Starting from 2021-07-01, all LRZ GitLab users will be required to explicitly accept the GitLab Terms of Service. Please see the detailed information at https://doku.lrz.de/display/PUBLIC/GitLab and make sure that your projects conform to the requirements.

test_parsers.py 13.4 KB
Newer Older
1 2
#!/usr/bin/python3

3
"""test_parsers.py - tests of the parsers-module of DHParser 
4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22

Author: Eckhart Arnold <arnold@badw.de>

Copyright 2017 Bavarian Academy of Sciences and Humanities

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.
"""

import sys
23
from functools import partial
24

Eckhart Arnold's avatar
Eckhart Arnold committed
25
sys.path.extend(['../', './'])
26

27
from DHParser.toolkit import is_logging, logging, compile_python_object
di68kap's avatar
di68kap committed
28
from DHParser.parsers import compile_source, Retrieve, Grammar, Forward, Token, ZeroOrMore, RE
Eckhart Arnold's avatar
Eckhart Arnold committed
29
from DHParser.ebnf import get_ebnf_grammar, get_ebnf_transformer, get_ebnf_compiler
30
from DHParser.dsl import parser_factory, DHPARSER_IMPORTS
31 32


33
class TestInfiLoopsAndRecursion:
34
    def test_direct_left_recursion1(self):
35 36 37 38 39 40 41 42
        minilang =""" 
            @ whitespace = linefeed
            formula = [ //~ ] expr
            expr = expr ("+"|"-") term | term
            term = term ("*"|"/") factor | factor
            factor = /[0-9]+/~
            # example:  "5 + 3 * 4"
            """
43
        snippet = "9 + 8 + 7 + 6 + 5 + 3 * 4"
44
        parser = parser_factory(minilang)()
45
        assert parser
Eckhart Arnold's avatar
Eckhart Arnold committed
46
        syntax_tree = parser(snippet)
47
        assert not syntax_tree.error_flag, str(syntax_tree.collect_errors())
48
        assert snippet == str(syntax_tree)
Eckhart Arnold's avatar
Eckhart Arnold committed
49 50
        if is_logging():
            syntax_tree.log("test_LeftRecursion_direct.cst")
51
            parser.log_parsing_history__("test_LeftRecursion_direct")
52

53
    def test_direct_left_recursion2(self):
54 55 56 57 58 59 60 61 62
        minilang = """
            @ whitespace = linefeed
            formula = [ //~ ] expr
            expr = ex
            ex   = expr ("+"|"-") term | term
            term = term ("*"|"/") factor | factor
            factor = /[0-9]+/~
            # example:  "5 + 3 * 4"
            """
63
        snippet = "9 + 8 + 7 + 6 + 5 + 3 * 4"
64 65 66
        parser = parser_factory(minilang)()
        assert parser
        syntax_tree = parser(snippet)
67
        assert not syntax_tree.error_flag, syntax_tree.collect_errors()
68
        assert snippet == str(syntax_tree)
69

70
    def test_indirect_left_recursion1(self):
71 72
        minilang = """
            Expr    = //~ (Product | Sum | Value)
73 74
            Product = Expr { ('*' | '/') Expr }+
            Sum     = Expr { ('+' | '-') Expr }+
75 76 77 78
            Value   = /[0-9.]+/~ | '(' Expr ')'
            """
        parser = parser_factory(minilang)()
        assert parser
79
        snippet = "8 * 4"
80
        syntax_tree = parser(snippet)
81
        assert not syntax_tree.error_flag, syntax_tree.collect_errors()
82 83
        snippet = "7 + 8 * 4"
        syntax_tree = parser(snippet)
84
        # print(syntax_tree.as_sxpr())
85
        assert not syntax_tree.error_flag, syntax_tree.collect_errors()
86 87
        snippet = "9 + 8 * (4 + 3)"
        syntax_tree = parser(snippet)
88
        assert not syntax_tree.error_flag, syntax_tree.collect_errors()
89
        assert snippet == str(syntax_tree)
90

91 92 93
    def test_inifinite_loops(self):
        minilang = """not_forever = { // } \n"""
        snippet = " "
94
        parser = parser_factory(minilang)()
Eckhart Arnold's avatar
Eckhart Arnold committed
95
        syntax_tree = parser(snippet)
96 97 98
        assert syntax_tree.error_flag
        # print(syntax_tree.collect_errors())

99

100 101 102 103 104 105 106
class TestRegex:
    def test_multilineRegex(self):
        mlregex = r"""
        regex =  /\w+    # one or more alphabetical characters including the underscore
                  [+]    # followed by a plus sign
                  \w*    # possibly followed by more alpha chracters/
        """
Eckhart Arnold's avatar
Eckhart Arnold committed
107 108
        result, messages, syntax_tree = compile_source(mlregex, None, get_ebnf_grammar(),
                        get_ebnf_transformer(), get_ebnf_compiler('MultilineRegexTest'))
109
        assert result
110 111 112 113 114 115 116
        assert not messages
        parser = compile_python_object(DHPARSER_IMPORTS + result, '\w+Grammar$')()
        node, rest = parser.regex('abc+def')
        assert rest == ''
        assert node.parser.name == "regex"
        assert str(node) == 'abc+def'

