utils.py 15.8 KB
Newer Older
a  
Kai Westerkamp committed
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 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520
# -*- coding: utf-8 -*-
"""
    jinja2.utils
    ~~~~~~~~~~~~

    Utility functions.

    :copyright: (c) 2010 by the Jinja Team.
    :license: BSD, see LICENSE for more details.
"""
import re
import errno
from collections import deque
from jinja2._compat import text_type, string_types, implements_iterator, \
     allocate_lock, url_quote


_word_split_re = re.compile(r'(\s+)')
_punctuation_re = re.compile(
    '^(?P<lead>(?:%s)*)(?P<middle>.*?)(?P<trail>(?:%s)*)$' % (
        '|'.join(map(re.escape, ('(', '<', '&lt;'))),
        '|'.join(map(re.escape, ('.', ',', ')', '>', '\n', '&gt;')))
    )
)
_simple_email_re = re.compile(r'^\S+@[a-zA-Z0-9._-]+\.[a-zA-Z0-9._-]+$')
_striptags_re = re.compile(r'(<!--.*?-->|<[^>]*>)')
_entity_re = re.compile(r'&([^;]+);')
_letters = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ'
_digits = '0123456789'

# special singleton representing missing values for the runtime
missing = type('MissingType', (), {'__repr__': lambda x: 'missing'})()

# internal code
internal_code = set()

concat = u''.join


def contextfunction(f):
    """This decorator can be used to mark a function or method context callable.
    A context callable is passed the active :class:`Context` as first argument when
    called from the template.  This is useful if a function wants to get access
    to the context or functions provided on the context object.  For example
    a function that returns a sorted list of template variables the current
    template exports could look like this::

        @contextfunction
        def get_exported_names(context):
            return sorted(context.exported_vars)
    """
    f.contextfunction = True
    return f


def evalcontextfunction(f):
    """This decorator can be used to mark a function or method as an eval
    context callable.  This is similar to the :func:`contextfunction`
    but instead of passing the context, an evaluation context object is
    passed.  For more information about the eval context, see
    :ref:`eval-context`.

    .. versionadded:: 2.4
    """
    f.evalcontextfunction = True
    return f


def environmentfunction(f):
    """This decorator can be used to mark a function or method as environment
    callable.  This decorator works exactly like the :func:`contextfunction`
    decorator just that the first argument is the active :class:`Environment`
    and not context.
    """
    f.environmentfunction = True
    return f


def internalcode(f):
    """Marks the function as internally used"""
    internal_code.add(f.__code__)
    return f


def is_undefined(obj):
    """Check if the object passed is undefined.  This does nothing more than
    performing an instance check against :class:`Undefined` but looks nicer.
    This can be used for custom filters or tests that want to react to
    undefined variables.  For example a custom default filter can look like
    this::

        def default(var, default=''):
            if is_undefined(var):
                return default
            return var
    """
    from jinja2.runtime import Undefined
    return isinstance(obj, Undefined)


def consume(iterable):
    """Consumes an iterable without doing anything with it."""
    for event in iterable:
        pass


def clear_caches():
    """Jinja2 keeps internal caches for environments and lexers.  These are
    used so that Jinja2 doesn't have to recreate environments and lexers all
    the time.  Normally you don't have to care about that but if you are
    messuring memory consumption you may want to clean the caches.
    """
    from jinja2.environment import _spontaneous_environments
    from jinja2.lexer import _lexer_cache
    _spontaneous_environments.clear()
    _lexer_cache.clear()


def import_string(import_name, silent=False):
    """Imports an object based on a string.  This is useful if you want to
    use import paths as endpoints or something similar.  An import path can
    be specified either in dotted notation (``xml.sax.saxutils.escape``)
    or with a colon as object delimiter (``xml.sax.saxutils:escape``).

    If the `silent` is True the return value will be `None` if the import
    fails.

    :return: imported object
    """
    try:
        if ':' in import_name:
            module, obj = import_name.split(':', 1)
        elif '.' in import_name:
            items = import_name.split('.')
            module = '.'.join(items[:-1])
            obj = items[-1]
        else:
            return __import__(import_name)
        return getattr(__import__(module, None, None, [obj]), obj)
    except (ImportError, AttributeError):
        if not silent:
            raise


def open_if_exists(filename, mode='rb'):
    """Returns a file descriptor for the filename if that file exists,
    otherwise `None`.
    """
    try:
        return open(filename, mode)
    except IOError as e:
        if e.errno not in (errno.ENOENT, errno.EISDIR):
            raise


