1 |
73
|
aaronmk
|
# String manipulation
|
2 |
|
|
|
3 |
1295
|
aaronmk
|
import codecs
|
4 |
861
|
aaronmk
|
import re
|
5 |
|
|
|
6 |
1232
|
aaronmk
|
import util
|
7 |
|
|
|
8 |
1622
|
aaronmk
|
##### Parsing
|
9 |
|
|
|
10 |
2932
|
aaronmk
|
def concat(str0, str1, max_len): return str0[:max_len-len(str1)]+str1
|
11 |
|
|
|
12 |
1622
|
aaronmk
|
def split(sep, str_):
|
13 |
|
|
'''Returns [] if str_ == ""'''
|
14 |
|
|
if str_ == '': return []
|
15 |
|
|
else: return str_.split(sep)
|
16 |
|
|
|
17 |
2221
|
aaronmk
|
def remove_prefix(prefix, str_, removed_ref=None):
|
18 |
|
|
if removed_ref == None: removed_ref = [False]
|
19 |
|
|
|
20 |
|
|
removed_ref[0] = str_.startswith(prefix)
|
21 |
|
|
if removed_ref[0]: return str_[len(prefix):]
|
22 |
1622
|
aaronmk
|
else: return str_
|
23 |
|
|
|
24 |
1680
|
aaronmk
|
def remove_prefixes(prefixes, str_):
|
25 |
|
|
for prefix in prefixes: str_ = remove_prefix(prefix, str_)
|
26 |
|
|
return str_
|
27 |
|
|
|
28 |
|
|
def with_prefixes(prefixes, str_): return (p+str_ for p in prefixes)
|
29 |
|
|
|
30 |
2221
|
aaronmk
|
def remove_suffix(suffix, str_, removed_ref=None):
|
31 |
|
|
if removed_ref == None: removed_ref = [False]
|
32 |
|
|
|
33 |
|
|
removed_ref[0] = str_.endswith(suffix)
|
34 |
|
|
if removed_ref[0]: return str_[:-len(suffix)]
|
35 |
1622
|
aaronmk
|
else: return str_
|
36 |
|
|
|
37 |
1959
|
aaronmk
|
def contains_any(haystack, needles):
|
38 |
|
|
for needle in needles:
|
39 |
|
|
if haystack.find(needle) >= 0: return True
|
40 |
|
|
return False
|
41 |
|
|
|
42 |
1622
|
aaronmk
|
def overlaps(str0, str1): return str0.find(str1) >= 0 or str1.find(str0) >= 0
|
43 |
|
|
|
44 |
2761
|
aaronmk
|
##### Escaping
|
45 |
|
|
|
46 |
|
|
def esc_for_mogrify(query):
|
47 |
|
|
'''Escapes a query right before being passed to a mogrifying function.'''
|
48 |
|
|
return query.replace('%', '%%')
|
49 |
|
|
|
50 |
1401
|
aaronmk
|
##### Unicode
|
51 |
|
|
|
52 |
2882
|
aaronmk
|
def to_raw_str(str_):
|
53 |
|
|
if isinstance(str_, unicode): str_ = str_.encode('utf_8')
|
54 |
|
|
return str_
|
55 |
|
|
|
56 |
1295
|
aaronmk
|
unicode_reader = codecs.getreader('utf_8')
|
57 |
|
|
|
58 |
73
|
aaronmk
|
def to_unicode(str_):
|
59 |
|
|
if isinstance(str_, unicode): return str_
|
60 |
|
|
encodings = ['utf_8', 'latin_1']
|
61 |
|
|
for encoding in encodings:
|
62 |
|
|
try: return unicode(str_, encoding)
|
63 |
|
|
except UnicodeDecodeError, e: pass
|
64 |
|
|
raise AssertionError(encoding+' is not a catch-all encoding')
|
65 |
340
|
aaronmk
|
|
66 |
1232
|
aaronmk
|
def ustr(val):
|
67 |
|
|
'''Like built-in str() but converts to unicode object'''
|
68 |
|
|
if not util.is_str(val): val = str(val)
|
69 |
|
|
return to_unicode(val)
|
70 |
|
|
|
71 |
2502
|
aaronmk
|
def repr_no_u(value):
|
72 |
|
|
'''Like built-in repr() but removes the "u" in `u'...'`'''
|
73 |
2582
|
aaronmk
|
return re.sub(r"^u(?=')", r'', repr(value))
|
74 |
2502
|
aaronmk
|
|
75 |
1401
|
aaronmk
|
##### Line endings
|
76 |
|
|
|
77 |
1622
|
aaronmk
|
def extract_line_ending(line):
|
78 |
|
|
'''@return tuple (contents, ending)'''
|
79 |
|
|
contents = remove_suffix('\r', remove_suffix('\n', line))
|
80 |
|
|
return (contents, line[len(contents):])
|
81 |
714
|