117 118 119 120 121 122 123 124 125 126 127 128
    def test_token(self):
        tokenlang = r"""
            @whitespace = linefeed
            lang        = "" begin_token {/\w+/ ""} end_token
            begin_token = "\begin{document}"
            end_token   = "\end{document}"
            """
        testdoc = r"""
            \begin{document}
            test
            \end{document}
            """
Eckhart Arnold's avatar
Eckhart Arnold committed
129 130
        result, messages, syntax_tree = compile_source(tokenlang, None, get_ebnf_grammar(),
                                    get_ebnf_transformer(), get_ebnf_compiler("TokenTest"))
131 132 133
        assert result
        assert not messages
        parser = compile_python_object(DHPARSER_IMPORTS + result, '\w+Grammar$')()
Eckhart Arnold's avatar
Eckhart Arnold committed
134
        result = parser(testdoc)
135
        # parser.log_parsing_history__("test.log")
136 137
        assert not result.error_flag

138

139
class TestGrammar:
140
    def setup(self):
141 142 143 144 145 146
        grammar = r"""@whitespace = horizontal
        haupt        = textzeile LEERZEILE
        textzeile    = { WORT }+
        WORT         = /[^ \t]+/~
        LEERZEILE    = /\n[ \t]*(?=\n)/~
        """
147 148 149
        self.pyparser, messages, syntax_tree = compile_source(grammar, None, get_ebnf_grammar(),
                                                              get_ebnf_transformer(), get_ebnf_compiler("PosTest"))
        assert self.pyparser
150
        assert not messages
151 152 153 154

    def test_pos_values_initialized(self):
        # checks whether pos values in the parsing result and in the
        # history record have been initialized
155
        with logging("LOGS"):
156 157 158
            grammar = compile_python_object(DHPARSER_IMPORTS + self.pyparser, '\w+Grammar$')()
            grammar("no_file_name*")
        for record in grammar.history__:
159 160
            assert not record.node or record.node.pos >= 0

161
    def test_select_parsing(self):
162 163 164 165 166
        grammar = compile_python_object(DHPARSER_IMPORTS + self.pyparser, '\w+Grammar$')()
        grammar("wort", "WORT")
        grammar("eine Zeile", "textzeile")
        grammar("kein Haupt", "haupt")
        grammar("so ist es richtig", "haupt")
167

di68kap's avatar
di68kap committed
168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186
    def test_grammar_subclassing(self):
        class Arithmetic(Grammar):
            '''
            expression =  term  { ("+" | "-") term }
            term       =  factor  { ("*" | "/") factor }
            factor     =  INTEGER | "("  expression  ")"
            INTEGER    =  /\d+/~
            '''
            expression = Forward()
            INTEGER = RE('\\d+')
            factor = INTEGER | Token("(") + expression + Token(")")
            term = factor + ZeroOrMore((Token("*") | Token("/")) + factor)
            expression.set(term + ZeroOrMore((Token("+") | Token("-")) + term))
            root__ = expression

        grammar = Arithmetic()
        CST = grammar('3+4')
        assert not CST.error_flag, CST.as_sxpr()

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
class TestPopRetrieve:
    mini_language = """
        document       = { text | codeblock }
        codeblock      = delimiter { text | (!:delimiter delimiter_sign) } ::delimiter
        delimiter      = delimiter_sign  # never use delimiter between capture and retrieve!!!
        delimiter_sign = /`+/
        text           = /[^`]+/ 
        """
    mini_lang2 = """
        @braces_filter=counterpart
        document       = { text | codeblock }
        codeblock      = braces { text | opening_braces | (!:braces closing_braces) } ::braces
        braces         = opening_braces
        opening_braces = /\{+/
        closing_braces = /\}+/
        text           = /[^{}]+/
        """
    mini_lang3 = """
        document       = { text | env }
        env            = (specialtag | opentag) text [closespecial | closetag]
        opentag        = "<" name ">"
        specialtag     = "<" /ABC/ !name ">"
        closetag       = close_slash | close_star 
        close_slash    = "<" ::name "/>"
        close_star     = "<" ::name "*>"
        closespecial   = "<" /ABC/~ ">"
        name           = /\w+/~
        text           = /[^<>]+/
        """

    def setup(self):
        self.minilang_parser = parser_factory(self.mini_language)()
        self.minilang_parser2 = parser_factory(self.mini_lang2)()
        self.minilang_parser3 = parser_factory(self.mini_lang3)()

    @staticmethod
    def opening_delimiter(node, name):
        return node.tag_name == name and not isinstance(node.parser, Retrieve)

