| 1 | # -*- coding: utf-8 -*- |
|---|
| 2 | # |
|---|
| 3 | # Copyright (C) 2007 Edgewall Software |
|---|
| 4 | # All rights reserved. |
|---|
| 5 | # |
|---|
| 6 | # This software is licensed as described in the file COPYING, which |
|---|
| 7 | # you should have received as part of this distribution. The terms |
|---|
| 8 | # are also available at http://genshi.edgewall.org/wiki/License. |
|---|
| 9 | # |
|---|
| 10 | # This software consists of voluntary contributions made by many |
|---|
| 11 | # individuals. For the exact contribution history, see the revision |
|---|
| 12 | # history and logs, available at http://genshi.edgewall.org/log/. |
|---|
| 13 | |
|---|
| 14 | """Utilities for internationalization and localization of templates. |
|---|
| 15 | |
|---|
| 16 | :since: version 0.4 |
|---|
| 17 | """ |
|---|
| 18 | |
|---|
| 19 | from compiler import ast |
|---|
| 20 | try: |
|---|
| 21 | frozenset |
|---|
| 22 | except NameError: |
|---|
| 23 | from sets import ImmutableSet as frozenset |
|---|
| 24 | from gettext import gettext |
|---|
| 25 | import re |
|---|
| 26 | |
|---|
| 27 | from genshi.core import Attrs, Namespace, QName, START, END, TEXT, START_NS, \ |
|---|
| 28 | END_NS, XML_NAMESPACE, _ensure |
|---|
| 29 | from genshi.template.base import Template, EXPR, SUB |
|---|
| 30 | from genshi.template.markup import MarkupTemplate, EXEC |
|---|
| 31 | |
|---|
| 32 | __all__ = ['Translator', 'extract'] |
|---|
| 33 | __docformat__ = 'restructuredtext en' |
|---|
| 34 | |
|---|
| 35 | I18N_NAMESPACE = Namespace('http://genshi.edgewall.org/i18n') |
|---|
| 36 | |
|---|
| 37 | |
|---|
| 38 | class Translator(object): |
|---|
| 39 | """Can extract and translate localizable strings from markup streams and |
|---|
| 40 | templates. |
|---|
| 41 | |
|---|
| 42 | For example, assume the followng template: |
|---|
| 43 | |
|---|
| 44 | >>> from genshi.template import MarkupTemplate |
|---|
| 45 | >>> |
|---|
| 46 | >>> tmpl = MarkupTemplate('''<html xmlns:py="http://genshi.edgewall.org/"> |
|---|
| 47 | ... <head> |
|---|
| 48 | ... <title>Example</title> |
|---|
| 49 | ... </head> |
|---|
| 50 | ... <body> |
|---|
| 51 | ... <h1>Example</h1> |
|---|
| 52 | ... <p>${_("Hello, %(name)s") % dict(name=username)}</p> |
|---|
| 53 | ... </body> |
|---|
| 54 | ... </html>''', filename='example.html') |
|---|
| 55 | |
|---|
| 56 | For demonstration, we define a dummy ``gettext``-style function with a |
|---|
| 57 | hard-coded translation table, and pass that to the `Translator` initializer: |
|---|
| 58 | |
|---|
| 59 | >>> def pseudo_gettext(string): |
|---|
| 60 | ... return { |
|---|
| 61 | ... 'Example': 'Beispiel', |
|---|
| 62 | ... 'Hello, %(name)s': 'Hallo, %(name)s' |
|---|
| 63 | ... }[string] |
|---|
| 64 | >>> |
|---|
| 65 | >>> translator = Translator(pseudo_gettext) |
|---|
| 66 | |
|---|
| 67 | Next, the translator needs to be prepended to any already defined filters |
|---|
| 68 | on the template: |
|---|
| 69 | |
|---|
| 70 | >>> tmpl.filters.insert(0, translator) |
|---|
| 71 | |
|---|
| 72 | When generating the template output, our hard-coded translations should be |
|---|
| 73 | applied as expected: |
|---|
| 74 | |
|---|
| 75 | >>> print tmpl.generate(username='Hans', _=pseudo_gettext) |
|---|
| 76 | <html> |
|---|
| 77 | <head> |
|---|
| 78 | <title>Beispiel</title> |
|---|
| 79 | </head> |
|---|
| 80 | <body> |
|---|
| 81 | <h1>Beispiel</h1> |
|---|
| 82 | <p>Hallo, Hans</p> |