def object_type_repr(obj):
    """Returns the name of the object's type.  For some recognized
    singletons the name of the object is returned instead. (For
    example for `None` and `Ellipsis`).
    """
    if obj is None:
        return 'None'
    elif obj is Ellipsis:
        return 'Ellipsis'
    # __builtin__ in 2.x, builtins in 3.x
    if obj.__class__.__module__ in ('__builtin__', 'builtins'):
        name = obj.__class__.__name__
    else:
        name = obj.__class__.__module__ + '.' + obj.__class__.__name__
    return '%s object' % name


def pformat(obj, verbose=False):
    """Prettyprint an object.  Either use the `pretty` library or the
    builtin `pprint`.
    """
    try:
        from pretty import pretty
        return pretty(obj, verbose=verbose)
    except ImportError:
        from pprint import pformat
        return pformat(obj)


def urlize(text, trim_url_limit=None, nofollow=False):
    """Converts any URLs in text into clickable links. Works on http://,
    https:// and www. links. Links can have trailing punctuation (periods,
    commas, close-parens) and leading punctuation (opening parens) and
    it'll still do the right thing.

    If trim_url_limit is not None, the URLs in link text will be limited
    to trim_url_limit characters.

    If nofollow is True, the URLs in link text will get a rel="nofollow"
    attribute.
    """
    trim_url = lambda x, limit=trim_url_limit: limit is not None \
                         and (x[:limit] + (len(x) >=limit and '...'
                         or '')) or x
    words = _word_split_re.split(text_type(escape(text)))
    nofollow_attr = nofollow and ' rel="nofollow"' or ''
    for i, word in enumerate(words):
        match = _punctuation_re.match(word)
        if match:
            lead, middle, trail = match.groups()
            if middle.startswith('www.') or (
                '@' not in middle and
                not middle.startswith('http://') and
                not middle.startswith('https://') and
                len(middle) > 0 and
                middle[0] in _letters + _digits and (
                    middle.endswith('.org') or
                    middle.endswith('.net') or
                    middle.endswith('.com')
                )):
                middle = '<a href="http://%s"%s>%s</a>' % (middle,
                    nofollow_attr, trim_url(middle))
            if middle.startswith('http://') or \
               middle.startswith('https://'):
                middle = '<a href="%s"%s>%s</a>' % (middle,
                    nofollow_attr, trim_url(middle))
            if '@' in middle and not middle.startswith('www.') and \
               not ':' in middle and _simple_email_re.match(middle):
                middle = '<a href="mailto:%s">%s</a>' % (middle, middle)
            if lead + middle + trail != word:
                words[i] = lead + middle + trail
    return u''.join(words)


def generate_lorem_ipsum(n=5, html=True, min=20, max=100):
    """Generate some lorem impsum for the template."""
    from jinja2.constants import LOREM_IPSUM_WORDS
    from random import choice, randrange
    words = LOREM_IPSUM_WORDS.split()
    result = []

    for _ in range(n):
        next_capitalized = True
        last_comma = last_fullstop = 0
        word = None
        last = None
        p = []

        # each paragraph contains out of 20 to 100 words.
        for idx, _ in enumerate(range(randrange(min, max))):
            while True:
                word = choice(words)
                if word != last:
                    last = word
                    break
            if next_capitalized:
                word = word.capitalize()
                next_capitalized = False
            # add commas
            if idx - randrange(3, 8) > last_comma:
                last_comma = idx
                last_fullstop += 2
                word += ','
            # add end of sentences
            if idx - randrange(10, 20) > last_fullstop:
                last_comma = last_fullstop = idx
                word += '.'
                next_capitalized = True
            p.append(word)

        # ensure that the paragraph ends with a dot.
        p = u' '.join(p)
        if p.endswith(','):
            p = p[:-1] + '.'
        elif not p.endswith('.'):
            p += '.'
        result.append(p)

    if not html:
        return u'\n\n'.join(result)
    return Markup(u'\n'.join(u'<p>%s</p>' % escape(x) for x in result))


def unicode_urlencode(obj, charset='utf-8'):
    """URL escapes a single bytestring or unicode string with the
    given charset if applicable to URL safe quoting under all rules
    that need to be considered under all supported Python versions.

    If non strings are provided they are converted to their unicode
    representation first.
    """
    if not isinstance(obj, string_types):
        obj = text_type(obj)
    if isinstance(obj, text_type):
        obj = obj.encode(charset)
    return text_type(url_quote(obj))


class LRUCache(object):
    """A simple LRU Cache implementation."""

