"""
Read in the weights file
"""

import string
import sys

WORDS = None
WORD_TO_VECTOR = None
def read():
    global WORDS
    global WORD_TO_VECTOR

    weightsfile = "lm-weights.txt"
    vocabfile = "words.asc"
    size = 30000
    dimensions = 50

    WORDS = [string.strip(w) for w in open(vocabfile).readlines()]
    assert len(WORDS) == 30000

    import numpy, math
    from common.str import percent

    WORD_TO_VECTOR = {}

    sys.stderr.write("Reading %s...\n" % weightsfile)
    f = open(weightsfile)
    f.readline()
    vals = [float(v) for v in string.split(f.readline())]
    assert len(vals) == size * dimensions
    vals.reverse()
    for i in range(size):
        l = vals[dimensions*i:dimensions*(i+1)]
        w = WORDS[i]
        WORD_TO_VECTOR[w] = l

import re
numberre = re.compile("[0-9]")
def convert_string(s):
    """
    Convert a string to a sequence of embeddings.
    """
    e = []
    for origw in string.split(string.lower(s)):
        w = numberre.sub("NUMBER", origw)
        if w in WORD_TO_VECTOR:
            e.append(WORD_TO_VECTOR[w])
        else:
            sys.stderr.write("Word not in vocabulary: %s (original %s)\n" % (w, origw))
    return e

read()