|---|
| 83 | </body> |
|---|
| 84 | </html> |
|---|
| 85 | |
|---|
| 86 | Note that elements defining ``xml:lang`` attributes that do not contain |
|---|
| 87 | variable expressions are ignored by this filter. That can be used to |
|---|
| 88 | exclude specific parts of a template from being extracted and translated. |
|---|
| 89 | """ |
|---|
| 90 | |
|---|
| 91 | IGNORE_TAGS = frozenset([ |
|---|
| 92 | QName('script'), QName('http://www.w3.org/1999/xhtml}script'), |
|---|
| 93 | QName('style'), QName('http://www.w3.org/1999/xhtml}style') |
|---|
| 94 | ]) |
|---|
| 95 | INCLUDE_ATTRS = frozenset(['abbr', 'alt', 'label', 'prompt', 'standby', |
|---|
| 96 | 'summary', 'title']) |
|---|
| 97 | |
|---|
| 98 | def __init__(self, translate=gettext, ignore_tags=IGNORE_TAGS, |
|---|
| 99 | include_attrs=INCLUDE_ATTRS, extract_text=True): |
|---|
| 100 | """Initialize the translator. |
|---|
| 101 | |
|---|
| 102 | :param translate: the translation function, for example ``gettext`` or |
|---|
| 103 | ``ugettext``. |
|---|
| 104 | :param ignore_tags: a set of tag names that should not be localized |
|---|
| 105 | :param include_attrs: a set of attribute names should be localized |
|---|
| 106 | :param extract_text: whether the content of text nodes should be |
|---|
| 107 | extracted, or only text in explicit ``gettext`` |
|---|
| 108 | function calls |
|---|
| 109 | """ |
|---|
| 110 | self.translate = translate |
|---|
| 111 | self.ignore_tags = ignore_tags |
|---|
| 112 | self.include_attrs = include_attrs |
|---|
| 113 | self.extract_text = extract_text |
|---|
| 114 | |
|---|
| 115 | def __call__(self, stream, ctxt=None, search_text=True, msgbuf=None): |
|---|
| 116 | """Translate any localizable strings in the given stream. |
|---|
| 117 | |
|---|
| 118 | This function shouldn't be called directly. Instead, an instance of |
|---|
| 119 | the `Translator` class should be registered as a filter with the |
|---|
| 120 | `Template` or the `TemplateLoader`, or applied as a regular stream |
|---|
| 121 | filter. If used as a template filter, it should be inserted in front of |
|---|
| 122 | all the default filters. |
|---|
| 123 | |
|---|
| 124 | :param stream: the markup event stream |
|---|
| 125 | :param ctxt: the template context (not used) |
|---|
| 126 | :param search_text: whether text nodes should be translated (used |
|---|
| 127 | internally) |
|---|
| 128 | :param msgbuf: a `MessageBuffer` object or `None` (used internally) |
|---|
| 129 | :return: the localized stream |
|---|
| 130 | """ |
|---|
| 131 | ignore_tags = self.ignore_tags |
|---|
| 132 | include_attrs = self.include_attrs |
|---|
| 133 | translate = self.translate |
|---|
| 134 | if not self.extract_text: |
|---|
| 135 | search_text = False |
|---|
| 136 | skip = 0 |
|---|
| 137 | i18n_msg = I18N_NAMESPACE['msg'] |
|---|
| 138 | ns_prefixes = [] |
|---|
| 139 | xml_lang = XML_NAMESPACE['lang'] |
|---|
| 140 | |
|---|
| 141 | for kind, data, pos in stream: |
|---|
| 142 | |
|---|
| 143 | # skip chunks that should not be localized |
|---|
| 144 | if skip: |
|---|
| 145 | if kind is START: |
|---|
| 146 | skip += 1 |
|---|
| 147 | elif kind is END: |
|---|
| 148 | skip -= 1 |
|---|
| 149 | yield kind, data, pos |
|---|
| 150 | continue |
|---|
| 151 | |
|---|
| 152 | # handle different events that can be localized |
|---|
| 153 | if kind is START: |
|---|
| 154 | tag, attrs = data |
|---|
| 155 | if tag in self.ignore_tags or \ |
|---|