aaronmk
|
|
82 |
1622
|
aaronmk
|
def remove_line_ending(line): return extract_line_ending(line)[0]
|
83 |
|
|
|
84 |
|
|
def ensure_newl(str_): return remove_line_ending(str_)+'\n'
|
85 |
|
|
|
86 |
856
|
aaronmk
|
def is_multiline(str_):
|
87 |
|
|
newl_idx = str_.find('\n')
|
88 |
|
|
return newl_idx >= 0 and newl_idx != len(str_)-1 # has newline before end
|
89 |
|
|
|
90 |
860
|
aaronmk
|
def remove_extra_newl(str_):
|
91 |
856
|
aaronmk
|
if is_multiline(str_): return str_
|
92 |
2480
|
aaronmk
|
else: return str_.rstrip('\n')
|
93 |
856
|
aaronmk
|
|
94 |
714
|
aaronmk
|
def std_newl(str_): return str_.replace('\r\n', '\n').replace('\r', '\n')
|
95 |
|
|
|
96 |
3255
|
aaronmk
|
def join_lines(lines): return ''.join((l+'\n' for l in lines))
|
97 |
|
|
|
98 |
1401
|
aaronmk
|
##### Whitespace
|
99 |
|
|
|
100 |
714
|
aaronmk
|
def cleanup(str_): return std_newl(str_.strip())
|
101 |
861
|
aaronmk
|
|
102 |
1364
|
aaronmk
|
def single_space(str_): return re.sub(r' {2,}', r' ', str_.strip())
|
103 |
|
|
|
104 |
861
|
aaronmk
|
def one_line(str_): return re.sub(r'\n *', r' ', cleanup(str_))
|
105 |
1761
|
aaronmk
|
|
106 |
|
|
##### Control characters
|
107 |
|
|
|
108 |
|
|
def is_ctrl(char):
|
109 |
|
|
'''Whether char is a (non-printable) control character'''
|
110 |
|
|
return ord(char) < 32 and not char.isspace()
|
111 |
|
|
|
112 |
|
|
def strip_ctrl(str_):
|
113 |
|
|
'''Strips (non-printable) control characters'''
|
114 |
|
|
return ''.join(filter(lambda c: not is_ctrl(c), str_))
|
115 |
2471
|
aaronmk
|
|
116 |
3172
|
aaronmk
|
##### Text
|
117 |
|
|
|
118 |
|
|
def first_word(str_): return str_.partition(' ')[0]
|
119 |
|
|
|
120 |
2471
|
aaronmk
|
##### Formatting
|
121 |
|
|
|
122 |
2477
|
aaronmk
|
def as_tt(str_): return '@'+str_+'@'
|
123 |
|
|
|
124 |
2475
|
aaronmk
|
def as_code(str_, lang=None, multiline=True):
|
125 |
2471
|
aaronmk
|
'''Wraps a string in Redmine tags to syntax-highlight it.'''
|
126 |
2480
|
aaronmk
|
str_ = '\n'+str_.rstrip('\n')+'\n'
|
127 |
2471
|
aaronmk
|
if lang != None: str_ = '<code class="'+lang+'">'+str_+'</code>'
|
128 |
2475
|
aaronmk
|
if multiline: str_ = '<pre>'+str_+'</pre>'
|
129 |
|
|
return str_
|
130 |
2477
|
aaronmk
|
|
131 |
2504
|
aaronmk
|
def as_inline_table(dict_, key_label='Output', value_label='Input', ustr=ustr):
|
132 |
2477
|
aaronmk
|
'''Wraps a dict in Redmine tags to format it as a table.'''
|
133 |
|
|
str_ = ''
|
134 |
2481
|
aaronmk
|
def row(entry): return (': '.join(entry))+'\n'
|
135 |
2477
|
aaronmk
|
str_ += row([key_label, value_label])
|
136 |
2481
|
aaronmk
|
for entry in dict_.iteritems(): str_ += row([ustr(v) for v in entry])
|
137 |
|
|
return '<pre>\n'+str_+'</pre>'
|
138 |
2482
|
aaronmk
|
|
139 |
2504
|
aaronmk
|
def as_table(dict_, key_label='Output', value_label='Input', ustr=ustr):
|
140 |
2482
|
aaronmk
|
'''Wraps a dict in Redmine tags to format it as a table.'''
|
141 |
|
|
str_ = ''
|
142 |
|
|
def row(entry): return ('|'.join(['']+entry+['']))+'\n'# '' for outer border
|
143 |
|
|
str_ += row([key_label, value_label])
|
144 |
|
|
for entry in dict_.iteritems(): str_ += row([as_tt(ustr(v)) for v in entry])
|
145 |
|
|
return '\n'+str_+' ' # space protects last \n so blank line ends table
|