Created
July 23, 2014 12:38
-
-
Save veer66/9e6908175e6fb52fdd09 to your computer and use it in GitHub Desktop.
Partial Apertium's stream parser (for parsing biltrans result)
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
module Apertium | |
OUTSIDE_WORD = 0 | |
INSIDE_WORD = 1 | |
class B | |
attr_reader :text | |
def initialize(text) | |
@text = text | |
end | |
def parse | |
self | |
end | |
end | |
class Analyse | |
attr_reader :lemma, :tags | |
def initialize(lemma, tags) | |
@lemma = lemma | |
@tags = tags | |
end | |
end | |
class AmbiLu | |
attr_reader :analyses | |
def initialize(analyses) | |
@analyses = analyses | |
end | |
end | |
class W0 | |
attr_reader :text | |
def initialize(text) | |
@text = text | |
end | |
def parse_analisis(t) | |
t = t.split(/(<[^>]+>)/).select{|w| w != ""} | |
lemma = t[0] | |
tags = t[1..-1].map{|tag| tag[1..-2]} | |
return Analyse.new(lemma, tags) | |
end | |
def parse | |
s = 0 | |
analyses = [] | |
text = @text[1..-2] | |
for i in 0..(text.length-1) | |
if text[i] == '/' and (i == 0 or text[i] != '\\') | |
analyses << parse_analisis(text[s..(i-1)]) | |
s = i+1 | |
end | |
end | |
if s < text.length | |
analyses << parse_analisis(text[s..(text.length-1)]) | |
end | |
return AmbiLu.new(analyses) | |
end | |
end | |
class StreamParser | |
def initialize | |
end | |
def parse(stream) | |
pass0 = parse0(stream) | |
return pass0.map{|t| t.parse} | |
end | |
def parse0(stream) | |
state = OUTSIDE_WORD | |
s = 0 | |
pass0 = [] | |
for i in 0 .. (stream.length - 1) | |
case state | |
when OUTSIDE_WORD | |
if stream[i] == '^' and (i == 0 or stream[i] != '\\') | |
if i > 0 | |
if i-1 >= s | |
pass0 << B.new(stream[s..(i-1)]) | |
end | |
end | |
s = i | |
state = INSIDE_WORD | |
end | |
when INSIDE_WORD | |
if stream[i] == '$' and (i == 0 or stream[i] != '\\') | |
state = OUTSIDE_WORD | |
pass0 << W0.new(stream[s..(i-1)]) | |
s = i + 1 | |
end | |
end | |
end #for | |
return pass0 | |
end | |
end | |
end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment