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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374
/* * Copyright (C) 2015 Benjamin Fry <benjaminfry@me.com> * * Licensed under the Apache License, Version 2.0 (the "License"); * you may not use this file except in compliance with the License. * You may obtain a copy of the License at * * http://www.apache.org/licenses/LICENSE-2.0 * * Unless required by applicable law or agreed to in writing, software * distributed under the License is distributed on an "AS IS" BASIS, * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. * See the License for the specific language governing permissions and * limitations under the License. */ use std::collections::BTreeMap; use std::io::Read; use std::fs::File; use ::error::*; use ::rr::{ Name, RecordType, Record, DNSClass, RData}; use ::authority::{Authority, RrKey, ZoneType, RRSet}; use super::master_lex::{Lexer, Token}; /// ```text /// 5. MASTER FILES /// /// Master files are text files that contain RRs in text form. Since the /// contents of a zone can be expressed in the form of a list of RRs a /// master file is most often used to define a zone, though it can be used /// to list a cache's contents. Hence, this section first discusses the /// format of RRs in a master file, and then the special considerations when /// a master file is used to create a zone in some name server. /// /// 5.1. Format /// /// The format of these files is a sequence of entries. Entries are /// predominantly line-oriented, though parentheses can be used to continue /// a list of items across a line boundary, and text literals can contain /// CRLF within the text. Any combination of tabs and spaces act as a /// delimiter between the separate items that make up an entry. The end of /// any line in the master file can end with a comment. The comment starts /// with a ";" (semicolon). /// /// The following entries are defined: /// /// <blank>[<comment>] /// /// $ORIGIN <domain-name> [<comment>] /// /// $INCLUDE <file-name> [<domain-name>] [<comment>] /// /// <domain-name><rr> [<comment>] /// /// <blank><rr> [<comment>] /// /// Blank lines, with or without comments, are allowed anywhere in the file. /// /// Two control entries are defined: $ORIGIN and $INCLUDE. $ORIGIN is /// followed by a domain name, and resets the current origin for relative /// domain names to the stated name. $INCLUDE inserts the named file into /// the current file, and may optionally specify a domain name that sets the /// relative domain name origin for the included file. $INCLUDE may also /// have a comment. Note that a $INCLUDE entry never changes the relative /// origin of the parent file, regardless of changes to the relative origin /// made within the included file. /// /// The last two forms represent RRs. If an entry for an RR begins with a /// blank, then the RR is assumed to be owned by the last stated owner. If /// an RR entry begins with a <domain-name>, then the owner name is reset. /// /// <rr> contents take one of the following forms: /// /// [<TTL>] [<class>] <type> <RDATA> /// /// [<class>] [<TTL>] <type> <RDATA> /// /// The RR begins with optional TTL and class fields, followed by a type and /// RDATA field appropriate to the type and class. Class and type use the /// standard mnemonics, TTL is a decimal integer. Omitted class and TTL /// values are default to the last explicitly stated values. Since type and /// class mnemonics are disjoint, the parse is unique. (Note that this /// order is different from the order used in examples and the order used in /// the actual RRs; the given order allows easier parsing and defaulting.) /// /// <domain-name>s make up a large share of the data in the master file. /// The labels in the domain name are expressed as character strings and /// separated by dots. Quoting conventions allow arbitrary characters to be /// stored in domain names. Domain names that end in a dot are called /// absolute, and are taken as complete. Domain names which do not end in a /// dot are called relative; the actual domain name is the concatenation of /// the relative part with an origin specified in a $ORIGIN, $INCLUDE, or as /// an argument to the master file loading routine. A relative name is an /// error when no origin is available. /// /// <character-string> is expressed in one or two ways: as a contiguous set /// of characters without interior spaces, or as a string beginning with a " /// and ending