aboutsummaryrefslogtreecommitdiffstats
path: root/utilities/vpl2mod.cpp
blob: cddc923630f20c0d2b4445ec5aac8ffcf1a97493 (plain) (blame)
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
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
#include <ctype.h>
#include <stdio.h>
#include <fcntl.h>
#include <errno.h>
#include <stdlib.h>

#ifndef __GNUC__
#include <io.h>
#else
#include <unistd.h>
#endif

#include <swmgr.h>
#include <rawtext.h>
#include <iostream>
#include <string>

#ifndef O_BINARY
#define O_BINARY 0
#endif

char readline(int fd, char **buf) {
	char ch;
	if (*buf)
		delete [] *buf;
	*buf = 0;
	int len;


	long index = lseek(fd, 0, SEEK_CUR);
	// clean up any preceding white space
	while ((len = read(fd, &ch, 1)) == 1) {
		if ((ch != 13) && (ch != ' ') && (ch != '\t'))
			break;
		else index++;
	}


	while (ch != 10) {
        if ((len = read(fd, &ch, 1)) != 1)
			break;
	}
	
	int size = (lseek(fd, 0, SEEK_CUR) - index) - 1;

	*buf = new char [ size + 1 ];

	if (size > 0) {
		lseek(fd, index, SEEK_SET);
		read(fd, *buf, size);
		read(fd, &ch, 1);   //pop terminating char
		(*buf)[size] = 0;

		// clean up any trailing junk on buf
		for (char *it = *buf+(strlen(*buf)-1); it > *buf; it--) {
			if ((*it != 10) && (*it != 13) && (*it != ' ') && (*it != '\t'))
				break;
			else *it = 0;
		}
	}
	else **buf = 0;
	return !len;
}


char *parseVReg(char *buf) {
	char stage = 0;

	while (*buf) {
		switch (stage) {
		case 0:
			if (isalpha(*buf))
				stage++;
			break;
		case 1:
			if (isdigit(*buf))
				stage++;
			break;
		case 2:
			if (*buf == ':')
				stage++;
			break;
		case 3:
			if (isdigit(*buf))
				stage++;
			break;
	   case 4:
			if (*buf == ' ') {
				*buf = 0;
				return ++buf;
			}
			break;
		}
		buf++;
	}
	return (stage == 4) ? buf : 0;  // if we got to stage 4 return after key buf, else return 0;
}


bool isKJVRef(const char *buf) {
	VerseKey vk, test;
	vk.AutoNormalize(0);
	vk.Headings(1);	// turn on mod/testmnt/book/chap headings
	vk.Persist(1);
	// lets do some tests on the verse --------------
	vk = buf;
	test = buf;

	if (vk.Testament() && vk.Book() && vk.Chapter() && vk.Verse()) { // if we're not a heading
//		std::cerr << (const char*)vk << " == "  << (const char*)test << std::endl;
		return (vk == test);
	}
	else return true;	// no check if we're a heading... Probably bad.
}


void fixText(char *text) {
	char *to = text;
	while(*text) {
		*to++ = *text++;
		*to++ = *text++;
		if (!*text)
			break;
		if (*text != ' ')
			std::cerr << "problem\n";
		else	text++;
	}
	*to = 0;
}

