MsWrdText.hxx
Go to the documentation of this file.
1/* -*- Mode: C++; c-default-style: "k&r"; indent-tabs-mode: nil; tab-width: 2; c-basic-offset: 2 -*- */
2
3/* libmwaw
4* Version: MPL 2.0 / LGPLv2+
5*
6* The contents of this file are subject to the Mozilla Public License Version
7* 2.0 (the "License"); you may not use this file except in compliance with
8* the License or as specified alternatively below. You may obtain a copy of
9* the License at http://www.mozilla.org/MPL/
10*
11* Software distributed under the License is distributed on an "AS IS" basis,
12* WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License
13* for the specific language governing rights and limitations under the
14* License.
15*
16* Major Contributor(s):
17* Copyright (C) 2002 William Lachance (wrlach@gmail.com)
18* Copyright (C) 2002,2004 Marc Maurer (uwog@uwog.net)
19* Copyright (C) 2004-2006 Fridrich Strba (fridrich.strba@bluewin.ch)
20* Copyright (C) 2006, 2007 Andrew Ziem
21* Copyright (C) 2011, 2012 Alonso Laurent (alonso@loria.fr)
22*
23*
24* All Rights Reserved.
25*
26* For minor contributions see the git repository.
27*
28* Alternatively, the contents of this file may be used under the terms of
29* the GNU Lesser General Public License Version 2 or later (the "LGPLv2+"),
30* in which case the provisions of the LGPLv2+ are applicable
31* instead of those above.
32*/
33
34/*
35 * Parser to Microsoft Word text document
36 *
37 */
38#ifndef MS_WRD_MWAW_TEXT
39# define MS_WRD_MWAW_TEXT
40
41#include <map>
42#include <string>
43#include <vector>
44
45#include "libmwaw_internal.hxx"
46
47#include "MWAWEntry.hxx"
48
49#include "MWAWDebug.hxx"
50
51#include "MsWrdTextStyles.hxx"
52
53namespace MsWrdTextInternal
54{
55struct State;
56struct Table;
57}
58
59struct MsWrdEntry;
60class MsWrdParser;
61class MsWrdTextStyles;
62
65{
66 friend class MsWrdParser;
67 friend class MsWrdTextStyles;
68public:
70 struct PLC {
72 PLC(Type type, int id=0) : m_type(type), m_id(id), m_extra("")
73 {
74 }
76 friend std::ostream &operator<<(std::ostream &o, PLC const &plc);
78 struct ltstr {
79 bool operator()(PLC const &s1, PLC const &s2) const
80 {
81 if (s1.m_type != s2.m_type)
82 return int(s1.m_type) < int(s2.m_type);
83 if (s1.m_id != s2.m_id)
84 return s1.m_id < s2.m_id;
85 return false;
86 }
87 };
91 int m_id;
93 std::string m_extra;
94 };
95public:
97 explicit MsWrdText(MsWrdParser &parser);
99 virtual ~MsWrdText();
100
102 int version() const;
103
105 int numPages() const;
106
108 MWAWEntry getHeader() const;
109
111 MWAWEntry getFooter() const;
112protected:
114 shared_ptr<MWAWParserState> &getParserState()
115 {
116 return m_parserState;
117 }
118
120 bool sendMainText();
121
123 bool sendText(MWAWEntry const &textEntry, bool mainZone, bool tableCell=false);
125 bool sendSection(int sectionId);
128
130 bool createZones(long bot);
131
133 bool readTextStruct(MsWrdEntry &entry);
134
136 bool readPageBreak(MsWrdEntry &entry);
137
139 bool readParagraphInfo(MsWrdEntry &entry);
140
142 bool readFields(MsWrdEntry &entry, std::vector<long> const &fieldPos);
143
145 bool sendFieldComment(int id);
146
148 bool readFootnotesPos(MsWrdEntry &entry, std::vector<long> const &noteDef);
