File: test_parser.py

package info (click to toggle)
pypy3 7.0.0%2Bdfsg-3
  • links: PTS, VCS
  • area: main
  • in suites: buster
  • size: 111,848 kB
  • sloc: python: 1,291,746; ansic: 74,281; asm: 5,187; cpp: 3,017; sh: 2,533; makefile: 544; xml: 243; lisp: 45; csh: 21; awk: 4
file content (332 lines) | stat: -rw-r--r-- 10,325 bytes parent folder | download | duplicates (2)
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
# New parser tests.
import py
import tokenize
import token
import StringIO
from pypy.interpreter.pyparser import parser, metaparser, pygram
from pypy.interpreter.pyparser.test.test_metaparser import MyGrammar


def test_char_set():
    first = {5: None, 9: None, 100: None, 255:None}
    p = parser.DFA(None, None, first)
    for i in range(256):
        assert p.could_match_token(i) == (i in first)

class SimpleParser(parser.Parser):

    def parse(self, input):
        self.prepare()
        rl = StringIO.StringIO(input + "\n").readline
        gen = tokenize.generate_tokens(rl)
        for tp, value, begin, end, line in gen:
            if self.add_token(parser.Token(tp, value, begin[0], begin[1], line)):
                py.test.raises(StopIteration, gen.next)
        return self.root


def tree_from_string(expected, gram):
    def count_indent(s):
        indent = 0
        for char in s:
            if char != " ":
                break
            indent += 1
        return indent
    last_newline_index = 0
    for i, char in enumerate(expected):
        if char == "\n":
            last_newline_index = i
        elif char != " ":
            break
    if last_newline_index:
        expected = expected[last_newline_index + 1:]
    base_indent = count_indent(expected)
    assert not divmod(base_indent, 4)[1], "not using 4 space indentation"
    lines = [line[base_indent:] for line in expected.splitlines()]
    last_indent = 0
    node_stack = []
    for line in lines:
        if not line.strip():
            continue
        data = line.split()
        if data[0].isupper():
            tp = getattr(token, data[0])
            if len(data) == 2:
                value = data[1].strip("\"")
            elif tp == token.NEWLINE:
                value = "\n"
            else:
                value = ""
            n = parser.Terminal(tp, value, 0, 0)
        else:
            tp = gram.symbol_ids[data[0]]
            n = parser.Nonterminal(tp)
        new_indent = count_indent(line)
        if new_indent >= last_indent:
            if new_indent == last_indent and node_stack:
                node_stack.pop()
            if node_stack:
                node_stack[-1].append_child(n)
            node_stack.append(n)
        else:
            diff = last_indent - new_indent
            pop_nodes = diff // 4 + 1
            del node_stack[-pop_nodes:]
            node_stack[-1].append_child(n)
            node_stack.append(n)
        last_indent = new_indent
    return node_stack[0]


class TestParser:

    def parser_for(self, gram, add_endmarker=True):
        if add_endmarker:
            gram += " NEWLINE ENDMARKER\n"
        pgen = metaparser.ParserGenerator(gram)
        g = pgen.build_grammar(MyGrammar)
        return SimpleParser(g), g

    def test_multiple_rules(self):
        gram = """foo: 'next_rule' bar 'end' NEWLINE ENDMARKER
bar: NAME NUMBER\n"""
        p, gram = self.parser_for(gram, False)
        expected = """
        foo
            NAME "next_rule"
            bar
                NAME "a_name"
                NUMBER "42"
            NAME "end"
            NEWLINE
            ENDMARKER"""
        input = "next_rule a_name 42 end"
        assert tree_from_string(expected, gram) == p.parse(input)

    def test_recursive_rule(self):
        gram = """foo: NAME bar STRING NEWLINE ENDMARKER
bar: NAME [bar] NUMBER\n"""
        p, gram = self.parser_for(gram, False)
        expected = """
        foo
            NAME "hi"
            bar
                NAME "hello"
                bar
                    NAME "a_name"
                    NUMBER "32"
                NUMBER "42"
            STRING "'string'"
            NEWLINE
            ENDMARKER"""
        input = "hi hello a_name 32 42 'string'"
        assert tree_from_string(expected, gram) == p.parse(input)

    def test_symbol(self):
        gram = """parent: first_child second_child NEWLINE ENDMARKER
first_child: NAME age
second_child: STRING
age: NUMBER\n"""
        p, gram = self.parser_for(gram, False)
        expected = """
        parent
            first_child
                NAME "harry"
                age
                     NUMBER "13"
            second_child
                STRING "'fred'"
            NEWLINE
            ENDMARKER"""
        input = "harry 13 'fred'"
        assert tree_from_string(expected, gram) == p.parse(input)

    def test_token(self):
        p, gram = self.parser_for("foo: NAME")
        expected = """
        foo
           NAME "hi"
           NEWLINE
           ENDMARKER"""
        assert tree_from_string(expected, gram) == p.parse("hi")
        py.test.raises(parser.ParseError, p.parse, "567")
        p, gram = self.parser_for("foo: NUMBER NAME STRING")
        expected = """
        foo
           NUMBER "42"
           NAME "hi"
           STRING "'bar'"
           NEWLINE
           ENDMARKER"""
        assert tree_from_string(expected, gram) == p.parse("42 hi 'bar'")

