Mercurial > hgrepos > Python2 > PyMuPDF

comparison mupdf-source/thirdparty/tesseract/src/ccutil/unicharmap.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: unicharmap.h
3 // Description: Unicode character/ligature to integer id class.
4 // Author: Thomas Kielbus
5 // Created: Wed Jun 28 17:05:01 PDT 2006
6 //
7 // (C) Copyright 2006, Google Inc.
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 #ifndef TESSERACT_CCUTIL_UNICHARMAP_H_
21 #define TESSERACT_CCUTIL_UNICHARMAP_H_
22
23 #include <tesseract/unichar.h>
24
25 namespace tesseract {
26
27 // A UNICHARMAP stores unique unichars. Each of them is associated with one
28 // UNICHAR_ID.
29 class TESS_API UNICHARMAP {
30 public:
31 // Create an empty UNICHARMAP
32 UNICHARMAP();
33
34 ~UNICHARMAP();
35
36 // Insert the given unichar representation in the UNICHARMAP and associate it
37 // with the given id. The length of the representation MUST be non-zero.
38 void insert(const char *const unichar_repr, UNICHAR_ID id);
39
40 // Return the id associated with the given unichar representation,
41 // this representation MUST exist within the UNICHARMAP. The first
42 // length characters (maximum) from unichar_repr are used. The length
43 // MUST be non-zero.
44 UNICHAR_ID unichar_to_id(const char *const unichar_repr, int length) const;
45
46 // Return true if the given unichar representation is already present in the
47 // UNICHARMAP. The first length characters (maximum) from unichar_repr are
48 // used. The length MUST be non-zero.
49 bool contains(const char *const unichar_repr, int length) const;
50
51 // Return the minimum number of characters that must be used from this string
52 // to obtain a match in the UNICHARMAP.
53 int minmatch(const char *const unichar_repr) const;
54
55 // Clear the UNICHARMAP. All previous data is lost.
56 void clear();
57
58 private:
59 // The UNICHARMAP is represented as a tree whose nodes are of type
60 // UNICHARMAP_NODE.
61 struct UNICHARMAP_NODE {
62 UNICHARMAP_NODE();
63 ~UNICHARMAP_NODE();
64
65 UNICHARMAP_NODE *children;
66 UNICHAR_ID id;
67 };
68
69 UNICHARMAP_NODE *nodes;
70 };
71
72 } // namespace tesseract
73
74 #endif // TESSERACT_CCUTIL_UNICHARMAP_H_