toolkit.py 12.6 KB
Newer Older
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
"""toolkit.py - utility functions 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.


Module ``toolkit`` contains utility functions and cross-sectional
functionality like logging support that is needed across several 
of the the other DHParser-Modules.

For logging functionality, the global variable LOGGING is defined which
contains the name of a directory where log files shall be placed. By
setting its value to the empty string "" logging can be turned off.

To read the directory name function ``LOGS_DIR()`` should be called
rather than reading the variable LOGGING. ``LOGS_DIR()`` makes sure
the directory exists and raises an error if a file with the same name
already exists.
"""

import collections
Eckhart Arnold's avatar
Eckhart Arnold committed
34
import contextlib
35
36
import hashlib
import os
di68kap's avatar
di68kap committed
37
38
39
40
try:
    import regex as re
except ImportError:
    import re
41
from typing import List, Tuple
42
43


Eckhart Arnold's avatar
Eckhart Arnold committed
44
45
46
__all__ = ['logging',
           'is_logging',
           'log_dir',
47
           'logfile_basename',
48
           'line_col',
49
           'error_messages',
Eckhart Arnold's avatar
Eckhart Arnold committed
50
           'compact_sexpr',
51
           'escape_re',
Eckhart Arnold's avatar
Eckhart Arnold committed
52
           'is_filename',
53
54
           'load_if_file',
           'is_python_code',
55
56
           'md5',
           'expand_table',
57
           'smart_list',
58
           'sane_parser_name']
59
60


Eckhart Arnold's avatar
Eckhart Arnold committed
61
62
63
def log_dir() -> str:
    """Creates a directory for log files (if it does not exist) and
    returns its path.
64

Eckhart Arnold's avatar
Eckhart Arnold committed
65
66
67
    WARNING: Any files in the log dir will eventually be overwritten.
    Don't use a directory name that could be the name of a directory
    for other purposes than logging.
68
69
70
71

    Returns:
        name of the logging directory
    """
Eckhart Arnold's avatar
Eckhart Arnold committed
72
    # the try-except clauses in the following are precautions for multiprocessing
73
    global LOGGING
Eckhart Arnold's avatar
Eckhart Arnold committed
74
75
76
77
78
79
80
81
82
83
    try:
        dirname = LOGGING    # raises a name error if LOGGING is not defined
        if not dirname:
            raise NameError  # raise a name error if LOGGING evaluates to False
    except NameError:
        raise NameError("No access to log directory before logging has been turned "
                        "on within the same thread/process.")
    if os.path.exists(dirname) and not os.path.isdir(dirname):
        raise IOError('"' + dirname + '" cannot be used as log directory, '
                                      'because it is not a directory!')
84
    else:
Eckhart Arnold's avatar
Eckhart Arnold committed
85
86
87
88
89
        try:
            os.mkdir(dirname)
        except FileExistsError:
            pass
    info_file_name = os.path.join(dirname, 'info.txt')
90
91
92
93
    if not os.path.exists(info_file_name):
        with open(info_file_name, 'w') as f:
            f.write("This directory has been created by DHParser to store log files from\n"
                    "parsing. ANY FILE IN THIS DIRECTORY CAN BE OVERWRITTEN! Therefore,\n"
94
95
                    "do not place any files here and do not bother editing files in this\n"
                    "directory as any changes will get lost.\n")
96
97
98
    return dirname


Eckhart Arnold's avatar
Eckhart Arnold committed
99
100
101
102
103
104
105
106
107
108
@contextlib.contextmanager
def logging(dirname="LOGS"):
    """Context manager. Log files within this context will be stored in
    directory ``dirname``. Logging is turned off if name is empty.
    
    Args:
        dirname: the name for the log directory or the empty string to
            turn logging of
    """
    global LOGGING
Eckhart Arnold's avatar
Eckhart Arnold committed
109
    if dirname == True:  dirname = "LOGS"  # be fail tolerant here...
Eckhart Arnold's avatar
Eckhart Arnold committed
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
    try:
        save = LOGGING
    except NameError:
        save = ""
    LOGGING = dirname
    yield
    LOGGING = save


def is_logging():
    """-> True, if logging is turned on."""
    global LOGGING
    try:
        return bool(LOGGING)
    except NameError:
        return False


128
def line_col(text: str, pos: int) -> Tuple[int, int]:
129
130
131
132
133
134
135
136
    """Returns the position within a text as (line, column)-tuple.
    """
    assert pos < len(text), str(pos) + " >= " + str(len(text))
    line = text.count("\n", 0, pos) + 1
    column = pos - text.rfind("\n", 0, pos)
    return line, column


137
def error_messages(source_text, errors) -> List[str]:
138
139
140
141
142
143
144
145
146
147
148
    """Returns the sequence or iterator of error objects as an intertor
    of error messages with line and column numbers at the beginning.
    
