/src/tesseract/src/ccmain/werdit.cpp
Line | Count | Source |
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 | 0 | PAGE_RES_IT *make_pseudo_word(PAGE_RES *page_res, const TBOX &selection_box) { |
39 | 0 | PAGE_RES_IT pr_it(page_res); |
40 | 0 | C_BLOB_LIST new_blobs; // list of gathered blobs |
41 | 0 | C_BLOB_IT new_blob_it = &new_blobs; // iterator |
42 | |
|
43 | 0 | for (WERD_RES *word_res = pr_it.word(); word_res != nullptr; word_res = pr_it.forward()) { |
44 | 0 | WERD *word = word_res->word; |
45 | 0 | if (word->bounding_box().overlap(selection_box)) { |
46 | 0 | C_BLOB_IT blob_it(word->cblob_list()); |
47 | 0 | for (blob_it.mark_cycle_pt(); !blob_it.cycled_list(); blob_it.forward()) { |
48 | 0 | C_BLOB *blob = blob_it.data(); |
49 | 0 | if (blob->bounding_box().overlap(selection_box)) { |
50 | 0 | new_blob_it.add_after_then_move(C_BLOB::deep_copy(blob)); |
51 | 0 | } |
52 | 0 | } |
53 | 0 | if (!new_blobs.empty()) { |
54 | 0 | WERD *pseudo_word = new WERD(&new_blobs, 1, nullptr); |
55 | 0 | word_res = pr_it.InsertSimpleCloneWord(*word_res, pseudo_word); |
56 | 0 | auto *it = new PAGE_RES_IT(page_res); |
57 | 0 | while (it->word() != word_res && it->word() != nullptr) { |
58 | 0 | it->forward(); |
59 | 0 | } |
60 | 0 | ASSERT_HOST(it->word() == word_res); |
61 | 0 | return it; |
62 | 0 | } |
63 | 0 | } |
64 | 0 | } |
65 | 0 | return nullptr; |
66 | 0 | } |
67 | | |
68 | | } // namespace tesseract |