From ffc2e6fc51403592198ebb82e5bdd0670c302909 Mon Sep 17 00:00:00 2001
From: Tomas Kucharik <tomas.kucharik@telekom.com>
Date: Thu, 4 Nov 2021 21:07:23 +0100
Subject: [PATCH] added initial script with squad loading, printing, saving and
 with example function for google translation, added markdown file with basic
 setup instructions

---
 .env                      |  1 +
 .gitignore                |  1 +
 google_translate_howto.md |  7 +++++
 requirements.txt          |  2 ++
 squad_translate_google.py | 60 +++++++++++++++++++++++++++++++++++++++
 5 files changed, 71 insertions(+)
 create mode 100644 .env
 create mode 100644 .gitignore
 create mode 100644 google_translate_howto.md
 create mode 100644 requirements.txt
 create mode 100644 squad_translate_google.py

diff --git a/.env b/.env
new file mode 100644
index 0000000..3533db2
--- /dev/null
+++ b/.env
@@ -0,0 +1 @@
+GOOGLE_APPLICATION_CREDENTIALS="./google_api_key.json"
diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000..6dcf8d6
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1 @@
+google_api_key.json
diff --git a/google_translate_howto.md b/google_translate_howto.md
new file mode 100644
index 0000000..c23fc1e
--- /dev/null
+++ b/google_translate_howto.md
@@ -0,0 +1,7 @@
+# Prerequisites
+Install google SDK from: [https://cloud.google.com/sdk/docs/install](https://cloud.google.com/sdk/docs/install)
+
+Set up a project in console.google.com
+Create a service account
+Create and download a key in json format
+Export GOOGLE_APPLICATION_CREDENTIALS variable with a path to the key
diff --git a/requirements.txt b/requirements.txt
new file mode 100644
index 0000000..1eeb3e2
--- /dev/null
+++ b/requirements.txt
@@ -0,0 +1,2 @@
+python-dotenv==0.19.1
+google-cloud-translate==2.0.1
diff --git a/squad_translate_google.py b/squad_translate_google.py
new file mode 100644
index 0000000..e46ae57
--- /dev/null
+++ b/squad_translate_google.py
@@ -0,0 +1,60 @@
+import json
+from dotenv import load_dotenv
+import six
+from google.cloud import translate_v2 as translate
+
+def load_squad(filename):
+    with open(filename, "r") as f:
+        squad = json.load(f)
+
+    return squad
+
+def save_squad(filename, squad):
+    with open(filename, "w") as f:
+        json.dump(squad, f)
+
+def print_squad(squad, article_limit=2, paragraph_limit=3, qas_limit=5):
+    for article in squad['data'][:article_limit]:
+        print("="*40)
+        print(f"Article title: {article['title']}\n\n")
+
+        for paragraph in article['paragraphs'][:paragraph_limit]:
+            print(f"{paragraph['context']}\n")
+
+            for qas in paragraph['qas'][:qas_limit]:
+                print(f"Question: {qas['question']}")
+
+                print(f"Answers:")
+                for answer in qas['answers']:
+                    print(f"\t{answer['text']}")
+
+                print("\n")
+
+def translate_text(target, text):
+    """Translates text into the target language.
+
+    Target must be an ISO 639-1 language code.
+    See https://g.co/cloud/translate/v2/translate-reference#supported_languages
+    """
+
+    translate_client = translate.Client()
+
+    if isinstance(text, six.binary_type):
+        text = text.decode("utf-8")
+
+    # Text can also be a sequence of strings, in which case this method
+    # will return a sequence of results for each text.
+    result = translate_client.translate(text, target_language=target)
+
+    print(u"Text: {}".format(result["input"]))
+    print(u"Translation: {}".format(result["translatedText"]))
+    print(u"Detected source language: {}".format(result["detectedSourceLanguage"]))
+
+
+if __name__ == "__main__":
+    load_dotenv()
+
+    orig_squad = load_squad('./squad-v2-dev.json')
+    # print_squad(orig_squad)
+
+