    Args:
        source_text (str):  The source text on which the errors occurred.
            (Needed in order to determine the line and column numbers.)
        errors (list):  The list of errors as returned by the method 
            ``collect_errors()`` of a Node object     
    Returns:
        a list that contains all error messages in string form. Each
        string starts with "line: [Line-No], column: [Column-No]
149
    """
150
151
    return ["line: %i, column: %i, error: %s" % (*line_col(source_text, err.pos), err.msg)
            for err in sorted(list(errors))]
152
153


154
def compact_sexpr(s) -> str:
155
156
157
158
159
160
161
162
163
164
    """Returns S-expression ``s`` as a one liner without unnecessary
    whitespace.

    Example:
        >>> compact_sexpr("(a\n    (b\n        c\n    )\n)\n")
        (a (b c))
    """
    return re.sub('\s(?=\))', '', re.sub('\s+', ' ', s)).strip()


Eckhart Arnold's avatar
Eckhart Arnold committed
165
166
167
168
169
170
171
172
173
174
175
176
# def quick_report(parsing_result) -> str:
#     """Returns short report (compact s-expression + errors messages)
#     of the parsing results by either a call to a grammar or to a parser
#     directly."""
#     err = ''
#     if isinstance(parsing_result, collections.Collection):
#         result = parsing_result[0]
#         err = ('\nUnmatched sequence: ' + parsing_result[1]) if parsing_result[1] else ''
#     sexpr = compact_sexpr(result.as_sexpr())
#     return sexpr + err


177
def escape_re(s) -> str:
178
179
180
181
182
183
184
185
186
    """Returns `s` with all regular expression special characters escaped.
    """
    assert isinstance(s, str)
    re_chars = r"\.^$*+?{}[]()#<>=|!"
    for esc_ch in re_chars:
        s = s.replace(esc_ch, '\\' + esc_ch)
    return s


187
def is_filename(s) -> bool:
Eckhart Arnold's avatar
Eckhart Arnold committed
188
189
190
191
192
    """Tries to guess whether string ``s`` is a file name."""
    return s.find('\n') < 0 and s[:1] != " " and s[-1:] != " " \
           and s.find('*') < 0 and s.find('?') < 0


193
def logfile_basename(filename_or_text, function_or_class_or_instance) -> str:
Eckhart Arnold's avatar
Eckhart Arnold committed
194
195
196
197
198
199
200
201
202
203
204
205
206
207
    """Generates a reasonable logfile-name (without extension) based on
    the given information.
    """
    if is_filename(filename_or_text):
        return os.path.basename(os.path.splitext(filename_or_text)[0])
    else:
        try:
            s = function_or_class_or_instance.__qualname.__
        except AttributeError:
            s = function_or_class_or_instance.__class__.__name__
        i = s.find('.')
        return s[:i] + '_out' if i >= 0 else s


208
209
210
211
212
def load_if_file(text_or_file) -> str:
    """Reads and returns content of a text-file if parameter
    `text_or_file` is a file name (i.e. a single line string),
    otherwise (i.e. if `text_or_file` is a multiline string)
    `text_or_file` is returned.
213
    """
Eckhart Arnold's avatar
Eckhart Arnold committed
214
    if is_filename(text_or_file):
215
216
217
218
219
        try:
            with open(text_or_file, encoding="utf-8") as f:
                content = f.read()
            return content
        except FileNotFoundError as error:
220
            if re.fullmatch(r'[\w/:. \\]+', text_or_file):
221
222
223
224
                raise FileNotFoundError('Not a valid file: ' + text_or_file + '\nAdd "\\n" '
                                        'to distinguish source data from a file name!')
            else:
                return text_or_file
225
226
227
228
    else:
        return text_or_file


229
def is_python_code(text_or_file) -> bool:
230
231
232
    """Checks whether 'text_or_file' is python code or the name of a file that
    contains python code.
    """
Eckhart Arnold's avatar
Eckhart Arnold committed
233
    if is_filename(text_or_file):
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
        return text_or_file[-3:].lower() == '.py'
    try:
        compile(text_or_file, '<string>', 'exec')
        return True
    except (SyntaxError, ValueError, OverflowError):
        pass
    return False


def md5(*txt):
    """Returns the md5-checksum for `txt`. This can be used to test if
    some piece of text, for example a grammar source file, has changed.
    """
    md5_hash = hashlib.md5()
    for t in txt:
        md5_hash.update(t.encode('utf8'))
    return md5_hash.hexdigest()


253
254
def smart_list(arg) -> list:
    """Returns the argument as list, depending on its type and content.
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
    