with a ". Inside a " delimited string any character can /// occur, except for a " itself, which must be quoted using \ (back slash). /// /// Because these files are text files several special encodings are /// necessary to allow arbitrary data to be loaded. In particular: /// /// of the root. /// /// @ A free standing @ is used to denote the current origin. /// /// \X where X is any character other than a digit (0-9), is /// used to quote that character so that its special meaning /// does not apply. For example, "\." can be used to place /// a dot character in a label. /// /// \DDD where each D is a digit is the octet corresponding to /// the decimal number described by DDD. The resulting /// octet is assumed to be text and is not checked for /// special meaning. /// /// ( ) Parentheses are used to group data that crosses a line /// boundary. In effect, line terminations are not /// recognized within parentheses. /// /// ; Semicolon is used to start a comment; the remainder of /// the line is ignored. /// ``` pub struct Parser; impl Parser { pub fn new() -> Self { Parser } pub fn parse_file(file: File, origin: Option<Name>, zone_type: ZoneType, allow_update: bool) -> ParseResult<Authority> { let mut file = file; let mut buf = String::new(); // TODO, this should really use something to read line by line or some other method to // keep the usage down. and be a custom lexer... try!(file.read_to_string(&mut buf)); let lexer = Lexer::new(&buf); Self::new().parse(lexer, origin, zone_type, allow_update) } pub fn parse(&mut self, lexer: Lexer, origin: Option<Name>, zone_type: ZoneType, allow_update: bool) -> ParseResult<Authority> { let mut lexer = lexer; let mut records: BTreeMap<RrKey, RRSet> = BTreeMap::new(); let mut origin: Option<Name> = origin; let mut current_name: Option<Name> = None; let mut rtype: Option<RecordType> = None; let mut ttl: Option<u32> = None; let mut class: Option<DNSClass> = None; let mut state = State::StartLine; let mut tokens: Vec<Token> = Vec::new(); while let Some(t) = try!(lexer.next_token()) { state = match state { State::StartLine => { // current_name is not reset on the next line b/c it might be needed from the previous rtype = None; tokens.clear(); match t { // if Dollar, then $INCLUDE or $ORIGIN Token::Include => unimplemented!(), Token::Origin => State::Origin, Token::Ttl => State::Ttl, // if CharData, then Name then ttl_class_type Token::CharData(ref data) => { current_name = Some(try!(Name::parse(data, origin.as_ref()))); State::TtlClassType }, // @ is a placeholder for specifying the current origin Token::At => { current_name = origin.clone(); // TODO a COW or RC would reduce copies... State::TtlClassType } // if blank, then nothing or ttl_class_type Token::Blank => { State::TtlClassType }, Token::EOL => State::StartLine, // probably a comment _ => return Err(ParseError::UnexpectedToken(t)), } }, State::Ttl => { match t { Token::CharData(ref data) => { ttl = Some(try!(Self::parse_time(data))); State::StartLine } _ => return Err(ParseError::UnexpectedToken(t)), } } State::Origin => { match t { Token::CharData(ref data) => { // TODO an origin was specified, should this be legal? definitely confusing... origin = Some(try!(Name::parse(data, None))); State::StartLine } _ => return Err(ParseError::UnexpectedToken(t)), } } State::Include => unimplemented!(), State::TtlClassType => { match t { // if number, TTL // Token::Number(ref num) => ttl = Some(*num), // One of Class or Type (these cannot be overlapping!) Token::CharData(ref data) => { // if it's a number it's a ttl let result: Result<u32, ParseError> = Self::parse_time(data); if result.is_ok() { ttl = result.ok(); State::TtlClassType // hm, should this go to just ClassType? } else { // if can parse DNSClass, then class let result = DNSClass::from_str(data); if result.is_ok() { class = result.ok(); State::TtlClassType } else { // if can parse RecordType, then RecordType rtype = Some(try!(RecordType::from_str(data))); State::Record } } } // could be nothing if started with blank and is a comment, i.e. EOL Token::EOL => { State::StartLine // next line }, _ => return Err(ParseError::UnexpectedToken(t)), } }, State::Record => { // b/c of ownership rules, perhaps, just collect all the RData components as a list of // tokens to pass into the processor match t { Token::EOL => { // call out to parsers for difference record types let rdata = try!(RData::parse(try!