Elasticsearch: custom highlighter implementation for proximity search implementation using slop query

highlighter.py

doc = 'The quick brown fox jumps over the lazy dog. The quick brown fox over the lazy dog. The quick brown fox jumps over the lazy dog.'

cur_pos = -1
end_pos = 0
distance = 2
tracked_words = []
start_pos = 0

search_words = ['quick', 'fox', 'over']
highlights = []


splitted_words = doc.split(' ')

matched_pair_pos = []

for word in splitted_words:
    cur_pos += 1
    if word in search_words and word not in tracked_words:
        if not tracked_words:
            start_pos = cur_pos
        tracked_words.append(word)
    if len(tracked_words) == len(search_words):
        end_pos = cur_pos + 1
        tracked_words = []
        cur_highlight = " ".join(splitted_words[start_pos:end_pos])
        pre_highlight = " ".join(splitted_words[:start_pos])
        post_highlight = " ".join(splitted_words[end_pos:])


        highlights.append("%s <b>%s</b> %s" %
                          (pre_highlight, cur_highlight, post_highlight))

print highlights

default_highlights = {
"info.FullContent" : [
"The generated Lorem Ipsum is therefore always free from repetition, injected humour, or non-characteristic words etc."
]
}

search_words = ['repetition', 'humour']
pre_tags = """"""
post_tags = ""
distance = 2

proximity_highlights = {}

for field, highlights in default_highlights.iteritems():
proximity_highlights[field] = []
for highlight in highlights:
splitted_words = highlight.split(' ')

    cur_pos = -1
    end_pos = 0
    start_pos = 0
    tracked_words = []

    for word in splitted_words:
        cur_pos += 1
        if word in search_words and word not in tracked_words:
            if not tracked_words:
                start_pos = cur_pos
            tracked_words.append(word)
        if len(tracked_words) == len(search_words):
            end_pos = cur_pos + 1
            tracked_words = []
            pre_highlight = " ".join(splitted_words[:start_pos])
            cur_highlight = " ".join(splitted_words[start_pos:end_pos])
            post_highlight = " ".join(splitted_words[end_pos:])
            complete_highlight = """%s %s%s%s %s""" % (
                pre_highlight, pre_tags, cur_highlight, post_tags, post_highlight
            )
            proximity_highlights[field].append(complete_highlight)

print proximity_highlights