toolkit.py 9.6 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
34
35
"""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
import hashlib
import os
di68kap's avatar
di68kap committed
36
37
38
39
try:
    import regex as re
except ImportError:
    import re
40
41
42
43
44
45


__all__ = ['logging_on',
           'logging_off',
           'IS_LOGGING',
           'LOGS_DIR',
46
           'line_col',
47
           'error_messages',
48
49
50
           'escape_re',
           'load_if_file',
           'is_python_code',
51
52
           'md5',
           'expand_table',
53
           'smart_list',
54
           'sane_parser_name']
55
56


57
LOGGING: str = ""  # "LOGS"  # LOGGING = "" turns logging off!
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


def logging_on(log_subdir="LOGS"):
    "Turns logging of syntax trees and parser history on."
    global LOGGING
    LOGGING = log_subdir


def logging_off():
    "Turns logging of syntax trees and parser history off."
    global LOGGING
    LOGGING = ""


def IS_LOGGING():
    """-> True, if logging is turned on."""
    return bool(LOGGING)


def LOGS_DIR() -> str:
    """Returns a path of a directory where log files will be stored.
    
    The default name of the logging directory is taken from the LOGGING
    variabe (default value 'LOGS'). The directory will be created if it
    does not exist. If the directory name does not contain a leading
    slash '/' it will be created as a subdirectory of the current
    directory Any files in the logging directory can be overwritten!
    
    Raises:
        AssertionError if logging has been turned off 
    Returns:
        name of the logging directory
    """
    global LOGGING
    if not LOGGING:
        raise AssertionError("Cannot use LOGS_DIR() if logging is turned off!")
    dirname = LOGGING
    if os.path.exists(LOGGING):
        if not os.path.isdir(LOGGING):
            raise IOError('"' + LOGGING + '" cannot be used as log directory, '
                                          'because it is not a directory!')
    else:
        os.mkdir(LOGGING)
    info_file_name = os.path.join(LOGGING, 'info.txt')
    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"
106
107
                    "do not place any files here and do not bother editing files in this\n"
                    "directory as any changes will get lost.\n")
108
109
110
    return dirname


111
112
113
114
115
116
117
118
119
def line_col(text, pos):
    """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


120
121
122
123
124
125
126
127
128
129
130
131
def error_messages(source_text, errors):
    """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]
132
    """
133
134
    return ["line: %i, column: %i, error: %s" % (*line_col(source_text, err.pos), err.msg)
            for err in sorted(list(errors))]
135
136


137
138
139
140
141
142
143
144
145
146
147
def compact_sexpr(s):
    """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()


148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
def escape_re(s):
    """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


def load_if_file(text_or_file):
    """Reads and returns content of a 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.
    """
163
    if text_or_file.find('\n') < 0:
164
165
166
167
168
        try:
            with open(text_or_file, encoding="utf-8") as f:
                content = f.read()
            return content
        except FileNotFoundError as error:
169
170
171
172
173
            if re.fullmatch(r'[\w/:\\]+', text_or_file):
                raise FileNotFoundError('Not a valid file: ' + text_or_file + '\nAdd "\\n" '
                                        'to distinguish source data from a file name!')
            else:
                return text_or_file
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
    else:
        return text_or_file


def is_python_code(text_or_file):
    """Checks whether 'text_or_file' is python code or the name of a file that
    contains python code.
    """
    if text_or_file.find('\n') < 0:
        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()


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
def smart_list(arg):
    """Returns the argument as list, depending on its type and content.
    
    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:
                return (s.strip() for s in lst)
        return (s.strip() for s in arg.strip().split(' '))
    elif isinstance(arg, collections.abc.Collection):
        return arg
    elif isinstance(arg, collections.abc.Iterable):
        return list(arg)
    else:
        return [arg]


243
244
245
246
247
248
249
250
251
252
253
254
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]
255
        for k in smart_list(key):
256
257
            if k in expanded_table:
                raise KeyError("Key %s used more than once in compact table!" % key)
258
            expanded_table[k] = value
259
    return expanded_table
260
261
262
263
264
265


def sane_parser_name(name):
    """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
266
267
268
269
270
271
272
273
274
275
276
277
278
    return name and name[:2] != '__' and name[-2:] != '__'


def compile_python_object(python_src, catch_obj_regex):
    """Compiles the python source code and returns the object the name of which
    ends is matched by ``catch_obj_regex``.
    """
    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?
    matches = [key for key in namespace.keys() if catch_obj_regex.match(key)]
279
280
281
282
283
284
    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)))
di68kap's avatar
di68kap committed
285
    return namespace[matches[0]] if matches else None