    If the argument is a string, it will be interpreted as a list of
    comma separated values, trying ';', ',', ' ' as possible delimiters
    in this order, e.g.
        >>> smart_list("1; 2, 3; 4")
        ["1", "2, 3", "4"]
        >>> smart_list("2, 3")
        ["2", "3"]
        >>> smart_list("a b cd")
        ["a", "b", "cd"]
    If the argument is a collection other than a string, it will be
    returned as is, e.g.
        >>> smart_list((1, 2, 3))
        (1, 2, 3)
        >>> smart_list({1, 2, 3})
        {1, 2, 3}
    If the argument is another iterable than a collection, it will
    be converted into a list, e.g.
        >>> smart_list(i for i in {1,2,3})
        [1, 2, 3]
    Finally, if none of the above is true, the argument will be 
    wrapped in a list and returned, e.g.
        >>> smart_list(125)
        [125]
    """
    if isinstance(arg, str):
        for delimiter in (';', ','):
            lst = arg.split(delimiter)
            if len(lst) > 1:
284
285
                return [s.strip() for s in lst]
        return [s.strip() for s in arg.strip().split(' ')]
Eckhart Arnold's avatar
Eckhart Arnold committed
286
287
    # elif isinstance(arg, collections.abc.Sequence):  # python 3.6: collections.abc.Collection
    #     return arg
288
    elif isinstance(arg, collections.abc.Iterable):
289
        return list(arg)
290
291
292
293
    else:
        return [arg]


294
295
296
297
298
299
300
301
302
303
304
305
def expand_table(compact_table):
    """Expands a table by separating keywords that are tuples or strings
    containing comma separated words into single keyword entries with
    the same values. Returns the expanded table.
    Example:
    >>> expand_table({"a, b": 1, "b": 1, ('d','e','f'):5, "c":3})
    {'a': 1, 'b': 1, 'c': 3, 'd': 5, 'e': 5, 'f': 5}
    """
    expanded_table = {}
    keys = list(compact_table.keys())
    for key in keys:
        value = compact_table[key]
306
        for k in smart_list(key):
307
308
            if k in expanded_table:
                raise KeyError("Key %s used more than once in compact table!" % key)
309
            expanded_table[k] = value
310
    return expanded_table
311

312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
# # commented, because this approach is too error-prone in connection with smart_list
# def as_partial(partial_ellipsis) -> functools.partial:
#     """Transforms ``partial_ellipsis`` into a partial function
#     application, i.e. string "remove_tokens({'(', ')'})" will be
#     transformed into the partial "partial(remove_tokens, {'(', ')'})".
#     Partial ellipsises can be considered as a short hand notation for
#     partials, which look like function, calls but aren't. Plain
#     function names are returned as is. Also, if ``partial_ellipsis``
#     already is a callable, it will be returned as is.
#     """
#     if callable(partial_ellipsis):
#         return partial_ellipsis
#     m = re.match('\s*(\w+)(?:\(([^)]*)\))?\s*$', partial_ellipsis)
#     if m:
#         fname, fargs = m.groups()
#         return eval("functools.partial(%s, %s)" % (fname, fargs)) if fargs else eval(fname)
#     raise SyntaxError(partial_ellipsis + " does not resemble a partial function ellipsis!")

330

331
def sane_parser_name(name) -> bool:
332
333
334
    """Checks whether given name is an acceptable parser name. Parser names
    must not be preceeded or succeeded by a double underscore '__'!
    """
di68kap's avatar
di68kap committed
335
336
337
    return name and name[:2] != '__' and name[-2:] != '__'


338
339
340
341
def compile_python_object(python_src, catch_obj_regex=""):
    """Compiles the python source code and returns the (first) object 
    the name of which is matched by ``catch_obj_regex``. If catch_obj
    is the empty string, the namespace dictionary will be returned.
di68kap's avatar
di68kap committed
342
343
344
345
346
347
    """
    if isinstance(catch_obj_regex, str):
        catch_obj_regex = re.compile(catch_obj_regex)
    code = compile(python_src, '<string>', 'exec')
    namespace = {}
    exec(code, namespace)  # safety risk?
348
349
350
351
352
353
354
355
356
357
358
    if catch_obj_regex:
        matches = [key for key in namespace.keys() if catch_obj_regex.match(key)]
        if len(matches) == 0:
            raise ValueError("No object matching /%s/ defined in source code." %
                             catch_obj_regex.pattern)
        elif len(matches) > 1:
            raise ValueError("Ambigous matches for %s : %s" %
                             (str(catch_obj_regex), str(matches)))
        return namespace[matches[0]] if matches else None
    else:
        return namespace