    # this is fast for small capacities (something below 1000) but doesn't
    # scale.  But as long as it's only used as storage for templates this
    # won't do any harm.

    def __init__(self, capacity):
        self.capacity = capacity
        self._mapping = {}
        self._queue = deque()
        self._postinit()

    def _postinit(self):
        # alias all queue methods for faster lookup
        self._popleft = self._queue.popleft
        self._pop = self._queue.pop
        self._remove = self._queue.remove
        self._wlock = allocate_lock()
        self._append = self._queue.append

    def __getstate__(self):
        return {
            'capacity':     self.capacity,
            '_mapping':     self._mapping,
            '_queue':       self._queue
        }

    def __setstate__(self, d):
        self.__dict__.update(d)
        self._postinit()

    def __getnewargs__(self):
        return (self.capacity,)

    def copy(self):
        """Return a shallow copy of the instance."""
        rv = self.__class__(self.capacity)
        rv._mapping.update(self._mapping)
        rv._queue = deque(self._queue)
        return rv

    def get(self, key, default=None):
        """Return an item from the cache dict or `default`"""
        try:
            return self[key]
        except KeyError:
            return default

    def setdefault(self, key, default=None):
        """Set `default` if the key is not in the cache otherwise
        leave unchanged. Return the value of this key.
        """
        self._wlock.acquire()
        try:
            try:
                return self[key]
            except KeyError:
                self[key] = default
                return default
        finally:
            self._wlock.release()

    def clear(self):
        """Clear the cache."""
        self._wlock.acquire()
        try:
            self._mapping.clear()
            self._queue.clear()
        finally:
            self._wlock.release()

    def __contains__(self, key):
        """Check if a key exists in this cache."""
        return key in self._mapping

    def __len__(self):
        """Return the current size of the cache."""
        return len(self._mapping)

    def __repr__(self):
        return '<%s %r>' % (
            self.__class__.__name__,
            self._mapping
        )

    def __getitem__(self, key):
        """Get an item from the cache. Moves the item up so that it has the
        highest priority then.

        Raise a `KeyError` if it does not exist.
        """
        self._wlock.acquire()
        try:
            rv = self._mapping[key]
            if self._queue[-1] != key:
                try:
                    self._remove(key)
                except ValueError:
                    # if something removed the key from the container
                    # when we read, ignore the ValueError that we would
                    # get otherwise.
                    pass
                self._append(key)
            return rv
        finally:
            self._wlock.release()

    def __setitem__(self, key, value):
        """Sets the value for an item. Moves the item up so that it
        has the highest priority then.
        """
        self._wlock.acquire()
        try:
            if key in self._mapping:
                self._remove(key)
            elif len(self._mapping) == self.capacity:
                del self._mapping[self._popleft()]
            self._append(key)
            self._mapping[key] = value
        finally:
            self._wlock.release()

    def __delitem__(self, key):
        """Remove an item from the cache dict.
        Raise a `KeyError` if it does not exist.
        """
        self._wlock.acquire()
        try:
            del self._mapping[key]
            try:
                self._remove(key)
            except ValueError:
                # __getitem__ is not locked, it might happen
                pass
        finally:
            self._wlock.release()

    def items(self):
        """Return a list of items."""
        result = [(key, self._mapping[key]) for key in list(self._queue)]
        result.reverse()
        return result

    def iteritems(self):
        """Iterate over all items."""
        return iter(self.items())

    def values(self):
        """Return a list of all values."""
        return [x[1] for x in self.items()]

    def itervalue(self):
        """Iterate over all values."""
        return iter(self.values())

    def keys(self):
        """Return a list of all keys ordered by most recent usage."""
        return list(self)

    def iterkeys(self):
        """Iterate over all keys in the cache dict, ordered by
        the most recent usage.
        """
        return reversed(tuple(self._queue))

    __iter__ = iterkeys

    def __reversed__(self):
        """Iterate over the values in the cache dict, oldest items
        coming first.
        """
        return iter(tuple(self._queue))

    __copy__ = copy


# register the LRU cache as mutable mapping if possible
try:
    from collections import MutableMapping
    MutableMapping.register(LRUCache)
except ImportError:
    pass


@implements_iterator
class Cycler(object):
    """A cycle helper for templates."""

    def __init__(self, *items):
        if not items:
            raise RuntimeError('at least one item has to be provided')
        self.items = items
        self.reset()

    def reset(self):
        """Resets the cycle."""
        self.pos = 0

    @property
    def current(self):
        """Returns the current item."""
        return self.items[self.pos]

    def __next__(self):
        """Goes one item ahead and returns it."""
        rv = self.current
        self.pos = (self.pos + 1) % len(self.items)
        return rv


class Joiner(object):
    """A joining helper for templates."""

    def __init__(self, sep=u', '):
        self.sep = sep
        self.used = False

    def __call__(self):
        if not self.used:
            self.used = True
            return u''
        return self.sep


# Imported here because that's where it was in the past
from .markupsafe import Markup, escape, soft_unicode