149
151 bool readFootnotesData(MsWrdEntry &entry);
152
154 bool sendFootnote(int id);
155
157 bool readFontNames(MsWrdEntry &entry);
158
160 void flushExtra();
161
163 bool sendTable(MsWrdTextInternal::Table const &table);
164
165 // interface with MsWrdTextStyles
166
168 long getMainTextLength() const;
170 std::multimap<long, MsWrdText::PLC> &getTextPLCMap();
172 std::multimap<long, MsWrdText::PLC> &getFilePLCMap();
173
174 //
175 // low level
176 //
177
179 void prepareData();
180
182 void prepareLines();
184 void convertFilePLCPos();
189
191 void prepareTableLimits();
193 bool updateTableBeginnningAt(long cPos, long &nextCPos);
194
196 bool readLongZone(MsWrdEntry &entry, int sz, std::vector<long> &list);
197
198private:
199 MsWrdText(MsWrdText const &orig);
201
202protected:
203 //
204 // data
205 //
208
210 shared_ptr<MsWrdTextInternal::State> m_state;
211
213 shared_ptr<MsWrdTextStyles> m_stylesManager;
214
217};
218#endif
219// vim: set filetype=cpp tabstop=2 shiftwidth=2 cindent autoindent smartindent noexpandtab:
basic class to store an entry in a file This contained :
Definition: MWAWEntry.hxx:47
the main class to read a Microsoft Word file
Definition: MsWrdParser.hxx:95
the main class to read/store the text font, paragraph, section stylesread
Definition: MsWrdTextStyles.hxx:67
the main class to read the text part of Microsoft Word file
Definition: MsWrdText.hxx:65
bool sendTable(MsWrdTextInternal::Table const &table)
try to send a table.
Definition: MsWrdText.cxx:2071
MsWrdText & operator=(MsWrdText const &orig)
bool sendSection(int sectionId)
try to open a section
Definition: MsWrdText.cxx:2055
MsWrdText(MsWrdText const &orig)
shared_ptr< MsWrdTextStyles > m_stylesManager
the style manager
Definition: MsWrdText.hxx:213
void prepareLines()
cut the text in line/cell pos
Definition: MsWrdText.cxx:1223
MsWrdText(MsWrdParser &parser)
constructor
Definition: MsWrdText.cxx:416
virtual ~MsWrdText()
destructor
Definition: MsWrdText.cxx:423
shared_ptr< MsWrdTextInternal::State > m_state
the state
Definition: MsWrdText.hxx:210
bool readFontNames(MsWrdEntry &entry)
read the font names
Definition: MsWrdText.cxx:793
int version() const
returns the file version
Definition: MsWrdText.cxx:426
bool readFields(MsWrdEntry &entry, std::vector< long > const &fieldPos)
read the field data
Definition: MsWrdText.cxx:1093
void prepareTableLimits()
find the table end position knowing the end cell/pos delimiter
Definition: MsWrdText.cxx:1565
bool sendFootnote(int id)
send a note to a listener
Definition: MsWrdText.cxx:2146
bool readParagraphInfo(MsWrdEntry &entry)
read the paragraph height info
Definition: MsWrdText.cxx:854
bool readHeaderTextLength()
reads the three different zone size
Definition: MsWrdText.cxx:551
long getMainTextLength() const
returns the main text length
Definition: MsWrdText.cxx:439
shared_ptr< MWAWParserState > & getParserState()
returns the parser state
Definition: MsWrdText.hxx:114
void prepareParagraphProperties()
retrieve the paragraph properties
Definition: MsWrdText.cxx:1384
bool readTextStruct(MsWrdEntry &entry)
read the text structure(some paragraph style+some text position?)