| 156 | isinstance(attrs.get(xml_lang), basestring): |
|---|
| 157 | skip += 1 |
|---|
| 158 | yield kind, data, pos |
|---|
| 159 | continue |
|---|
| 160 | |
|---|
| 161 | new_attrs = [] |
|---|
| 162 | changed = False |
|---|
| 163 | for name, value in attrs: |
|---|
| 164 | newval = value |
|---|
| 165 | if search_text and isinstance(value, basestring): |
|---|
| 166 | if name in include_attrs: |
|---|
| 167 | newval = self.translate(value) |
|---|
| 168 | else: |
|---|
| 169 | newval = list(self(_ensure(value), ctxt, |
|---|
| 170 | search_text=False) |
|---|
| 171 | ) |
|---|
| 172 | if newval != value: |
|---|
| 173 | value = newval |
|---|
| 174 | changed = True |
|---|
| 175 | new_attrs.append((name, value)) |
|---|
| 176 | if changed: |
|---|
| 177 | attrs = Attrs(new_attrs) |
|---|
| 178 | |
|---|
| 179 | if msgbuf: |
|---|
| 180 | msgbuf.append(kind, data, pos) |
|---|
| 181 | continue |
|---|
| 182 | elif i18n_msg in attrs: |
|---|
| 183 | params = attrs.get(i18n_msg) |
|---|
| 184 | if params and type(params) is list: # event tuple |
|---|
| 185 | params = params[0][1] |
|---|
| 186 | msgbuf = MessageBuffer(params) |
|---|
| 187 | attrs -= i18n_msg |
|---|
| 188 | |
|---|
| 189 | yield kind, (tag, attrs), pos |
|---|
| 190 | |
|---|
| 191 | elif search_text and kind is TEXT: |
|---|
| 192 | if not msgbuf: |
|---|
| 193 | text = data.strip() |
|---|
| 194 | if text: |
|---|
| 195 | data = data.replace(text, unicode(translate(text))) |
|---|
| 196 | yield kind, data, pos |
|---|
| 197 | else: |
|---|
| 198 | msgbuf.append(kind, data, pos) |
|---|
| 199 | |
|---|
| 200 | elif msgbuf and kind is EXPR: |
|---|
| 201 | msgbuf.append(kind, data, pos) |
|---|
| 202 | |
|---|
| 203 | elif not skip and msgbuf and kind is END: |
|---|
| 204 | msgbuf.append(kind, data, pos) |
|---|
| 205 | if not msgbuf.depth: |
|---|
| 206 | for event in msgbuf.translate(translate(msgbuf.format())): |
|---|
| 207 | yield event |
|---|
| 208 | msgbuf = None |
|---|
| 209 | yield kind, data, pos |
|---|
| 210 | |
|---|
| 211 | elif kind is SUB: |
|---|
| 212 | subkind, substream = data |
|---|
| 213 | new_substream = list(self(substream, ctxt, msgbuf=msgbuf)) |
|---|
| 214 | yield kind, (subkind, new_substream), pos |
|---|
| 215 | |
|---|
| 216 | elif kind is START_NS and data[1] == I18N_NAMESPACE: |
|---|
| 217 | ns_prefixes.append(data[0]) |
|---|
| 218 | |
|---|
| 219 | elif kind is END_NS and data in ns_prefixes: |
|---|
| 220 | ns_prefixes.remove(data) |
|---|
| 221 | |
|---|
| 222 | else: |
|---|
| 223 | yield kind, data, pos |
|---|
| 224 | |
|---|
| 225 | GETTEXT_FUNCTIONS = ('_', 'gettext', 'ngettext', 'dgettext', 'dngettext', |
|---|
| 226 | 'ugettext', 'ungettext') |
|---|
| 227 | |
|---|
| 228 | def extract(self, stream, gettext_functions=GETTEXT_FUNCTIONS, |
|---|
| 229 | search_text=True, msgbuf=None): |
|---|
| 230 | """Extract localizable strings from the given template stream. |
|---|
| 231 | |
|---|
| 232 | For every string found, this function yields a ``(lineno, function, |
|---|
| 233 | message)`` tuple, where: |
|---|
| 234 | |
|---|
| 235 | * ``lineno`` is the number of the line on which the string was found, |
|---|
| 236 | * ``function`` is the name of the ``gettext`` function used (if the |
|---|
| 237 | string was extracted from embedded Python code), and |
|---|
| 238 | * ``message`` is the string itself (a ``unicode`` object, or a tuple |
|---|
| 239 | of ``unicode`` objects for functions with multiple string arguments). |
