星号的情形(如char"/>
基于Predictive Parsing的ABNF语法分析器(八)——AbnfParser文法解析器之带星号的情形(如char
带星号*表示重复的次数,例如*A表示A可以重复0至任意多次,*3A表示A可以重复0次、1次、2次或3次,4*A表示A至少要重复4次。我们先来看最简单的情形*A,ABNF的语法定义中char-val和prose-val都属于这种。
/*This file is one of the component a Context-free Grammar Parser Generator,which accept a piece of text as the input, and generates a parserfor the inputted context-free grammar.Copyright (C) 2013, Junbiao Pan (Email: panjunbiao@gmail)This program is free software: you can redistribute it and/or modifyit under the terms of the GNU General Public License as published bythe Free Software Foundation, either version 3 of the License, orany later version.This program is distributed in the hope that it will be useful,but WITHOUT ANY WARRANTY; without even the implied warranty ofMERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See theGNU General Public License for more details.You should have received a copy of the GNU General Public Licensealong with this program. If not, see </>.*/// char-val = DQUOTE *(%x20-21 / %x23-7E) DQUOTE
// DQUOTE = %x22protected CharVal char_val() throws IOException, MatchException {String char_val = "";
// char-val是双引号开始的assertMatch(is.peek(), 0x22);
// 把这个双引号消化掉 :)is.read();
// 双引号后面跟着的0x20-21、0x23-7E都属于合法的字符,读入之while (match(is.peek(), 0x20, 0x21) || match(is.peek(), 0x23, 0x7E)) {char_val += (char)is.read();}
// 如果不是跟着0x20-21、0x23-7E,则必须是双引号,否则异常assertMatch(is.peek(), 0x22);is.read();
// 返回这个字符串return new CharVal(char_val);}// char-val = DQUOTE *(%x20-21 / %x23-7E) DQUOTE
// DQUOTE = %x22@Testpublic void testChar_val() throws Exception {Tester<CharVal> tester = new Tester<CharVal>() {@Overridepublic CharVal test(AbnfParser parser) throws MatchException, IOException {return parser.char_val();}};String input;input = "";
// 用来虐待char_var()方法的各种case,自己看吧Assert.assertEquals(input, AbnfParserFactory.newInstance("\"" + input + "\"").char_val().toString());input = String.valueOf((char)0x20);Assert.assertEquals(input, AbnfParserFactory.newInstance("\"" + input + "\"").char_val().toString());input = String.valueOf((char)0x21);Assert.assertEquals(input, AbnfParserFactory.newInstance("\"" + input + "\"").char_val().toString());input = String.valueOf((char)0x23);Assert.assertEquals(input, AbnfParserFactory.newInstance("\"" + input + "\"").char_val().toString());input = String.valueOf((char)0x7E);Assert.assertEquals(input, AbnfParserFactory.newInstance("\"" + input + "\"").char_val().toString());input = String.valueOf((char)0x20) + String.valueOf((char)0x20);Assert.assertEquals(input, AbnfParserFactory.newInstance("\"" + input + "\"").char_val().toString());input = String.valueOf((char)0x21) + String.valueOf((char)0x21);Assert.assertEquals(input, AbnfParserFactory.newInstance("\"" + input + "\"").char_val().toString());input = String.valueOf((char)0x23) + String.valueOf((char)0x23);Assert.assertEquals(input, AbnfParserFactory.newInstance("\"" + input + "\"").char_val().toString());input = String.valueOf((char)0x7E) + String.valueOf((char)0x7E);Assert.assertEquals(input, AbnfParserFactory.newInstance("\"" + input + "\"").char_val().toString());input = "AbCd1234#$%^~!@#$%^&*()`-=_+[]\\{}|,./<>?;:'";Assert.assertEquals(input, AbnfParserFactory.newInstance("\"" + input + "\"").char_val().toString());Assert.assertEquals(input, AbnfParserFactory.newInstance("\"" + input + "\"A").char_val().toString());Assert.assertEquals(input, AbnfParserFactory.newInstance("\"" + input + "\"\"").char_val().toString());// Assertion.assertMatchException("", tester, 1, 1);Assertion.assertMatchException("" + (char)0x19, tester, 1, 1);
// 这个case可以发现我们这个解析器的缺陷,
// 例如当一个输入流是只有一个双引号开头,没有双引号结尾的情况下,
// char_var()方法会抛出异常(这一点是可以接受的),
// 但读指针却无法到双引号之前了(也就是说这个算法不支持回溯)Assertion.assertMatchException("\"", tester, 2, 1);Assertion.assertMatchException("\"a", tester, 3, 1);Assertion.assertMatchException("B", tester, 1, 1);}// prose-val = "<" *(%x20-3D / %x3F-7E) ">"
// prose_val()方法和char_val()方法很类似,请自行阅读protected ProseVal prose_val() throws IOException, MatchException {String proseval = "";assertMatch(is.peek(), '<');is.read();while (match(is.peek(), 0x20, 0x3D) || match(is.peek(), 0x3F, 0x7E)) {proseval += (char)is.read();}assertMatch(is.peek(), '>');is.read();return new ProseVal(proseval);}// prose-val = "<" *(%x20-3D / %x3F-7E) ">"@Testpublic void testProse_val() throws Exception {Tester<String> tester = new Tester<String>() {@Overridepublic String test(AbnfParser parser) throws MatchException, IOException {return parser.prose_val().toString();}};String input;input = String.valueOf(new char[] {'<', '>'});Assert.assertEquals(input, AbnfParserFactory.newInstance(input).prose_val().toString());input = String.valueOf(new char[] {'<', 0x20, '>'});Assert.assertEquals(input, AbnfParserFactory.newInstance(input).prose_val().toString());input = String.valueOf(new char[] {'<', 0x3D, '>'});Assert.assertEquals(input, AbnfParserFactory.newInstance(input).prose_val().toString());input = String.valueOf(new char[] {'<', 0x3F, '>'});Assert.assertEquals(input, AbnfParserFactory.newInstance(input).prose_val().toString());input = String.valueOf(new char[] {'<', 0x7E, '>'});Assert.assertEquals(input, AbnfParserFactory.newInstance(input).prose_val().toString());input = String.valueOf(new char[] {'<', 0x20, 0x3D, 0x3F, 0x7E, '>'});Assert.assertEquals(input, AbnfParserFactory.newInstance(input).prose_val().toString());Assert.assertEquals("<>", AbnfParserFactory.newInstance("<>>").prose_val().toString());Assertion.assertMatchException("<" + (char) 0x19 + ">", tester, 2, 1);Assertion.assertMatchException("<" + (char) 0x7F + ">", tester, 2, 1);Assertion.assertMatchException("<" + (char)0x20 + (char)0x19 + ">", tester, 3, 1);}
本系列文章索引:基于预测的ABNF文法分析器
更多推荐
基于Predictive Parsing的ABNF语法分析器(八)——AbnfParser文法解析器之带星号的情形(如char
发布评论