Rev 295 | Rev 297 | Go to most recent revision | Show entire file | Ignore whitespace | Details | Blame | Last modification | View Log | RSS feed
| Rev 295 | Rev 296 | ||
|---|---|---|---|
| Line 30... | Line 30... | ||
| 30 | class Dictionary(dict): |
30 | class Dictionary(dict): |
| 31 | """
|
31 | """
|
| 32 | classdocs
|
32 | classdocs
|
| 33 |
|
33 |
|
| 34 | """
|
34 | """
|
| - | 35 | _language_key = 'en' |
|
| 35 | _keys = "ipa|en|lit|pos|com|tag|ex" |
36 | _keys = "ipa|en|lit|pos|com|tag|ex" |
| 36 | _expressions = {} |
37 | _expressions = {} |
| 37 | 38 | ||
| 38 | def load (self, dictionary_file, language_key='en'): |
39 | def load (self, dictionary_file, language_key='en'): |
| - | 40 | self._language_key = language_key |
|
| - | 41 | ||
| 39 | dmsg('Loading dictionary '.format(dictionary_file), end='', min_level=1) |
42 | dmsg('Loading dictionary '.format(dictionary_file), end='', min_level=1) |
| 40 | 43 | ||
| 41 | chdir(dirname(realpath(__file__))) |
44 | chdir(dirname(realpath(__file__))) |
| 42 | 45 | ||
| 43 | pickle_file = basename(dictionary_file) + '.pickle' |
46 | pickle_file = basename(dictionary_file) + '.pickle' |
| Line 54... | Line 57... | ||
| 54 | value = None |
57 | value = None |
| 55 | with open(dictionary_file) as f: |
58 | with open(dictionary_file) as f: |
| 56 | indent = None |
59 | indent = None |
| 57 | 60 | ||
| 58 | for line in f: |
61 | for line in f: |
| 59 | m = match(r'^\s*{0}:\s*(?P<phrase>.+)'.format(language_key), line) |
62 | m = match(r'^\s*{0}:\s*(?P<phrase>.+)'.format(self._language_key), line) |
| 60 | if m is not None: |
63 | if m is not None: |
| 61 | phrase = m.group("phrase") |
64 | phrase = m.group("phrase") |
| 62 | self[phrase] = {} |
65 | self[phrase] = {} |
| 63 | indent = None |
66 | indent = None |
| 64 | else:
|
67 | else:
|
| Line 100... | Line 103... | ||
| 100 | self[key] = value |
103 | self[key] = value |
| 101 | 104 | ||
| 102 | dmsg(' done ({0} entries).'.format(len(self)), min_level=1) |
105 | dmsg(' done ({0} entries).'.format(len(self)), min_level=1) |
| 103 | 106 | ||
| 104 | def clean (self): |
107 | def clean (self): |
| 105 | parens_re = compile(r'\(.+\)', DOTALL) |
108 | re_parens = compile(r'\(.+\)', DOTALL) |
| - | 109 | re_parens_no_alt = compile(r'\(([^|]+)\)', DOTALL) |
|
| 106 | braces_re = compile( |
110 | re_braces = compile( |
| 107 | r'^\s*\{(?P<phrase>.+)\}(?:\s*\((?P<variant>.+?)\))?\s*$', |
111 | r'^\s*\{(?P<phrase>.+)\}(?:\s*\((?P<variant>.+?)\))?\s*$', |
| 108 | DOTALL)
|
112 | DOTALL)
|
| 109 | semicolon_re = compile(r'\s*;\s*') |
113 | re_semicolon = compile(r'\s*;\s*') |
| 110 | 114 | ||
| 111 | for orig_phrase, data in list(self.items()): |
115 | for orig_phrase, data in list(self.items()): |
| 112 | # if there are optional or alternating parts
|
116 | # if there are optional or alternating parts
|
| 113 | if search(parens_re, orig_phrase): |
117 | if search(re_parens, orig_phrase): |
| 114 | if orig_phrase.find('|') > -1: |
118 | if orig_phrase.find('|') > -1: |
| 115 | # TODO alternation
|
119 | # TODO alternation
|
| 116 | pass
|
120 | pass
|
| 117 | else:
|
121 | else:
|
| 118 | # TODO optional parts
|
122 | # TODO optional parts
|
| 119 | pass
|
123 | pass
|
| 120 | 124 | ||
| 121 | if orig_phrase.find(';') > -1: |
125 | if orig_phrase.find(';') > -1: |
| 122 | synonyms = map( |
126 | synonyms = map( |
| 123 | lambda x: sub(braces_re, r'\1', x), |
127 | lambda x: sub(re_braces, r'\1', x), |
| 124 | split(semicolon_re, orig_phrase)) |
128 | split(re_semicolon, orig_phrase)) |
| 125 | 129 | ||
| 126 | for synonym in synonyms: |
130 | for synonym in synonyms: |
| 127 | self[synonym] = data |
131 | self[synonym] = data |
| 128 | 132 | ||
| 129 | del self[orig_phrase] |
133 | del self[orig_phrase] |
| 130 | else:
|
134 | else:
|
| 131 | m = match(braces_re, orig_phrase) |
135 | m = match(re_braces, orig_phrase) |
| 132 | if m is not None: |
136 | if m is not None: |
| 133 | phrase = m.group("phrase") |
137 | phrase = m.group("phrase") |
| 134 | m2 = match(parens_re, phrase) |
138 | m_parens = search(re_parens, phrase) |
| 135 | if m2 is not None: |
139 | if m_parens is not None: |
| 136 | # TODO alternation and optional parts
|
140 | # alternation and optional parts
|
| - | 141 | expr = sub(re_parens_no_alt, r'(?:\1)?', phrase) |
|
| - | 142 | expr = sub('~', '(?=.)', expr) |
|
| - | 143 | self._expressions[expr] = data |
|
| 137 | pass
|
144 | else:
|
| - | 145 | # remove braces
|
|
| - | 146 | self[phrase] = data |
|
| 138 | 147 | ||
| 139 | self[phrase] = data |
- | |
| 140 | del self[orig_phrase] |
148 | del self[orig_phrase] |
| - | 149 | ||
| - | 150 | def translate (self, phrase): |
|
| - | 151 | translation = self.get(phrase.lower(), None) |
|
| - | 152 | if translation is not None: |
|
| - | 153 | translation[self._language_key] = phrase |
|
| - | 154 | return translation
|
|
| - | 155 | ||
| - | 156 | return None |
|
| - | 157 | ||
| - | 158 | def translate_expression (self, phrase): |
|
| - | 159 | for expression, data in list(self._expressions.items()): |
|
| - | 160 | expression_match = match(expression, phrase) |
|
| - | 161 | if expression_match is not None: |
|
| - | 162 | data[self._language_key] = expression_match.group(0) |
|
| - | 163 | return data
|
|
| - | 164 | ||
| - | 165 | return None |
|