|---|
| 240 | |
|---|
| 241 | >>> from genshi.template import MarkupTemplate |
|---|
| 242 | >>> |
|---|
| 243 | >>> tmpl = MarkupTemplate('''<html xmlns:py="http://genshi.edgewall.org/"> |
|---|
| 244 | ... <head> |
|---|
| 245 | ... <title>Example</title> |
|---|
| 246 | ... </head> |
|---|
| 247 | ... <body> |
|---|
| 248 | ... <h1>Example</h1> |
|---|
| 249 | ... <p>${_("Hello, %(name)s") % dict(name=username)}</p> |
|---|
| 250 | ... <p>${ngettext("You have %d item", "You have %d items", num)}</p> |
|---|
| 251 | ... </body> |
|---|
| 252 | ... </html>''', filename='example.html') |
|---|
| 253 | >>> |
|---|
| 254 | >>> for lineno, funcname, message in Translator().extract(tmpl.stream): |
|---|
| 255 | ... print "%d, %r, %r" % (lineno, funcname, message) |
|---|
| 256 | 3, None, u'Example' |
|---|
| 257 | 6, None, u'Example' |
|---|
| 258 | 7, '_', u'Hello, %(name)s' |
|---|
| 259 | 8, 'ngettext', (u'You have %d item', u'You have %d items', None) |
|---|
| 260 | |
|---|
| 261 | :param stream: the event stream to extract strings from; can be a |
|---|
| 262 | regular stream or a template stream |
|---|
| 263 | :param gettext_functions: a sequence of function names that should be |
|---|
| 264 | treated as gettext-style localization |
|---|
| 265 | functions |
|---|
| 266 | :param search_text: whether the content of text nodes should be |
|---|
| 267 | extracted (used internally) |
|---|
| 268 | |
|---|
| 269 | :note: Changed in 0.4.1: For a function with multiple string arguments |
|---|
| 270 | (such as ``ngettext``), a single item with a tuple of strings is |
|---|
| 271 | yielded, instead an item for each string argument. |
|---|
| 272 | """ |
|---|
| 273 | if not self.extract_text: |
|---|
| 274 | search_text = False |
|---|
| 275 | skip = 0 |
|---|
| 276 | i18n_msg = I18N_NAMESPACE['msg'] |
|---|
| 277 | xml_lang = XML_NAMESPACE['lang'] |
|---|
| 278 | |
|---|
| 279 | for kind, data, pos in stream: |
|---|
| 280 | |
|---|
| 281 | if skip: |
|---|
| 282 | if kind is START: |
|---|
| 283 | skip += 1 |
|---|
| 284 | if kind is END: |
|---|
| 285 | skip -= 1 |
|---|
| 286 | |
|---|
| 287 | if kind is START and not skip: |
|---|
| 288 | tag, attrs = data |
|---|
| 289 | |
|---|
| 290 | if tag in self.ignore_tags or \ |
|---|
| 291 | isinstance(attrs.get(xml_lang), basestring): |
|---|
| 292 | skip += 1 |
|---|
| 293 | continue |
|---|
| 294 | |
|---|
| 295 | for name, value in attrs: |
|---|
| 296 | if search_text and isinstance(value, basestring): |
|---|
| 297 | if name in self.include_attrs: |
|---|
| 298 | text = value.strip() |
|---|
| 299 | if text: |
|---|
| 300 | yield pos[1], None, text |
|---|
| 301 | else: |
|---|
| 302 | for lineno, funcname, text in self.extract( |
|---|
| 303 | _ensure(value), gettext_functions, |
|---|
| 304 | search_text=False): |
|---|
| 305 | yield lineno, funcname, text |
|---|
| 306 | |
|---|
| 307 | if msgbuf: |
|---|
| 308 | msgbuf.append(kind, data, pos) |
|---|
| 309 | elif i18n_msg in attrs: |
|---|
| 310 | params = attrs.get(i18n_msg) |
|---|
| 311 | if params and type(params) is list: # event tuple |
|---|
| 312 | params = params[0][1] |
|---|
| 313 | msgbuf = MessageBuffer(params, pos[1]) |
|---|
| 314 | |
|---|
| 315 | elif not skip and search_text and kind is TEXT: |
|---|
| 316 | if not msgbuf: |
|---|
| 317 | text = data.strip() |
|---|
| 318 | if text and filter(None, [ch.isalpha() for ch in text]): |
|---|