    @staticmethod
    def closing_delimiter(node):
        return isinstance(node.parser, Retrieve)

    def test_compile_mini_language(self):
        assert self.minilang_parser
        assert self.minilang_parser2
        assert self.minilang_parser3

    def test_stackhandling(self):
        ambigous_opening = "<ABCnormal> normal tag <ABCnormal*>"
        syntax_tree = self.minilang_parser3(ambigous_opening)
        assert not syntax_tree.error_flag, str(syntax_tree.collect_errors())

        ambigous_opening = "<ABCnormal> normal tag <ABCnormal/>"
        syntax_tree = self.minilang_parser3(ambigous_opening)
        assert not syntax_tree.error_flag, str(syntax_tree.collect_errors())

        forgot_closing_tag = "<em> where is the closing tag?"
        syntax_tree = self.minilang_parser3(forgot_closing_tag)
        assert syntax_tree.error_flag, str(syntax_tree.collect_errors())

        proper = "<em> has closing tag <em/>"
        syntax_tree = self.minilang_parser3(proper)
        assert not syntax_tree.error_flag, str(syntax_tree.collect_errors())

        proper = "<em> has closing tag <em*>"
        syntax_tree = self.minilang_parser3(proper)
        assert not syntax_tree.error_flag, str(syntax_tree.collect_errors())

257
    def test_cache_neutrality(self):
258 259
        """Test that packrat-caching does not interfere with the variable-
        changing parsers: Capture and Retrieve."""
260 261 262 263 264 265 266 267 268 269 270 271 272
        lang = """
            text = opening closing
            opening = (unmarked_package | marked_package)
            closing = ::variable
            unmarked_package = package "."
            marked_package = package "*" "."
            package = "(" variable ")"
            variable = /\w+/~
            """
        case = "(secret)*. secret"
        gr = parser_factory(lang)()
        st = gr(case)
        assert not st.error_flag, str(st.collect_errors())
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

    def test_single_line(self):
        teststr = "Anfang ```code block `` <- keine Ende-Zeichen ! ``` Ende"
        syntax_tree = self.minilang_parser(teststr)
        assert not syntax_tree.collect_errors()
        delim = str(next(syntax_tree.find(partial(self.opening_delimiter, name="delimiter"))))
        pop = str(next(syntax_tree.find(self.closing_delimiter)))
        assert delim == pop
        if is_logging():
            syntax_tree.log("test_PopRetrieve_single_line.cst")

    def test_multi_line(self):
        teststr = """
            Anfang ```code block `` <- keine Ende-Zeichen ! ``` Ebde

            Absatz ohne ``` codeblock, aber
            das stellt sich erst am Ende herause...

            Mehrzeliger ```code block
            """
        syntax_tree = self.minilang_parser(teststr)
        assert not syntax_tree.collect_errors()
        delim = str(next(syntax_tree.find(partial(self.opening_delimiter, name="delimiter"))))
        pop = str(next(syntax_tree.find(self.closing_delimiter)))
        assert delim == pop
        if is_logging():
            syntax_tree.log("test_PopRetrieve_multi_line.cst")

    def test_single_line_complement(self):
        teststr = "Anfang {{{code block }} <- keine Ende-Zeichen ! }}} Ende"
        syntax_tree = self.minilang_parser2(teststr)
        assert not syntax_tree.collect_errors()
        delim = str(next(syntax_tree.find(partial(self.opening_delimiter, name="braces"))))
        pop = str(next(syntax_tree.find(self.closing_delimiter)))
        assert len(delim) == len(pop) and delim != pop
        if is_logging():
            syntax_tree.log("test_PopRetrieve_single_line.cst")

    def test_multi_line_complement(self):
        teststr = """
            Anfang {{{code block {{ <- keine Ende-Zeichen ! }}} Ende

            Absatz ohne {{{ codeblock, aber
            das stellt sich erst am Ende heraus...

            Mehrzeliger }}}code block
            """
        syntax_tree = self.minilang_parser2(teststr)
        assert not syntax_tree.collect_errors()
        delim = str(next(syntax_tree.find(partial(self.opening_delimiter, name="braces"))))
        pop = str(next(syntax_tree.find(self.closing_delimiter)))
        assert len(delim) == len(pop) and delim != pop
        if is_logging():
            syntax_tree.log("test_PopRetrieve_multi_line.cst")


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
class TestWhitespaceHandling:
    minilang = """@testing = True
        doc = A B
        A = "A"
        B = "B"
        Rdoc = ar br
        ar = /A/
        br = /B/
        """

    def setup(self):
        self.gr = parser_factory(self.minilang)()

    def test_token_whitespace(self):
        st = self.gr("AB", 'doc')
        assert not st.error_flag
        st = self.gr("A B", 'doc')
        assert not st.error_flag

    def test_regexp_whitespace(self):
        st = self.gr("AB", 'Rdoc')
        assert not st.error_flag
        st = self.gr("A B", 'Rdoc')
        assert st.error_flag


355
if __name__ == "__main__":
356
    from DHParser.testing import runner
357 358
    with logging(True):
        runner("TestInfiLoopsAndRecursion.test_direct_left_recursion1", globals())