view piecrust/uriutil.py @ 173:0a86a7a6b284

routes: Actually match metadata when finding routes, fix problems with paths. When we look for a route that matches a given page, we now look at the source metadata that comes with that page, and compare it to the metadata we need to build URIs. Also, when matching URIs, we handle the case where a 'path'-component in our pattern may be completely empty, and thus we may be missing some trailing slashes in the URI.
author Ludovic Chabant <ludovic@chabant.com>
date Sat, 03 Jan 2015 21:10:44 -0800
parents 62c7a97c8340
children b7ab1b503510
line wrap: on
line source

import re
import os.path
import string
import logging
import functools


logger = logging.getLogger(__name__)


class UriError(Exception):
    def __init__(self, uri):
        super(UriError, self).__init__("Invalid URI: %s" % uri)


@functools.total_ordering
class UriInfo(object):
    def __init__(self, uri, source, args, taxonomy=None, page_num=1):
        self.uri = uri
        self.source = source
        self.args = args
        self.taxonomy = taxonomy
        self.page_num = page_num

    def __eq__(self, other):
        return ((self.uri, self.source, self.args, self.taxonomy,
                self.page_num) ==
            (other.uri, other.source, other.args, other.taxonomy,
                other.page_num))

    def __lt__(self, other):
        return ((self.uri, self.source, self.args, self.taxonomy,
                self.page_num) <
            (other.uri, other.source, other.args, other.taxonomy,
                other.page_num))


pagenum_pattern = re.compile(r'/(\d+)/?$')


def parse_uri(routes, uri):
    if uri.find('..') >= 0:
        raise UriError(uri)

    page_num = 1
    match = pagenum_pattern.search(uri)
    if match is not None:
        uri = uri[:match.start()]
        page_num = int(match.group(1))

    uri = '/' + uri.strip('/')

    for rn, rc in routes.items():
        pattern = route_to_pattern(rn)
        m = re.match(pattern, uri)
        if m is not None:
            args = m.groupdict()
            return UriInfo(uri, rc['source'], args, rc.get('taxonomy'),
                    page_num)

    return None


r2p_pattern = re.compile(r'%(\w+)%')


def route_to_pattern(route):
    return r2p_pattern.sub(r'(?P<\1>[\w\-]+)', route)


def multi_replace(text, replacements):
    reps = dict((re.escape(k), v) for k, v in replacements.items())
    pattern = re.compile("|".join(list(reps.keys())))
    return pattern.sub(lambda m: reps[re.escape(m.group(0))], text)


def get_slug(app, uri):
    site_root = app.config.get('site/root')
    uri = uri[len(site_root):]
    return uri.lstrip('/')


def get_first_sub_uri(app, uri):
    pretty_urls = app.config.get('site/pretty_urls')
    if not pretty_urls:
        uri, ext = os.path.splitext(uri)

    pgn_suffix_re = app.config.get('__cache/pagination_suffix_re')
    m = re.search(pgn_suffix_re, uri)
    if m:
        uri = uri[:m.start()]

    if not pretty_urls:
        uri += ext

    return uri