| 319 | yield pos[1], None, text |
|---|
| 320 | else: |
|---|
| 321 | msgbuf.append(kind, data, pos) |
|---|
| 322 | |
|---|
| 323 | elif not skip and msgbuf and kind is END: |
|---|
| 324 | msgbuf.append(kind, data, pos) |
|---|
| 325 | if not msgbuf.depth: |
|---|
| 326 | yield msgbuf.lineno, None, msgbuf.format() |
|---|
| 327 | msgbuf = None |
|---|
| 328 | |
|---|
| 329 | elif kind is EXPR or kind is EXEC: |
|---|
| 330 | if msgbuf: |
|---|
| 331 | msgbuf.append(kind, data, pos) |
|---|
| 332 | for funcname, strings in extract_from_code(data, |
|---|
| 333 | gettext_functions): |
|---|
| 334 | yield pos[1], funcname, strings |
|---|
| 335 | |
|---|
| 336 | elif kind is SUB: |
|---|
| 337 | subkind, substream = data |
|---|
| 338 | messages = self.extract(substream, gettext_functions, |
|---|
| 339 | search_text=search_text and not skip, |
|---|
| 340 | msgbuf=msgbuf) |
|---|
| 341 | for lineno, funcname, text in messages: |
|---|
| 342 | yield lineno, funcname, text |
|---|
| 343 | |
|---|
| 344 | |
|---|
| 345 | class MessageBuffer(object): |
|---|
| 346 | """Helper class for managing internationalized mixed content. |
|---|
| 347 | |
|---|
| 348 | :since: version 0.5 |
|---|
| 349 | """ |
|---|
| 350 | |
|---|
| 351 | def __init__(self, params=u'', lineno=-1): |
|---|
| 352 | """Initialize the message buffer. |
|---|
| 353 | |
|---|
| 354 | :param params: comma-separated list of parameter names |
|---|
| 355 | :type params: `basestring` |
|---|
| 356 | :param lineno: the line number on which the first stream event |
|---|
| 357 | belonging to the message was found |
|---|
| 358 | """ |
|---|
| 359 | self.params = [name.strip() for name in params.split(',')] |
|---|
| 360 | self.lineno = lineno |
|---|
| 361 | self.string = [] |
|---|
| 362 | self.events = {} |
|---|
| 363 | self.values = {} |
|---|
| 364 | self.depth = 1 |
|---|
| 365 | self.order = 1 |
|---|
| 366 | self.stack = [0] |
|---|
| 367 | |
|---|
| 368 | def append(self, kind, data, pos): |
|---|
| 369 | """Append a stream event to the buffer. |
|---|
| 370 | |
|---|
| 371 | :param kind: the stream event kind |
|---|
| 372 | :param data: the event data |
|---|
| 373 | :param pos: the position of the event in the source |
|---|
| 374 | """ |
|---|
| 375 | if kind is TEXT: |
|---|
| 376 | self.string.append(data) |
|---|
| 377 | self.events.setdefault(self.stack[-1], []).append(None) |
|---|
| 378 | elif kind is EXPR: |
|---|
| 379 | param = self.params.pop(0) |
|---|
| 380 | self.string.append('%%(%s)s' % param) |
|---|
| 381 | self.events.setdefault(self.stack[-1], []).append(None) |
|---|
| 382 | self.values[param] = (kind, data, pos) |
|---|
| 383 | else: |
|---|
| 384 | if kind is START: |
|---|
| 385 | self.string.append(u'[%d:' % self.order) |
|---|
| 386 | self.events.setdefault(self.order, []).append((kind, data, pos)) |
|---|
| 387 | self.stack.append(self.order) |
|---|
| 388 | self.depth += 1 |
|---|
| 389 | self.order += 1 |
|---|
| 390 | elif kind is END: |
|---|
| 391 | self.depth -= 1 |
|---|
| 392 | if self.depth: |
|---|
| 393 | self.events[self.stack[-1]].append((kind, data, pos)) |
|---|
| 394 | self.string.append(u']') |
|---|
| 395 | self.stack.pop() |
|---|
| 396 | |
|---|
| 397 | def format(self): |
|---|
| 398 | """Return a message identifier representing the content in the |
|---|
| 399 | buffer. |
|---|
| 400 | """ |
|---|
| 401 | return u''.join(self.string).strip() |
|---|
| 402 | |
|---|