    def test_optional(self):
        p, gram = self.parser_for("foo: [NAME] 'end'")
        expected = """
        foo
            NAME "hi"
            NAME "end"
            NEWLINE
            ENDMARKER"""
        assert tree_from_string(expected, gram) == p.parse("hi end")
        expected = """
        foo
            NAME "end"
            NEWLINE
            ENDMARKER"""
        assert tree_from_string(expected, gram) == p.parse("end")

    def test_grouping(self):
        p, gram = self.parser_for(
            "foo: ((NUMBER NAME | STRING) | 'second_option')")
        expected = """
        foo
            NUMBER "42"
            NAME "hi"
            NEWLINE
            ENDMARKER"""
        assert tree_from_string(expected, gram) == p.parse("42 hi")
        expected = """
        foo
            STRING "'hi'"
            NEWLINE
            ENDMARKER"""
        assert tree_from_string(expected, gram) == p.parse("'hi'")
        expected = """
        foo
            NAME "second_option"
            NEWLINE
            ENDMARKER"""
        assert tree_from_string(expected, gram) == p.parse("second_option")
        py.test.raises(parser.ParseError, p.parse, "42 a_name 'hi'")
        py.test.raises(parser.ParseError, p.parse, "42 second_option")

    def test_alternative(self):
        p, gram = self.parser_for("foo: (NAME | NUMBER)")
        expected = """
        foo
            NAME "hi"
            NEWLINE
            ENDMARKER"""
        assert tree_from_string(expected, gram) == p.parse("hi")
        expected = """
        foo
            NUMBER "42"
            NEWLINE
            ENDMARKER"""
        assert tree_from_string(expected, gram) == p.parse("42")
        py.test.raises(parser.ParseError, p.parse, "hi 23")
        py.test.raises(parser.ParseError, p.parse, "23 hi")
        py.test.raises(parser.ParseError, p.parse, "'some string'")

    def test_keyword(self):
        p, gram = self.parser_for("foo: 'key'")
        expected = """
        foo
            NAME "key"
            NEWLINE
            ENDMARKER"""
        assert tree_from_string(expected, gram) == p.parse("key")
        py.test.raises(parser.ParseError, p.parse, "")
        p, gram = self.parser_for("foo: NAME 'key'")
        expected = """
        foo
            NAME "some_name"
            NAME "key"
            NEWLINE
            ENDMARKER"""
        assert tree_from_string(expected, gram) == p.parse("some_name key")
        py.test.raises(parser.ParseError, p.parse, "some_name")

    def test_repeaters(self):
        p, gram = self.parser_for("foo: NAME+ 'end'")
        expected = """
        foo
            NAME "hi"
            NAME "bye"
            NAME "nothing"
            NAME "end"
            NEWLINE
            ENDMARKER"""
        assert tree_from_string(expected, gram) == p.parse("hi bye nothing end")
        py.test.raises(parser.ParseError, p.parse, "end")
        py.test.raises(parser.ParseError, p.parse, "hi bye")
        p, gram = self.parser_for("foo: NAME* 'end'")
        expected = """
        foo
            NAME "hi"
            NAME "bye"
            NAME "end"
            NEWLINE
            ENDMARKER"""
        assert tree_from_string(expected, gram) == p.parse("hi bye end")
        py.test.raises(parser.ParseError, p.parse, "hi bye")
        expected = """
        foo
            NAME "end"
            NEWLINE
            ENDMARKER"""
        assert tree_from_string(expected, gram) == p.parse("end")

        p, gram = self.parser_for("foo: (NAME | NUMBER)+ 'end'")
        expected = """
        foo
            NAME "a_name"
            NAME "name_two"
            NAME "end"
            NEWLINE
            ENDMARKER"""
        assert tree_from_string(expected, gram) == p.parse("a_name name_two end")
        expected = """
        foo
            NUMBER "42"
            NAME "name"
            NAME "end"
            NEWLINE
            ENDMARKER"""
        assert tree_from_string(expected, gram) == p.parse("42 name end")
        py.test.raises(parser.ParseError, p.parse, "end")
        p, gram = self.parser_for("foo: (NAME | NUMBER)* 'end'")
        expected = """
        foo
            NAME "hi"
            NUMBER 42
            NAME "end"
            NEWLINE
            ENDMARKER"""
        assert tree_from_string(expected, gram) == p.parse("hi 42 end")


    def test_optimized_terminal(self):
        gram = """foo: bar baz 'end' NEWLINE ENDMARKER
bar: NAME
baz: NUMBER
"""
        p, gram = self.parser_for(gram, False)
        expected = """
        foo
            bar
                NAME "a_name"
            baz
                NUMBER "42"
            NAME "end"
            NEWLINE
            ENDMARKER"""
        input = "a_name 42 end"
        tree = p.parse(input)
        assert tree_from_string(expected, gram) == tree
        assert isinstance(tree, parser.Nonterminal)
        assert isinstance(tree.get_child(0), parser.Nonterminal1)
        assert isinstance(tree.get_child(1), parser.Nonterminal1)


    def test_error_string(self):
        p, gram = self.parser_for(
            "foo: 'if' NUMBER '+' NUMBER"
        )
        info = py.test.raises(parser.ParseError, p.parse, "if 42")
        info.value.expected_str is None
        info = py.test.raises(parser.ParseError, p.parse, "if 42 42")
        info.value.expected_str == '+'