Mercurial > hgrepos > Python2 > PyMuPDF

comparison mupdf-source/thirdparty/tesseract/src/ccmain/werdit.cpp @ 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 /**********************************************************************
2 * File: werdit.cpp (Formerly wordit.c)
3 * Description: An iterator for passing over all the words in a document.
4 * Author: Ray Smith
5 * Created: Mon Apr 27 08:51:22 BST 1992
6 *
7 * (C) Copyright 1992, Hewlett-Packard Ltd.
8 ** Licensed under the Apache License, Version 2.0 (the "License");
9 ** you may not use this file except in compliance with the License.
10 ** You may obtain a copy of the License at
11 ** http://www.apache.org/licenses/LICENSE-2.0
12 ** Unless required by applicable law or agreed to in writing, software
13 ** distributed under the License is distributed on an "AS IS" BASIS,
14 ** WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
15 ** See the License for the specific language governing permissions and
16 ** limitations under the License.
17 *
18 **********************************************************************/
19
20 #include "werdit.h"
21
22 #include "errcode.h" // for ASSERT_HOST
23 #include "pageres.h" // for PAGE_RES_IT, PAGE_RES (ptr only), WERD_RES
24 #include "stepblob.h" // for C_BLOB_IT, C_BLOB, C_BLOB_LIST
25 #include "werd.h" // for WERD
26
27 namespace tesseract {
28
29 /**********************************************************************
30 * make_pseudo_word
31 *
32 * Make all the blobs inside a selection into a single word.
33 * The returned PAGE_RES_IT* it points to the new word. After use, call
34 * it->DeleteCurrentWord() to delete the fake word, and then
35 * delete it to get rid of the iterator itself.
36 **********************************************************************/
37
38 PAGE_RES_IT *make_pseudo_word(PAGE_RES *page_res, const TBOX &selection_box) {
39 PAGE_RES_IT pr_it(page_res);
40 C_BLOB_LIST new_blobs; // list of gathered blobs
41 C_BLOB_IT new_blob_it = &new_blobs; // iterator
42
43 for (WERD_RES *word_res = pr_it.word(); word_res != nullptr; word_res = pr_it.forward()) {
44 WERD *word = word_res->word;
45 if (word->bounding_box().overlap(selection_box)) {
46 C_BLOB_IT blob_it(word->cblob_list());
47 for (blob_it.mark_cycle_pt(); !blob_it.cycled_list(); blob_it.forward()) {
48 C_BLOB *blob = blob_it.data();
49 if (blob->bounding_box().overlap(selection_box)) {
50 new_blob_it.add_after_then_move(C_BLOB::deep_copy(blob));
51 }
52 }
53 if (!new_blobs.empty()) {
54 WERD *pseudo_word = new WERD(&new_blobs, 1, nullptr);
55 word_res = pr_it.InsertSimpleCloneWord(*word_res, pseudo_word);
56 auto *it = new PAGE_RES_IT(page_res);
57 while (it->word() != word_res && it->word() != nullptr) {
58 it->forward();
59 }
60 ASSERT_HOST(it->word() == word_res);
61 return it;
62 }
63 }
64 }
65 return nullptr;
66 }
67
68 } // namespace tesseract