From 0bc4a3e394eb5c9587896e91379a61bb340f28d2 Mon Sep 17 00:00:00 2001
From: Mathias Quillot <mathiasquillot@gmail.com>
Date: Wed, 11 Sep 2019 22:18:47 +0200
Subject: [PATCH] New implementation of data functions for skyrim

---
 bin/data.py | 48 ++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 48 insertions(+)

diff --git a/bin/data.py b/bin/data.py
index fb25050..d077d7c 100644
--- a/bin/data.py
+++ b/bin/data.py
@@ -10,6 +10,7 @@ the README file please.
 
 import sys
 
+
 def read_file(filepath):
     '''
     Read the file and return an array with pairs
@@ -26,6 +27,24 @@ def read_file(filepath):
     return data
 
 
+def read_file_skyrim(filepath):
+    '''
+    Read the file and return an array with pairs
+    where each pair is composed by the metas and the 
+    features.
+
+    This is for Skyrim files.
+    '''
+    data = []
+    with open(filepath, "r") as f:
+        for line in f:
+            splited = line.replace("\n", "").split(" ")
+            metas = splited[0].split(".")
+            features = splited[1:]
+            data.append((metas, features))
+    return data
+
+
 def index_by(data, num_col):
     '''
     Allows the user to index data by number of columns.
@@ -58,6 +77,24 @@ def index_by_id(data):
     return indexed
 
 
+def index_by_id_skyrim(data):
+    '''
+    Allows the user to index data by id.
+    Index data by id consists in indexing two times 
+    because data have two keys. On with the language 
+    and the other one with the id of the sentence.
+    '''
+    indexed = {}
+    for line in data:
+        metas = line[0]
+        id_sen = metas[2]
+        lang = metas[0]
+        if lang not in indexed:
+            indexed[lang] = {}
+        indexed[lang][id_sen] = line
+    return indexed
+
+
 def write_line(metas, features, f=sys.stdout):
     '''
     Just print the line. No need to specify a file.
@@ -67,3 +104,14 @@ def write_line(metas, features, f=sys.stdout):
     f: file to write it
     '''
     print(",".join(metas) + " " + " ".join(features), file=f)
+
+
+def write_line_skyrim(metas, features, f=sys.stdout):
+    '''
+    Just print the line. No need to specify a file.
+
+    metas: meta information on list
+    features: feature vector
+    f: file to write it
+    '''
+    print(".".join(metas) + " " + " ".join(features), file=f)
-- 
1.8.2.3