Definition: MsWrdText.cxx:693
std::multimap< long, MsWrdText::PLC > & getFilePLCMap()
returns the file correspondance zone ( filepos, plc )
Definition: MsWrdText.cxx:495
bool sendText(MWAWEntry const &textEntry, bool mainZone, bool tableCell=false)
send a text zone
Definition: MsWrdText.cxx:1845
bool readLongZone(MsWrdEntry &entry, int sz, std::vector< long > &list)
read a zone which consists in a list of int
Definition: MsWrdText.cxx:1185
void flushExtra()
sends the data which have not yet been sent to the listener
Definition: MsWrdText.cxx:2184
int numPages() const
returns the number of pages
Definition: MsWrdText.cxx:433
MWAWParserStatePtr m_parserState
the parser state
Definition: MsWrdText.hxx:207
void convertFilePLCPos()
convert the file position in character position and compute the paragraph limit
Definition: MsWrdText.cxx:1263
bool readFootnotesPos(MsWrdEntry &entry, std::vector< long > const &noteDef)
read the footnote pos in text + val
Definition: MsWrdText.cxx:983
MWAWEntry getHeader() const
returns the header entry
Definition: MsWrdText.cxx:444
bool readFootnotesData(MsWrdEntry &entry)
read the footnote data
Definition: MsWrdText.cxx:1045
MsWrdParser * m_mainParser
the main parser;
Definition: MsWrdText.hxx:216
MWAWEntry getFooter() const
returns the footer entry
Definition: MsWrdText.cxx:467
std::multimap< long, MsWrdText::PLC > & getTextPLCMap()
returns the text correspondance zone ( textpos, plc )
Definition: MsWrdText.cxx:490
bool sendFieldComment(int id)
send a field note to a listener
Definition: MsWrdText.cxx:2164
void prepareData()
prepare the data to be send
Definition: MsWrdText.cxx:1690
bool sendMainText()
send a main zone
Definition: MsWrdText.cxx:2137
bool updateTableBeginnningAt(long cPos, long &nextCPos)
try to find a table which begin at position cPos, if so, update its data...
Definition: MsWrdText.cxx:1667
void prepareFontProperties()
retrieve the font properties
Definition: MsWrdText.cxx:1479
bool readPageBreak(MsWrdEntry &entry)
read the page limit ?
Definition: MsWrdText.cxx:920
bool createZones(long bot)
finds the different zones
Definition: MsWrdText.cxx:581
shared_ptr< MWAWParserState > MWAWParserStatePtr
a smart pointer of MWAWParserState
Definition: libmwaw_internal.hxx:509
Internal: the structures of a MsWrdText.
Definition: MsWrdText.cxx:70
the entry of MsWrdParser
Definition: MsWrdParser.hxx:63
Internal and low level: a structure to store a table of a MsWrdText.
Definition: MsWrdText.cxx:262
a comparaison structure
Definition: MsWrdText.hxx:78
bool operator()(PLC const &s1, PLC const &s2) const
Definition: MsWrdText.hxx:79
Internal: the plc.
Definition: MsWrdText.hxx:70
Type
Definition: MsWrdText.hxx:71
@ FootnoteDef
Definition: MsWrdText.hxx:71
@ ParagraphInfo
Definition: MsWrdText.hxx:71
@ Paragraph
Definition: MsWrdText.hxx:71
@ TextPosition
Definition: MsWrdText.hxx:71
@ Object
Definition: MsWrdText.hxx:71
@ HeaderFooter
Definition: MsWrdText.hxx:71
@ Font
Definition: MsWrdText.hxx:71
@ Page
Definition: MsWrdText.hxx:71
@ Section
Definition: MsWrdText.hxx:71
@ Field
Definition: MsWrdText.hxx:71
@ Footnote
Definition: MsWrdText.hxx:71
Type m_type
the plc type
Definition: MsWrdText.hxx:89
friend std::ostream & operator<<(std::ostream &o, PLC const &plc)
operator<<
Definition: MsWrdText.cxx:504
int m_id
the identificator
Definition: MsWrdText.hxx:91
std::string m_extra
some extra data
Definition: MsWrdText.hxx:93
PLC(Type type, int id=0)
Definition: MsWrdText.hxx:72

Generated on Wed Jan 19 2022 22:23:15 for libmwaw by doxygen 1.9.3