(rtype.ok_or(ParseError::RecordTypeNotSpecified)), &tokens, origin.as_ref())); // verify that we have everything we need for the record let mut record = Record::new(); // TODO COW or RC would reduce mem usage, perhaps Name should have an intern()... // might want to wait until RC.weak() stabilizes, as that would be needed for global // memory where you want record.name(try!(current_name.clone().ok_or(ParseError::RecordNameNotSpecified))); record.rr_type(rtype.unwrap()); record.dns_class(try!(class.ok_or(ParseError::RecordClassNotSpecified))); // slightly annoying, need to grab the TTL, then move rdata into the record, // then check the Type again and have custom add logic. match rtype.unwrap() { RecordType::SOA => { // TTL for the SOA is set internally... // expire is for the SOA, minimum is default for records if let RData::SOA(ref soa) = rdata { // TODO, this looks wrong, get_expire() should be get_minimum(), right? record.ttl(soa.get_expire() as u32); // the spec seems a little inaccurate with u32 and i32 if ttl.is_none() { ttl = Some(soa.get_minimum()); } // TODO: should this only set it if it's not set? } else { assert!(false, "Invalid RData here, expected SOA: {:?}", rdata); } }, _ => { record.ttl(try!(ttl.ok_or(ParseError::RecordTTLNotSpecified))); }, } // TODO validate record, e.g. the name of SRV record allows _ but others do not. // move the rdata into record... record.rdata(rdata); // add to the map let key = RrKey::new(record.get_name(), record.get_rr_type()); match rtype.unwrap() { RecordType::SOA => { let mut set = RRSet::new(record.get_name(), record.get_rr_type(), 0); set.insert(record, 0); if records.insert(key, set).is_some() { return Err(ParseError::SoaAlreadySpecified); } }, _ => { // add a Vec if it's not there, then add the record to the list let mut set = records.entry(key).or_insert(RRSet::new(record.get_name(), record.get_rr_type(), 0)); set.insert(record, 0); }, } State::StartLine }, _ => { tokens.push(t); State::Record }, } }, } } // // build the Authority and return. Ok(Authority::new(try!(origin.ok_or(ParseError::OriginIsUndefined)), records, zone_type, allow_update)) } /// parses the string following the rules from: /// https://tools.ietf.org/html/rfc2308 (NXCaching RFC) and /// http://www.zytrax.com/books/dns/apa/time.html /// /// default is seconds /// #s = seconds = # x 1 seconds (really!) /// #m = minutes = # x 60 seconds /// #h = hours = # x 3600 seconds /// #d = day = # x 86400 seconds /// #w = week = # x 604800 seconds /// /// returns the result of the parsing or and error /// /// # Example /// ``` /// use trust_dns::serialize::txt::Parser; /// /// assert_eq!(Parser::parse_time("0").unwrap(), 0); /// assert_eq!(Parser::parse_time("s").unwrap(), 0); /// assert_eq!(Parser::parse_time("0s").unwrap(), 0); /// assert_eq!(Parser::parse_time("1").unwrap(), 1); /// assert_eq!(Parser::parse_time("1S").unwrap(), 1); /// assert_eq!(Parser::parse_time("1s").unwrap(), 1); /// assert_eq!(Parser::parse_time("1M").unwrap(), 60); /// assert_eq!(Parser::parse_time("1m").unwrap(), 60); /// assert_eq!(Parser::parse_time("1H").unwrap(), 3600); /// assert_eq!(Parser::parse_time("1h").unwrap(), 3600); /// assert_eq!(Parser::parse_time("1D").unwrap(), 86400); /// assert_eq!(Parser::parse_time("1d").unwrap(), 86400); /// assert_eq!(Parser::parse_time("1W").unwrap(), 604800); /// assert_eq!(Parser::parse_time("1w").unwrap(), 604800); /// assert_eq!(Parser::parse_time("1s2d3w4h2m").unwrap(), 1+2*86400+3*604800+4*3600+2*60); /// assert_eq!(Parser::parse_time("3w3w").unwrap(), 3*604800+3*604800); /// ``` pub fn parse_time(ttl_str: &str) -> ParseResult<u32> { let mut value: u32 = 0; let mut collect: u32 = 0; for c in ttl_str.chars() { match c { // TODO, should these all be checked operations? '0' ... '9' => { collect *= 10; collect += try!(c.to_digit(10).ok_or(ParseError::CharToIntError(c))); }, 'S' | 's' => { value += collect; collect = 0; }, 'M' | 'm' => { value += collect * 60; collect = 0; }, 'H' | 'h' => { value += collect * 3600; collect = 0; }, 'D' | 'd' => { value += collect * 86400; collect = 0; }, 'W' | 'w' => { value += collect * 604800; collect = 0; }, _ => return Err(ParseError::ParseTimeError(ttl_str.to_string())), } } return Ok(value + collect); // collects the initial num, or 0 if it was already collected } } #[allow(unused)] enum State { StartLine, // start of line, @, $<WORD>, Name, Blank TtlClassType, // [<TTL>] [<class>] <type>, Ttl, // $TTL <time> Record, Include, // $INCLUDE <filename> Origin, }