1 /* index_utils.cc - utility functions for indexing testcase data
2 *
3 * Copyright (C) 2005,2007 Olly Betts
4 *
5 * This program is free software; you can redistribute it and/or modify
6 * it under the terms of the GNU General Public License as published by
7 * the Free Software Foundation; either version 2 of the License, or
8 * (at your option) any later version.
9 *
10 * This program is distributed in the hope that it will be useful,
11 * but WITHOUT ANY WARRANTY; without even the implied warranty of
12 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
13 * GNU General Public License for more details.
14 *
15 * You should have received a copy of the GNU General Public License
16 * along with this program; if not, write to the Free Software
17 * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
18 */
19
20 #include <config.h>
21
22 #include "index_utils.h"
23
24 #include "stringutils.h"
25
26 #include <algorithm>
27 #include <cstring>
28 #include <fstream>
29
30 #include "safeerrno.h"
31
32 using namespace std;
33
34 /// Read a paragraph from stream @a input.
35 static string
get_paragraph(istream & input)36 get_paragraph(istream &input)
37 {
38 string para, line;
39 while (true) {
40 getline(input, line);
41 if (find_if(line.begin(), line.end(), C_isnotspace) == line.end())
42 return para;
43 para += line;
44 para += '\n';
45 }
46 }
47
48 Xapian::Document
next()49 FileIndexer::next()
50 {
51 if (input.eof()) next_file();
52
53 Xapian::Stem stemmer("english");
54
55 Xapian::Document doc;
56 string para = get_paragraph(input);
57 doc.set_data(para);
58
59 // Value 0 contains all possible character values so we can check that
60 // none of them cause problems.
61 string value0("X\0\0\0 \1\t"
62 "\x00\x01\x02\x03\x04\x05\x06\x07\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
63 "\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f"
64 "\x20\x21\x22\x23\x24\x25\x26\x27\x28\x29\x2a\x2b\x2c\x2d\x2e\x2f"
65 "\x30\x31\x32\x33\x34\x35\x36\x37\x38\x39\x3a\x3b\x3c\x3d\x3e\x3f"
66 "\x40\x41\x42\x43\x44\x45\x46\x47\x48\x49\x4a\x4b\x4c\x4d\x4e\x4f"
67 "\x50\x51\x52\x53\x54\x55\x56\x57\x58\x59\x5a\x5b\x5c\x5d\x5e\x5f"
68 "\x60\x61\x62\x63\x64\x65\x66\x67\x68\x69\x6a\x6b\x6c\x6d\x6e\x6f"
69 "\x70\x71\x72\x73\x74\x75\x76\x77\x78\x79\x7a\x7b\x7c\x7d\x7e\x7f"
70 "\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f"
71 "\x90\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f"
72 "\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf"
73 "\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf"
74 "\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf"
75 "\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf"
76 "\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef"
77 "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff",
78 7 + 256);
79 if (para.size() > 2) value0[0] = para[2];
80 value0 += para;
81 doc.add_value(0, value0);
82
83 for (Xapian::valueno i = min(para.length(), size_t(10)); i >= 1; --i) {
84 doc.add_value(i, para.substr(i, 1));
85 }
86 // Value 11 is useful for tests of sorting
87 doc.add_value(11, Xapian::sortable_serialise(para.size()));
88
89 // Value 12 is useful for tests of collapsing
90 doc.add_value(12, Xapian::sortable_serialise(para.size() % 5));
91
92 // Value 13 contains the first 3 letters of the paragraph
93 doc.add_value(13, para.substr(0, 3));
94
95 Xapian::termcount pos = 0;
96 string::const_iterator word_end = para.begin();
97 // Need a const_iterator version of para.end() for find_if.
98 const string::const_iterator para_end = para.end();
99 while (word_end != para_end) {
100 string::const_iterator word_start;
101 word_start = find_if(word_end, para_end, C_isnotspace);
102 word_end = find_if(word_start, para_end, C_isspace);
103 string word = stemmer(munge_term(string(word_start, word_end)));
104 if (!word.empty()) doc.add_posting(word, ++pos);
105 }
106
107 return doc;
108 }
109
110 // Strip unwanted characters, force to lower case, and handle \ escapes.
111 string
munge_term(const string & term)112 munge_term(const string &term)
113 {
114 string result;
115 for (string::const_iterator i = term.begin(); i != term.end(); ++i) {
116 char ch = *i;
117 if (C_isalnum(ch))
118 result += C_tolower(ch);
119 else if (ch == '\\') {
120 ++i;
121 if (i != term.end()) {
122 switch (*i) {
123 case '\\': ch = '\\'; break;
124 case '0': ch = '\0'; break;
125 case 'n': ch = '\n'; break;
126 case 'r': ch = '\r'; break;
127 case 't': ch = '\t'; break;
128 case 'x': {
129 // Check we can read the next two characters.
130 if (size_t(i - term.begin()) >= term.size() - 2) {
131 --i;
132 break;
133 }
134 string::const_iterator j = i;
135 char b = *++i;
136 char c = *++i;
137 if (!C_isxdigit(b) || !C_isxdigit(c)) {
138 i = j - 1;
139 break;
140 }
141 if (C_isdigit(b)) {
142 ch = b - '0';
143 } else {
144 ch = C_tolower(b) - 'a' + 10;
145 }
146 ch *= 16;
147 if (C_isdigit(c)) {
148 ch |= c - '0';
149 } else {
150 ch |= C_tolower(c) - 'a' + 10;
151 }
152 break;
153 }
154 }
155 }
156 result += ch;
157 }
158 }
159 return result;
160 }
161
162 void
next_file()163 FileIndexer::next_file()
164 {
165 if (input.is_open()) {
166 input.close();
167 // MSVC doesn't clear fail() on close() and re-open().
168 input.clear();
169 }
170
171 // Find the next non-empty filename.
172 while (file != end && (*file).empty()) {
173 ++file;
174 }
175 if (file == end) return;
176
177 string filename;
178 if (!datadir.empty()) {
179 filename = datadir;
180 if (!endswith(datadir, '/')) filename += '/';
181 }
182 filename += *file++;
183 filename += ".txt";
184
185 input.open(filename.c_str());
186 // Need to check is_open() - just using operator! fails with MSVC.
187 if (!input.is_open()) {
188 string msg = "Can't read file '";
189 msg += filename;
190 msg += "' for indexing (";
191 msg += strerror(errno);
192 msg += ')';
193 throw msg;
194 }
195 }
196