11.3.2021, 9:00 - 11:00: Due to updates GitLab may be unavailable for some minutes between 09:00 and 11:00.

dhparser.py 8.46 KB
Newer Older
1
#!/usr/bin/python
2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20

"""dhparser.py - command line tool for DHParser

Copyright 2016  by Eckhart Arnold (arnold@badw.de)
                Bavarian Academy of Sciences an Humanities (badw.de)

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.
"""

21
#  TODO: This is still a stub...
22

23 24 25
import os
import sys

26
from DHParser.dsl import compileDSL, compile_on_disk
Eckhart Arnold's avatar
Eckhart Arnold committed
27
from DHParser.ebnf import get_ebnf_grammar, get_ebnf_transformer, get_ebnf_compiler
28
from DHParser.parser import compile_source
29
from DHParser.toolkit import logging
30

31

32
EBNF_TEMPLATE = r"""-grammar
33

34 35 36 37 38 39 40
#######################################################################
#
#  EBNF-Directives
#
#######################################################################

@ testing     = True            # testing supresses error messages for unconnected symbols
41
@ whitespace  = vertical        # implicit whitespace, includes any number of line feeds
42
@ literalws   = right           # literals have implicit whitespace on the right hand side 
Eckhart Arnold's avatar
Eckhart Arnold committed
43
@ comment     = /#.*/           # comments range from a '#'-character to the end of the line
44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65
@ ignorecase  = False           # literals and regular expressions are case-sensitive


#######################################################################
#
#  Structure and Components
#
#######################################################################

document = //~ { WORD } §EOF    # root parser: optional whitespace followed by a sequence of words
                                # until the end of file

#######################################################################
#
#  Regular Expressions
#
#######################################################################

WORD     =  /\w+/~              # a sequence of letters, possibly followed by implicit whitespace
EOF      =  !/./                # no more characters ahead, end of file reached
"""

66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81
TEST_WORD_TEMPLATE = r'''[match:WORD]
1  : word
2  : one_word_with_underscores

[fail:WORD]
1  : two words
'''

TEST_DOCUMENT_TEMPLATE = r'''[match:document]
1  : """This is a sequence of words
     extending over several lines"""
     
[fail:document]
1  : """This test should fail, because neither
     comma nor full have been defined anywhere."""
'''
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

README_TEMPLATE = """# {name}

PLACE A SHORT DESCRIPTION HERE

Author: AUTHOR'S NAME <EMAIL>, AFFILIATION


## License

{name} is open source software under the [MIT License](https://opensource.org/licenses/MIT)

Copyright YEAR AUTHOR'S NAME <EMAIL>, AFFILIATION

Permission is hereby granted, free of charge, to any person obtaining
a copy of this software and associated documentation files (the 
"Software"), to deal in the Software without restriction, including
without limitation the rights to use, copy, modify, merge, publish,
distribute, sublicense, and/or sell copies of the Software, and to
permit persons to whom the Software is furnished to do so, subject
 to the following conditions:

The above copyright notice and this permission notice shall be included
in all copies or substantial portions of the Software.

THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF 
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
"""


117
GRAMMAR_TEST_TEMPLATE = r'''#!/usr/bin/python3
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

"""tst_{name}_grammar.py - runs the unit tests for the {name}-grammar
"""

import sys

import DHParser.dsl
from DHParser import testing
from DHParser import toolkit

if not DHParser.dsl.recompile_grammar('{name}.ebnf', force=False):  # recompiles Grammar only if it has changed
    print('\nErrors while recompiling "{name}.ebnf":\n--------------------------------------\n\n')
    with open('{name}_ebnf_ERRORS.txt') as f:
        print(f.read())
    sys.exit(1)

sys.path.append('./')
# must be appended after module creation, because otherwise an ImportError is raised under Windows
from {name}Compiler import get_grammar, get_transformer

with toolkit.logging(True):
    error_report = testing.grammar_suite('grammar_tests', get_grammar,
                                         get_transformer, report=True, verbose=True)
if error_report:
    print('\n')
    print(error_report)
    sys.exit(1)
else:
    print('\nSUCCESS! All tests passed :-)')
'''
148 149 150 151 152 153 154 155 156 157 158 159


def selftest() -> bool:
    print("DHParser selftest...")
    print("\nSTAGE I:  Trying to compile EBNF-Grammar:\n")
    builtin_ebnf_parser = get_ebnf_grammar()
    ebnf_src = builtin_ebnf_parser.__doc__[builtin_ebnf_parser.__doc__.find('#'):]
    ebnf_transformer = get_ebnf_transformer()
    ebnf_compiler = get_ebnf_compiler('EBNF')
    generated_ebnf_parser, errors, ast = compile_source(ebnf_src, None,
        builtin_ebnf_parser, ebnf_transformer, ebnf_compiler)