int main(int argc, char **argv) {

	// Let's test our command line arguments
	if (argc < 2) {
//		fprintf(stderr, "usage: %s <vpl_file> </path/to/mod> [0|1 - file includes prepended verse references]\n", argv[0]);
		fprintf(stderr, "usage: %s <source_vpl_file> </path/to/output/mod/> [0|1 - prepended verse refs] [0|1 - NT only]\n\n", argv[0]);
		fprintf(stderr, "\tWith no verse refs, source file must contain exactly 31102 lines.\n");
		fprintf(stderr, "\tThis is KJV verse count plus headings for MODULE,\n");
		fprintf(stderr, "\tTESTAMENT, BOOK, CHAPTER. An example snippet follows:\n\n");
		fprintf(stderr, "\t\tMODULE HEADER\n");
		fprintf(stderr, "\t\tOLD TESTAMENT HEADER\n");
		fprintf(stderr, "\t\tGENESIS HEADER\n");
		fprintf(stderr, "\t\tCHAPTER 1 HEADER\n");
		fprintf(stderr, "\t\tIn the beginning...\n\n");
		fprintf(stderr, "\t... implying there must also be a CHAPTER2 HEADER,\n");
        fprintf(stderr, "\tEXODUS HEADER, NEW TESTAMENT HEADER, etc.  If there is no text for\n");
		fprintf(stderr, "\tthe header, a blank line must, at least, hold place.\n\n");
		fprintf(stderr, "\tWith verse refs, source file must simply contain any number of lines,\n");
		fprintf(stderr, "\tthat begin with the verse reference for which it is an entry.  e.g.:\n\n");
		fprintf(stderr, "\t\tgen 1:0 CHAPTER 1 HEADER\n");
		fprintf(stderr, "\t\tgen 1:1 In the beginning...\n\n");
		exit(-1);
	}

	// Let's see if we can open our input file
	int fd = open(argv[1], O_RDONLY|O_BINARY);
	if (fd < 0) {
		fprintf(stderr, "error: %s: couldn't open input file: %s \n", argv[0], argv[1]);
		exit(-2);
	}

	// Try to initialize a default set of datafiles and indicies at our
	// datapath location passed to us from the user.
	if (RawText::createModule(argv[2])) {
		fprintf(stderr, "error: %s: couldn't create module at path: %s \n", argv[0], argv[2]);
		exit(-3);
	}

	// not used yet, but for future support of a vpl file with each line
	// prepended with verse reference, eg. "Gen 1:1 In the beginning..."
	bool vref = false;
	if (argc > 3)
		vref = (argv[3][0] == '0') ? false : true;

	// if 'nt' is the 4th arg, our vpl file only has the NT
	bool ntonly = false;
	if (argc > 4)
                ntonly = (argv[4][0] == '0') ? false : true;
	
	// Do some initialization stuff
	char *buffer = 0;
	RawText mod(argv[2]);	// open our datapath with our RawText driver.
	VerseKey vk;
	vk.AutoNormalize(0);
	vk.Headings(1);	// turn on mod/testmnt/book/chap headings
	vk.Persist(1);

	mod.SetKey(vk);

	// Loop through module from TOP to BOTTOM and set next line from
	// input file as text for this entry in the module
	mod = TOP;
	if (ntonly) vk = "Matthew 1:1";
	  
	int successive = 0;  //part of hack below
	while ((!mod.Error()) && (!readline(fd, &buffer))) {
		if (*buffer == '|')	// comments, ignore line
			continue;
		if (vref) {
			const char *verseText = parseVReg(buffer);
			if (!verseText) {	// if we didn't find a valid verse ref
				std::cerr << "No valid verse ref found on line: " << buffer << "\n";
				exit(-4);
			}

			vk = buffer;
			if (vk.Error()) {
				std::cerr << "Error parsing key: " << buffer << "\n";
				exit(-5);
			}
			string orig = mod.getRawEntry();

			if (!isKJVRef(buffer)) {
				VerseKey origVK = vk;
				/* This block is functioning improperly -- problem with AutoNormalize???
				do {
					vk--;
				}
				while (!vk.Error() && !isKJVRef(vk)); */
				//hack to replace above:
				successive++;
				vk -= successive;
				orig = mod.getRawEntry();

				std::cerr << "Not a valid KJV ref: " << origVK << "\n";
				std::cerr << "appending to ref: " << vk << "\n";
				orig += " [ (";
				orig += origVK;
				orig += ") ";
				orig += verseText;
				orig += " ] ";
				verseText = orig.c_str();
			}
			else {
			  successive = 0;
			}

			if (orig.length() > 1)
				   std::cerr << "Warning, overwriting verse: " << vk << std::endl;
			  
			// ------------- End verse tests -----------------
			mod << verseText;	// save text to module at current position
		}
		else {
			fixText(buffer);
			mod << buffer;	// save text to module at current position
			mod++;	// increment module position
		}
	}

	// clear up our buffer that readline might have allocated
	if (buffer)
		delete [] buffer;
}