Mercurial > hgrepos > Python2 > PyMuPDF

comparison mupdf-source/thirdparty/tesseract/src/textord/workingpartset.h @ 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: workingpartset.h
3 // Description: Class to hold a working set of partitions of the page
4 // during construction of text/image regions.
5 // Author: Ray Smith
6 // Created: Tue Ocr 28 17:21:01 PDT 2008
7 //
8 // (C) Copyright 2008, Google Inc.
9 // Licensed under the Apache License, Version 2.0 (the "License");
10 // you may not use this file except in compliance with the License.
11 // You may obtain a copy of the License at
12 // http://www.apache.org/licenses/LICENSE-2.0
13 // Unless required by applicable law or agreed to in writing, software
14 // distributed under the License is distributed on an "AS IS" BASIS,
15 // WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
16 // See the License for the specific language governing permissions and
17 // limitations under the License.
18 //
19 ///////////////////////////////////////////////////////////////////////
20
21 #ifndef TESSERACT_TEXTORD_WORKINGPARSET_H_
22 #define TESSERACT_TEXTORD_WORKINGPARSET_H_
23
24 #include "blobbox.h" // For TO_BLOCK_LIST and BLOCK_LIST.
25 #include "colpartition.h" // For ColPartition_LIST.
26
27 namespace tesseract {
28
29 // WorkingPartSet holds a working set of ColPartitions during transformation
30 // from the grid-based storage to regions in logical reading order, and is
31 // therefore only used during construction of the regions.
32 class WorkingPartSet : public ELIST_LINK {
33 public:
34 explicit WorkingPartSet(ColPartition *column)
35 : column_(column), latest_part_(nullptr), part_it_(&part_set_) {}
36
37 // Simple accessors.
38 ColPartition *column() const {
39 return column_;
40 }
41 void set_column(ColPartition *col) {
42 column_ = col;
43 }
44
45 // Add the partition to this WorkingPartSet. Partitions are generally
46 // stored in the order in which they are received, but if the partition
47 // has a SingletonPartner, make sure that it stays with its partner.
48 void AddPartition(ColPartition *part);
49
50 // Make blocks out of any partitions in this WorkingPartSet, and append
51 // them to the end of the blocks list. bleft, tright and resolution give
52 // the bounds and resolution of the source image, so that blocks can be
53 // made to fit in the bounds.
54 // All ColPartitions go in the used_parts list, as they need to be kept
55 // around, but are no longer needed.
56 void ExtractCompletedBlocks(const ICOORD &bleft, const ICOORD &tright, int resolution,
57 ColPartition_LIST *used_parts, BLOCK_LIST *blocks,
58 TO_BLOCK_LIST *to_blocks);
59
60 // Insert the given blocks at the front of the completed_blocks_ list so
61 // they can be kept in the correct reading order.
62 void InsertCompletedBlocks(BLOCK_LIST *blocks, TO_BLOCK_LIST *to_blocks);
63
64 private:
65 // Convert the part_set_ into blocks, starting a new block at a break
66 // in partnerships, or a change in linespacing (for text).
67 void MakeBlocks(const ICOORD &bleft, const ICOORD &tright, int resolution,
68 ColPartition_LIST *used_parts);
69
70 // The column that this working set applies to. Used by the caller.
71 ColPartition *column_;
72 // The most recently added partition.
73 ColPartition *latest_part_;
74 // All the partitions in the block that is currently under construction.
75 ColPartition_LIST part_set_;
76 // Iteratorn on part_set_ pointing to the most recent addition.
77 ColPartition_IT part_it_;
78 // The blocks that have been made so far and belong before the current block.
79 BLOCK_LIST completed_blocks_;
80 TO_BLOCK_LIST to_blocks_;
81 };
82
83 ELISTIZEH(WorkingPartSet)
84
85 } // namespace tesseract.
86
87 #endif // TESSERACT_TEXTORD_WORKINGPARSET_H_