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
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
use reader::lexer::rdf_lexer::RdfLexer;
use reader::lexer::token::Token;
use reader::input_reader::InputReader;
use std::io::Read;
use error::{Error, ErrorType};
use Result;
/// Produces tokens from NTriples input.
pub struct NTriplesLexer<R: Read> {
input_reader: InputReader<R>,
peeked_token: Option<Token>,
}
impl<R: Read> RdfLexer<R> for NTriplesLexer<R> {
/// Constructor for `NTriplesLexer`;
///
/// # Examples
///
/// ```
/// use rdf::reader::lexer::rdf_lexer::RdfLexer;
/// use rdf::reader::lexer::n_triples_lexer::NTriplesLexer;
///
/// let input = "<example.org/a>".as_bytes();
///
/// NTriplesLexer::new(input);
/// ```
fn new(input: R) -> NTriplesLexer<R> {
NTriplesLexer {
input_reader: InputReader::new(input),
peeked_token: None,
}
}
/// Determines the next token from the input.
///
/// # Examples
///
/// ```
/// use rdf::reader::lexer::rdf_lexer::RdfLexer;
/// use rdf::reader::lexer::n_triples_lexer::NTriplesLexer;
/// use rdf::reader::lexer::token::Token;
///
/// let input = "_:auto <example.org/b> \"test\" .".as_bytes();
///
/// let mut lexer = NTriplesLexer::new(input);
///
/// assert_eq!(lexer.get_next_token().unwrap(), Token::BlankNode("auto".to_string()));
/// assert_eq!(lexer.get_next_token().unwrap(), Token::Uri("example.org/b".to_string()));
/// assert_eq!(lexer.get_next_token().unwrap(), Token::Literal("test".to_string()));
/// assert_eq!(lexer.get_next_token().unwrap(), Token::TripleDelimiter);
/// ```
///
/// # Failures
///
/// - Input that does not conform to the NTriples standard.
///
fn get_next_token(&mut self) -> Result<Token> {
if let Some(token) = self.peeked_token.clone() {
self.peeked_token = None;
return Ok(token);
}
match self.input_reader.peek_next_char_discard_leading_spaces()? {
Some('#') => self.get_comment(),
Some('"') => self.get_literal(),
Some('<') => self.get_uri(),
Some('_') => self.get_blank_node(),
Some('.') => {
self.consume_next_char(); // consume '.'
Ok(Token::TripleDelimiter)
}
None => Ok(Token::EndOfInput),
Some(c) => Err(Error::new(
ErrorType::InvalidReaderInput,
"Invalid NTriples input: ".to_string() + &c.to_string(),
)),
}
}
/// Determines the next token without consuming it.
///
/// # Examples
///
/// ```
/// use rdf::reader::lexer::rdf_lexer::RdfLexer;
/// use rdf::reader::lexer::n_triples_lexer::NTriplesLexer;
/// use rdf::reader::lexer::token::Token;
///
/// let input = "_:auto <example.org/b> \"test\" .".as_bytes();
///
/// let mut lexer = NTriplesLexer::new(input);
///
/// assert_eq!(lexer.peek_next_token().unwrap(), Token::BlankNode("auto".to_string()));
/// assert_eq!(lexer.peek_next_token().unwrap(), Token::BlankNode("auto".to_string()));
/// assert_eq!(lexer.get_next_token().unwrap(), Token::BlankNode("auto".to_string()));
/// assert_eq!(lexer.peek_next_token().unwrap(), Token::Uri("example.org/b".to_string()));
/// ```
///
/// # Failures
///
/// - End of input reached.
/// - Invalid input that does not conform with NTriples standard.
///
fn peek_next_token(&mut self) -> Result<Token> {
match self.peeked_token.clone() {
Some(token) => Ok(token),
None => {
let next = self.get_next_token()?;
self.peeked_token = Some(next.clone());
Ok(next)
}
}
}
}
impl<R: Read> NTriplesLexer<R> {
/// Consumes the next character of the input reader.
fn consume_next_char(&mut self) {
let _ = self.input_reader.get_next_char();
}
/// Parses the comment from the input and returns it as token.
fn get_comment(&mut self) -> Result<Token> {
self.consume_next_char(); // consume '#'
match self.input_reader
.get_until_discard_leading_spaces(|c| c == '\n' || c == '\r')
{
Ok(chars) => {
self.consume_next_char(); // consume comment delimiter
Ok(Token::Comment(chars.to_string()))
}
Err(err) => match *err.error_type() {
ErrorType::EndOfInput(ref chars) => Ok(Token::Comment(chars.to_string())),
_ => Err(Error::new(
ErrorType::InvalidReaderInput,
"Invalid input for Turtle lexer while parsing comment.",
)),
},
}
}
/// Parses the language specification from the input and returns it as token.
fn get_language_specification(&mut self) -> Result<String> {
match self.input_reader
.get_until(|c| c == '\n' || c == '\r' || c == ' ' || c == '.')
