searxng/searx/utils.py

# import htmlentitydefs
from codecs import getincrementalencoder
from HTMLParser import HTMLParser
from random import choice

from searx.version import VERSION_STRING
from searx import settings

import cStringIO
import csv
import os
import re

ua_versions = ('29.0',
               '30.0',
               '31.0',
               '32.0',
               '33.0')

ua_os = ('Windows NT 6.3; WOW64',
         'X11; Linux x86_64',
         'X11; Linux x86')

ua = "Mozilla/5.0 ({os}) Gecko/20100101 Firefox/{version}"

blocked_tags = ('script',
                'style')


def gen_useragent():
    # TODO
    return ua.format(os=choice(ua_os), version=choice(ua_versions))


def searx_useragent():
    return 'searx/{searx_version} {suffix}'.format(
           searx_version=VERSION_STRING,
           suffix=settings['server'].get('useragent_suffix', ''))


def highlight_content(content, query):

    if not content:
        return None
    # ignoring html contents
    # TODO better html content detection
    if content.find('<') != -1:
        return content

    query = query.decode('utf-8')
    if content.lower().find(query.lower()) > -1:
        query_regex = u'({0})'.format(re.escape(query))
        content = re.sub(query_regex, '<span class="highlight">\\1</span>',
                         content, flags=re.I | re.U)
    else:
        regex_parts = []
        for chunk in query.split():
            if len(chunk) == 1:
                regex_parts.append(u'\W+{0}\W+'.format(re.escape(chunk)))
            else:
                regex_parts.append(u'{0}'.format(re.escape(chunk)))
        query_regex = u'({0})'.format('|'.join(regex_parts))
        content = re.sub(query_regex, '<span class="highlight">\\1</span>',
                         content, flags=re.I | re.U)

    return content


class HTMLTextExtractor(HTMLParser):
    def __init__(self):
        HTMLParser.__init__(self)
        self.result = []
        self.tags = []

    def handle_starttag(self, tag, attrs):
        print tag
        self.tags.append(tag)

    def handle_endtag(self, tag):
        print tag,tag
        if tag != self.tags[-1]:
            raise Exception("invalid html")
        self.tags.pop()

    def is_valid_tag(self):
        return not self.tags or self.tags[-1] not in blocked_tags

    def handle_data(self, d):
        if not self.is_valid_tag():
            return
        self.result.append(d)

    def handle_charref(self, number):
        if not self.is_valid_tag():
            return
        if number[0] in (u'x', u'X'):
            codepoint = int(number[1:], 16)
        else:
            codepoint = int(number)
        self.result.append(unichr(codepoint))

    def handle_entityref(self, name):
        if not self.is_valid_tag():
            return
        # codepoint = htmlentitydefs.name2codepoint[name]
        # self.result.append(unichr(codepoint))
        self.result.append(name)

    def get_text(self):
        return u''.join(self.result)


def html_to_text(html):
    s = HTMLTextExtractor()
    s.feed(html)
    return s.get_text()


class UnicodeWriter:
    """
    A CSV writer which will write rows to CSV file "f",
    which is encoded in the given encoding.
    """

    def __init__(self, f, dialect=csv.excel, encoding="utf-8", **kwds):
        # Redirect output to a queue
        self.queue = cStringIO.StringIO()
        self.writer = csv.writer(self.queue, dialect=dialect, **kwds)
        self.stream = f
        self.encoder = getincrementalencoder(encoding)()

    def writerow(self, row):
        unicode_row = []
        for col in row:
            if type(col) == str or type(col) == unicode:
                unicode_row.append(col.encode('utf-8').strip())
            else:
                unicode_row.append(col)
        self.writer.writerow(unicode_row)
        # Fetch UTF-8 output from the queue ...
        data = self.queue.getvalue()
        data = data.decode("utf-8")
        # ... and reencode it into the target encoding
        data = self.encoder.encode(data)
        # write to the target stream
        self.stream.write(data)
        # empty queue
        self.queue.truncate(0)

    def writerows(self, rows):
        for row in rows:
            self.writerow(row)


def get_themes(root):
    """Returns available themes list."""

    static_path = os.path.join(root, 'static')
    static_names = set(os.listdir(static_path))
    templates_path = os.path.join(root, 'templates')
    templates_names = set(os.listdir(templates_path))

    themes = []
    for name in static_names.intersection(templates_names):
        themes += [name]
    return static_path, templates_path, themes