| 403 | def translate(self, string, regex=re.compile(r'%\((\w+)\)s')): |
|---|
| 404 | """Interpolate the given message translation with the events in the |
|---|
| 405 | buffer and return the translated stream. |
|---|
| 406 | |
|---|
| 407 | :param string: the translated message string |
|---|
| 408 | """ |
|---|
| 409 | parts = parse_msg(string) |
|---|
| 410 | for order, string in parts: |
|---|
| 411 | events = self.events[order] |
|---|
| 412 | while events: |
|---|
| 413 | event = events.pop(0) |
|---|
| 414 | if event: |
|---|
| 415 | yield event |
|---|
| 416 | else: |
|---|
| 417 | if not string: |
|---|
| 418 | break |
|---|
| 419 | for idx, part in enumerate(regex.split(string)): |
|---|
| 420 | if idx % 2: |
|---|
| 421 | yield self.values[part] |
|---|
| 422 | elif part: |
|---|
| 423 | yield TEXT, part, (None, -1, -1) |
|---|
| 424 | if not self.events[order] or not self.events[order][0]: |
|---|
| 425 | break |
|---|
| 426 | |
|---|
| 427 | |
|---|
| 428 | def parse_msg(string, regex=re.compile(r'(?:\[(\d+)\:)|\]')): |
|---|
| 429 | """Parse a translated message using Genshi mixed content message |
|---|
| 430 | formatting. |
|---|
| 431 | |
|---|
| 432 | >>> parse_msg("See [1:Help].") |
|---|
| 433 | [(0, 'See '), (1, 'Help'), (0, '.')] |
|---|
| 434 | |
|---|
| 435 | >>> parse_msg("See [1:our [2:Help] page] for details.") |
|---|
| 436 | [(0, 'See '), (1, 'our '), (2, 'Help'), (1, ' page'), (0, ' for details.')] |
|---|
| 437 | |
|---|
| 438 | >>> parse_msg("[2:Details] finden Sie in [1:Hilfe].") |
|---|
| 439 | [(2, 'Details'), (0, ' finden Sie in '), (1, 'Hilfe'), (0, '.')] |
|---|
| 440 | |
|---|
| 441 | >>> parse_msg("[1:] Bilder pro Seite anzeigen.") |
|---|
| 442 | [(1, ''), (0, ' Bilder pro Seite anzeigen.')] |
|---|
| 443 | |
|---|
| 444 | :param string: the translated message string |
|---|
| 445 | :return: a list of ``(order, string)`` tuples |
|---|
| 446 | :rtype: `list` |
|---|
| 447 | """ |
|---|
| 448 | parts = [] |
|---|
| 449 | stack = [0] |
|---|
| 450 | while True: |
|---|
| 451 | mo = regex.search(string) |
|---|
| 452 | if not mo: |
|---|
| 453 | break |
|---|
| 454 | |
|---|
| 455 | if mo.start() or stack[-1]: |
|---|
| 456 | parts.append((stack[-1], string[:mo.start()])) |
|---|
| 457 | string = string[mo.end():] |
|---|
| 458 | |
|---|
| 459 | orderno = mo.group(1) |
|---|
| 460 | if orderno is not None: |
|---|
| 461 | stack.append(int(orderno)) |
|---|
| 462 | else: |
|---|
| 463 | stack.pop() |
|---|
| 464 | if not stack: |
|---|
| 465 | break |
|---|
| 466 | |
|---|
| 467 | if string: |
|---|
| 468 | parts.append((stack[-1], string)) |
|---|
| 469 | |
|---|
| 470 | return parts |
|---|
| 471 | |
|---|
| 472 | |
|---|
| 473 | def extract_from_code(code, gettext_functions): |
|---|
| 474 | """Extract strings from Python bytecode. |
|---|
| 475 | |
|---|
| 476 | >>> from genshi.template.eval import Expression |
|---|
| 477 | |
|---|
| 478 | >>> expr = Expression('_("Hello")') |
|---|
| 479 | >>> list(extract_from_code(expr, Translator.GETTEXT_FUNCTIONS)) |
|---|
| 480 | [('_', u'Hello')] |
|---|
| 481 | |
|---|
| 482 | >>> expr = Expression('ngettext("You have %(num)s item", ' |
|---|
| 483 | ... '"You have %(num)s items", num)') |
|---|
| 484 | >>> list(extract_from_code(expr, Translator.GETTEXT_FUNCTIONS)) |
|---|
| 485 | [('ngettext', (u'You have %(num)s item', u'You have %(num)s items', None))] |
|---|
| 486 | |
|---|
| 487 | :param code: the `Code` object |
|---|
