TAG_TITLE) {
+      if (child->v.element.children.length != 1) {
+        return "<empty title>";
+      }
+      GumboNode* title_text = child->v.element.children.data[0];
+      assert(title_text->type == GUMBO_NODE_TEXT || title_text->type == GUMBO_NODE_WHITESPACE);
+      return title_text->v.text.text;
+    }
+  }
+  return "<no title found>";
+}
+
+int main(int argc, const char** argv) {
+  if (argc != 2) {
+    printf("Usage: get_title <html filename>.\n");
+    exit(EXIT_FAILURE);
+  }
+  const char* filename = argv[1];
+
+  FILE* fp = fopen(filename, "r");
+  if (!fp) {
+    printf("File %s not found!\n", filename);
+    exit(EXIT_FAILURE);
+  }
+
+  char* input;
+  int input_length;
+  read_file(fp, &input, &input_length);
+  GumboOutput* output = gumbo_parse_with_options(
+      &kGumboDefaultOptions, input, input_length);
+  const char* title = find_title(output->root);
+  printf("%s\n", title);
+  gumbo_destroy_output(&kGumboDefaultOptions, output);
+  free(input);
+}