{
Ok(chars) => Ok(chars.to_string()),
Err(err) => match *err.error_type() {
ErrorType::EndOfInput(ref chars) => Ok(chars.to_string()),
_ => Err(Error::new(
ErrorType::InvalidReaderInput,
"Invalid input for NTriples lexer while parsing language specification.",
)),
},
}
}
/// Parses a literal from the input and returns it as token.
fn get_literal(&mut self) -> Result<Token> {
self.consume_next_char(); // consume '"'
let literal = self.input_reader.get_until(|c| c == '"')?.to_string();
self.consume_next_char(); // consume '"'
match self.input_reader.peek_next_char()? {
Some('@') => {
self.consume_next_char(); // consume '@'
let language = self.get_language_specification()?;
Ok(Token::LiteralWithLanguageSpecification(literal, language))
}
Some('^') => {
self.consume_next_char(); // consume '^'
self.consume_next_char(); // consume '^'
match self.input_reader.peek_next_char()? {
Some('<') => {
// data type is an URI (NTriples allows only URI data types)
match self.get_uri()? {
Token::Uri(datatype_uri) => {
Ok(Token::LiteralWithUrlDatatype(literal, datatype_uri))
}
_ => Err(Error::new(
ErrorType::InvalidReaderInput,
"Invalid data type URI for NTriples literal.",
)),
}
}
Some(c) => Err(Error::new(
ErrorType::InvalidReaderInput,
"Invalid data type token for NTriples: ".to_string() + &c.to_string(),
)),
None => Err(Error::new(
ErrorType::InvalidReaderInput,
"Invalid NTriples input.",
)),
}
}
_ => {
self.consume_next_char(); // consume '"'
Ok(Token::Literal(literal))
}
}
}
/// Parses a URI from the input and returns it as token.
fn get_uri(&mut self) -> Result<Token> {
self.consume_next_char(); // consume '<'
let chars = self.input_reader.get_until(|c| c == '>')?;
self.consume_next_char(); // consume '>'
Ok(Token::Uri(chars.to_string()))
}
/// Parses a blank node ID from the input and returns it as token.
fn get_blank_node(&mut self) -> Result<Token> {
self.consume_next_char(); // consume '_'
// get colon after under score
match self.input_reader.get_next_char()? {
Some(':') => {}
Some(c) => {
return Err(Error::new(
ErrorType::InvalidReaderInput,
"Invalid character while parsing NTriples blank node: ".to_string()
+ &c.to_string(),
))
}
None => {
return Err(Error::new(
ErrorType::InvalidReaderInput,
"Error while parsing NTriples blank node.",
))
}
}
match self.input_reader
.get_until(|c| c == '\n' || c == '\r' || c == ' ' || c == '.')
{
Ok(chars) => Ok(Token::BlankNode(chars.to_string())),
Err(err) => match *err.error_type() {
ErrorType::EndOfInput(ref chars) => Ok(Token::BlankNode(chars.to_string())),
_ => Err(Error::new(
ErrorType::InvalidReaderInput,
"Invalid input for NTriples lexer while parsing blank node.",
)),
},
}
}
}
#[cfg(test)]
mod tests {
use reader::lexer::rdf_lexer::RdfLexer;
use reader::lexer::n_triples_lexer::NTriplesLexer;
use reader::lexer::token::Token;
#[test]
fn test_n_triples_parse_comment() {
let input = "# Hello World!\n# Foo".as_bytes();
let mut lexer = NTriplesLexer::new(input);
assert_eq!(
lexer.get_next_token().unwrap(),
Token::Comment("Hello World!".to_string())
);
assert_eq!(
lexer.get_next_token().unwrap(),
Token::Comment("Foo".to_string())
);
}
#[test]
fn test_n_triples_parse_literal() {
let input = "\"a\"".as_bytes();
let mut lexer = NTriplesLexer::new(input);
assert_eq!(
lexer.get_next_token().unwrap(),
Token::Literal("a".to_string())
);
}
#[test]
fn test_n_triples_parse_uri() {
let input = "<example.org/a>".as_bytes();
let mut lexer = NTriplesLexer::new(input);
assert_eq!(
lexer.get_next_token().unwrap(),
Token::Uri("example.org/a".to_string())
);
}
#[test]
fn test_n_triples_parse_literal_with_language_specification() {
let input = "\"a\"@abc".as_bytes();
let mut lexer = NTriplesLexer::new(input);
assert_eq!(
lexer.get_next_token().unwrap(),
Token::LiteralWithLanguageSpecification("a".to_string(), "abc".to_string())
);
}
#[test]
fn test_n_triples_parse_blank_node() {
let input = "_:auto".as_bytes();
let mut lexer = NTriplesLexer::new(input);
assert_eq!(
lexer.get_next_token().unwrap(),
Token::BlankNode("auto".to_string())
);
}
#[test]
fn test_n_triples_parse_literal_with_data_type() {
let input = "\"a\"^^<example.org/abc>".as_bytes();
let mut lexer = NTriplesLexer::new(input);
assert_eq!(
lexer.get_next_token().unwrap(),
Token::LiteralWithUrlDatatype("a".to_string(), "example.org/abc".to_string())
);
}
#[test]
fn test_n_triples_parse_triple_delimiter() {
let input = ". \"a\" .".as_bytes();
let mut lexer = NTriplesLexer::new(input);
assert_eq!(lexer.get_next_token().unwrap(), Token::TripleDelimiter);
assert_eq!(
lexer.get_next_token().unwrap(),
Token::Literal("a".to_string())
);
assert_eq!(lexer.get_next_token().unwrap(), Token::TripleDelimiter);
}
}