| 488 | :type code: `genshi.template.eval.Code` |
|---|
| 489 | :param gettext_functions: a sequence of function names |
|---|
| 490 | :since: version 0.5 |
|---|
| 491 | """ |
|---|
| 492 | def _walk(node): |
|---|
| 493 | if isinstance(node, ast.CallFunc) and isinstance(node.node, ast.Name) \ |
|---|
| 494 | and node.node.name in gettext_functions: |
|---|
| 495 | strings = [] |
|---|
| 496 | def _add(arg): |
|---|
| 497 | if isinstance(arg, ast.Const) \ |
|---|
| 498 | and isinstance(arg.value, basestring): |
|---|
| 499 | strings.append(unicode(arg.value, 'utf-8')) |
|---|
| 500 | elif arg and not isinstance(arg, ast.Keyword): |
|---|
| 501 | strings.append(None) |
|---|
| 502 | [_add(arg) for arg in node.args] |
|---|
| 503 | _add(node.star_args) |
|---|
| 504 | _add(node.dstar_args) |
|---|
| 505 | if len(strings) == 1: |
|---|
| 506 | strings = strings[0] |
|---|
| 507 | else: |
|---|
| 508 | strings = tuple(strings) |
|---|
| 509 | yield node.node.name, strings |
|---|
| 510 | else: |
|---|
| 511 | for child in node.getChildNodes(): |
|---|
| 512 | for funcname, strings in _walk(child): |
|---|
| 513 | yield funcname, strings |
|---|
| 514 | return _walk(code.ast) |
|---|
| 515 | |
|---|
| 516 | |
|---|
| 517 | def extract(fileobj, keywords, comment_tags, options): |
|---|
| 518 | """Babel extraction method for Genshi templates. |
|---|
| 519 | |
|---|
| 520 | :param fileobj: the file-like object the messages should be extracted from |
|---|
| 521 | :param keywords: a list of keywords (i.e. function names) that should be |
|---|
| 522 | recognized as translation functions |
|---|
| 523 | :param comment_tags: a list of translator tags to search for and include |
|---|
| 524 | in the results |
|---|
| 525 | :param options: a dictionary of additional options (optional) |
|---|
| 526 | :return: an iterator over ``(lineno, funcname, message, comments)`` tuples |
|---|
| 527 | :rtype: ``iterator`` |
|---|
| 528 | """ |
|---|
| 529 | template_class = options.get('template_class', MarkupTemplate) |
|---|
| 530 | if isinstance(template_class, basestring): |
|---|
| 531 | module, clsname = template_class.split(':', 1) |
|---|
| 532 | template_class = getattr(__import__(module, {}, {}, [clsname]), clsname) |
|---|
| 533 | encoding = options.get('encoding', None) |
|---|
| 534 | |
|---|
| 535 | extract_text = options.get('extract_text', True) |
|---|
| 536 | if isinstance(extract_text, basestring): |
|---|
| 537 | extract_text = extract_text.lower() in ('1', 'on', 'yes', 'true') |
|---|
| 538 | |
|---|
| 539 | ignore_tags = options.get('ignore_tags', Translator.IGNORE_TAGS) |
|---|
| 540 | if isinstance(ignore_tags, basestring): |
|---|
| 541 | ignore_tags = ignore_tags.split() |
|---|
| 542 | ignore_tags = [QName(tag) for tag in ignore_tags] |
|---|
| 543 | |
|---|
| 544 | include_attrs = options.get('include_attrs', Translator.INCLUDE_ATTRS) |
|---|
| 545 | if isinstance(include_attrs, basestring): |
|---|
| 546 | include_attrs = include_attrs.split() |
|---|
| 547 | include_attrs = [QName(attr) for attr in include_attrs] |
|---|
| 548 | |
|---|
| 549 | tmpl = template_class(fileobj, filename=getattr(fileobj, 'name', None), |
|---|
| 550 | encoding=encoding) |
|---|
| 551 | translator = Translator(None, ignore_tags, include_attrs, extract_text) |
|---|
| 552 | for lineno, func, message in translator.extract(tmpl.stream, |
|---|
| 553 | gettext_functions=keywords): |
|---|
| 554 | yield lineno, func, message, [] |
|---|