160
    if errors:
161 162 163 164 165 166 167
        print("Selftest FAILED :-(")
        print("\n\n".join(errors))
        return False
    print(generated_ebnf_parser)
    print("\n\nSTAGE 2: Selfhosting-test: Trying to compile EBNF-Grammar with generated parser...\n")
    selfhosted_ebnf_parser = compileDSL(ebnf_src, None, generated_ebnf_parser,
                                        ebnf_transformer, ebnf_compiler)
168
    ebnf_compiler.gen_transformer_skeleton()
169 170 171 172
    print(selfhosted_ebnf_parser)
    print("\n\n Selftest SUCCEEDED :-)\n\n")
    return True

173

174 175 176 177
def create_project(path,
                   ebnf_tmpl=EBNF_TEMPLATE,
                   readme_tmpl=README_TEMPLATE,
                   grammar_test_tmpl=GRAMMAR_TEST_TEMPLATE):
178 179 180 181 182 183 184 185 186 187
    def create_file(name, content):
        if not os.path.exists(name):
            print('Creating file "%s".' % name)
            with open(name, 'w') as f:
                f.write(content)
        else:
            print('"%s" already exists! Not overwritten.' % name)

    if os.path.exists(path) and not os.path.isdir(path):
        print('Cannot create new project, because a file named "%s" alread exists!' % path)
188 189
        sys.exit(1)
    name = os.path.basename(path)
190 191 192 193
    print('Creating new DHParser-project "%s".' % name)
    if not os.path.exists(path):
        os.mkdir(path)
    curr_dir = os.getcwd()
194
    os.chdir(path)
195 196 197 198 199 200 201 202 203 204 205 206 207
    if os.path.exists('grammar_tests'):
        if not os.path.isdir('grammar_tests'):
            print('Cannot overwrite existing file "grammar_tests"')
            sys.exit(1)
    else:
        os.mkdir('grammar_tests')

    create_file(os.path.join('grammar_tests', '01_test_word.ini'), TEST_WORD_TEMPLATE)
    create_file(os.path.join('grammar_tests', '02_test_document.ini'), TEST_DOCUMENT_TEMPLATE)
    create_file(name + '.ebnf', '# ' + name + EBNF_TEMPLATE)
    create_file('README.md', README_TEMPLATE.format(name=name))
    create_file('tst_%s_grammar.py' % name, GRAMMAR_TEST_TEMPLATE.format(name=name))
    os.chdir(curr_dir)
208 209
    print('ready.')

210 211

def profile(func):
212
    import cProfile, pstats
213 214
    pr = cProfile.Profile()
    pr.enable()
215 216 217 218
    for i in range(1):
        success = func()
        if not success:
            break
219 220
    pr.disable()
    # after your program ends
221 222 223
    st = pstats.Stats(pr)
    st.strip_dirs()
    st.sort_stats('time').print_stats(10)
224
    return success
225 226


227 228 229 230 231 232 233 234 235 236 237 238
def mem_profile(func):
    import tracemalloc
    tracemalloc.start()
    success = func()
    snapshot = tracemalloc.take_snapshot()
    top_stats = snapshot.statistics('lineno')
    print("[ Top 20 ]")
    for stat in top_stats[:20]:
        print(stat)
    return success


239 240
if __name__ == "__main__":
    if len(sys.argv) > 1:
241
        if os.path.exists(sys.argv[1]) and os.path.isfile(sys.argv[1]):
242 243 244 245 246 247 248
            _errors = compile_on_disk(sys.argv[1],
                                      sys.argv[2] if len(sys.argv) > 2 else "")
            if _errors:
                print('\n\n'.join(_errors))
                sys.exit(1)
        else:
            create_project(sys.argv[1])
249 250 251
    else:
        # run self test
        # selftest('EBNF/EBNF.ebnf')
252
        with logging(False):
253
            if not mem_profile(selftest):
254 255
                sys.exit(1)