1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
|
/***************************************************************************
*
* teiplain.cpp - TEI to Plaintext filter
*
* $Id: teiplain.cpp 2833 2013-06-29 06:40:28Z chrislit $
*
* Copyright 2006-2013 CrossWire Bible Society (http://www.crosswire.org)
* CrossWire Bible Society
* P. O. Box 2528
* Tempe, AZ 85280-2528
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License as published by the
* Free Software Foundation version 2.
*
* This program is distributed in the hope that it will be useful, but
* WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* General Public License for more details.
*
*/
#include <stdlib.h>
#include <teiplain.h>
#include <ctype.h>
SWORD_NAMESPACE_START
TEIPlain::TEIPlain() {
setTokenStart("<");
setTokenEnd(">");
setEscapeStart("&");
setEscapeEnd(";");
setEscapeStringCaseSensitive(true);
addEscapeStringSubstitute("amp", "&");
addEscapeStringSubstitute("apos", "'");
addEscapeStringSubstitute("lt", "<");
addEscapeStringSubstitute("gt", ">");
addEscapeStringSubstitute("quot", "\"");
setTokenCaseSensitive(true);
}
bool TEIPlain::handleToken(SWBuf &buf, const char *token, BasicFilterUserData *userData) {
// manually process if it wasn't a simple substitution
if (!substituteToken(buf, token)) {
//MyUserData *u = (MyUserData *)userData;
XMLTag tag(token);
// <p> paragraph tag
if (!strcmp(tag.getName(), "p")) {
if ((!tag.isEndTag()) && (!tag.isEmpty())) { // non-empty start tag
buf += "\n";
}
else if (tag.isEndTag()) { // end tag
buf += "\n";
userData->supressAdjacentWhitespace = true;
}
else { // empty paragraph break marker
buf += "\n\n";
userData->supressAdjacentWhitespace = true;
}
}
// <entryFree>
else if (!strcmp(tag.getName(), "entryFree")) {
SWBuf n = tag.getAttribute("n");
if ((!tag.isEndTag()) && (!tag.isEmpty())) {
if (n != "") {
buf += n;
buf += ". ";
}
}
}
// <sense>
else if (!strcmp(tag.getName(), "sense")) {
SWBuf n = tag.getAttribute("n");
if ((!tag.isEndTag()) && (!tag.isEmpty())) {
if (n != "") {
buf += n;
buf += ". ";
}
}
else if (tag.isEndTag()) {
buf += "\n";
}
}
// <div>
else if (!strcmp(tag.getName(), "div")) {
if ((!tag.isEndTag()) && (!tag.isEmpty())) {
buf.append("\n\n\n");
}
else if (tag.isEndTag()) {
}
}
// <etym>
else if (!strcmp(tag.getName(), "etym")) {
if ((!tag.isEndTag()) && (!tag.isEmpty())) {
buf += "[";
}
else if (tag.isEndTag()) {
buf += "]";
}
}
else {
return false; // we still didn't handle token
}
}
return true;
}
SWORD_NAMESPACE_END
|
