#65 add max length parameter to ISummaryStrategy

src/nlp/app/nlp_server.py

@@ -47,11 +47,12 @@ async def api_strategies():
 
 @app.get("/summarize/{strategy_id}", summary="Generate a summary of the given"
                                              " text.")
-async def summarize(strategy_id: str, text: str):
+async def summarize(strategy_id: str, max_length: int, text: str):
     """
     This function will summarize a given text with a given summarization
     strategy
 
+    :param max_length: max number of characters in the summarization
     :param strategy_id: The id of the strategy
     :param text: The text to be summarized
     :return: The summary, strategy and quality of the summary in JSON format
@@ -59,7 +60,7 @@ async def summarize(strategy_id: str, text: str):
     for strategy in strategies:
         if strategy.id == strategy_id:
             quality = 0.5
-            summary = strategy.summarize(text)
+            summary = strategy.summarize(text, max_length)
             return {"strategy": strategy_id, "quality": quality,
                     "summary": summary}
 

src/nlp/app/summary/simple_spacy_summarizer.py

@@ -15,7 +15,7 @@ class SimpleSpacySummarizer(ISummaryStrategy):
     def id(self):
         return self._id
 
-    def summarize(self, text: str):
+    def summarize(self, text: str, max_length: int):
         doc = self.nlp(text)
 
         # Divide into tokens, vectorize and remove stop words

src/nlp/app/summary/summarization_with_strategy_TFIDF.py

-from app.summary.summary_strategy_interface import ISummaryStrategy
 import spacy
 import math
 from nltk.stem import WordNetLemmatizer
 import nltk
+from app.summary.summary_strategy_interface import ISummaryStrategy
 
 nltk.download('wordnet')
 
@@ -204,7 +204,7 @@ class SummaryTFIDF(ISummaryStrategy):
 
         return summary[1:]
 
-    def summarize(self, text: str) -> str:
+    def summarize(self, text: str, max_length: int) -> str:
         text = self.nlpGer(text)
 
         # put all sentences in a list

src/nlp/app/summary/summary_sentence_embedding.py

@@ -23,7 +23,7 @@ class SentenceEmbeddingSummarizer(ISummaryStrategy):
     def id(self):
         return self._id
 
-    def summarize(self, text: str) -> str:
+    def summarize(self, text: str, max_length: int) -> str:
         # convert the article/passage to a list of sentences using nltk’s
         # sentence tokenizer.
         sentences = nltk.sent_tokenize(text)

src/nlp/app/summary/summary_strategy_interface.py

@@ -11,11 +11,12 @@ class ISummaryStrategy(ABC):
         raise NotImplementedError
 
     @abstractmethod
-    def summarize(self, text: str) -> str:
+    def summarize(self, text: str, max_length: int) -> str:
         """
         This methods generates the summary to a given text
 
         :param text: text to summarize
+        :param max_length: max number of characters in the summarization
         :returns: summary: a string representing a summarized version of the
          input text
         """

src/nlp/app/summary/summary_word_embedding.py

@@ -18,7 +18,7 @@ class WordEmbeddingSummarizer(ISummaryStrategy):
     def id(self):
         return self._id
 
-    def summarize(self, text: str) -> str:
+    def summarize(self, text: str, max_length: int) -> str:
         extra_words = list(STOP_WORDS) + list(punctuation) + ['\n']
         docx = self.nlp(text)
         # Technik um ein Vokabular anzulegen

src/nlp/app/tests/test_nlp_server.py

@@ -12,7 +12,7 @@ class TestStrategy1(ISummaryStrategy):
 
     id = "test1"
 
-    def summarize(self, text: str) -> str:
+    def summarize(self, text: str, max_length: int) -> str:
         return text
 
 
@@ -24,7 +24,7 @@ class TestStrategy2(ISummaryStrategy):
 
     id = "test2"
 
-    def summarize(self, text: str) -> str:
+    def summarize(self, text: str, max_length: int) -> str:
         return "result text"
 
 
@@ -65,8 +65,10 @@ class TestNlpApi(TestCase):
         client = TestClient(app.nlp_server.app)
 
         # run test
-        response1 = client.get("/summarize/test1?text=test%20text")
-        response2 = client.get("/summarize/test2?text=test%20text")
+        response1 = client.get(
+            "/summarize/test1?max_length=130&text=test%20text")
+        response2 = client.get(
+            "/summarize/test2?max_length=130&text=test%20text")
 
         # assert result
         assert response1.status_code == 200

src/nlp/app/tests/test_simple_spacy_summarizer.py

@@ -53,5 +53,5 @@ class TestBasicSimpleSpacySummarization(TestCase):
 
         # init test data
         summarizer = SimpleSpacySummarizer()
-        summarized_text = summarizer.summarize(self.test_text)
+        summarized_text = summarizer.summarize(self.test_text, max_length=130)
         self.assertLess(len(summarized_text), len(self.test_text))

src/nlp/app/tests/test_summarization_with_strategy_tfidf.py

@@ -165,5 +165,5 @@ class TestSummarizationSpacy(TestCase):
     def test_summarize_text(self):
         summary_tfidf = SummaryTFIDF()
 
-        summary = summary_tfidf.summarize(self.test_text)
+        summary = summary_tfidf.summarize(self.test_text, max_length=130)
         assert type(summary) == str

src/nlp/app/tests/test_summary_sentence_embedding.py

 import math
-from unittest import TestCase
-
 import nltk
+from unittest import TestCase
 
 from app.summary.summary_sentence_embedding import SentenceEmbeddingSummarizer
 
@@ -172,7 +171,8 @@ class TestSummarizationSentenceEmbedding(TestCase):
 
         summary_sentence_embedding = SentenceEmbeddingSummarizer()
 
-        summary = summary_sentence_embedding.summarize(self.test_text)
+        summary = summary_sentence_embedding.summarize(self.test_text,
+                                                       max_length=130)
         assert type(summary) == str
 
     def test_summarize_text_length(self):
@@ -182,14 +182,18 @@ class TestSummarizationSentenceEmbedding(TestCase):
 
         summary_sentence_embedding = SentenceEmbeddingSummarizer()
 
-        summary = summary_sentence_embedding.summarize(self.test_text)
+        summary = summary_sentence_embedding.summarize(self.test_text,
+                                                       max_length=130)
         sentences = nltk.sent_tokenize(self.test_text)
+
         sentences = [sentence.strip() for sentence in sentences]
         total_sentences_text = len(sentences)
 
         min_num_sentences_for_summary = 1
         max_num_sentences_for_summary = 10
-        num_sentences_for_summary = math.floor(total_sentences_text * 0.3)
+        num_sentences_in_percent = 0.3
+        num_sentences_for_summary = math.floor(total_sentences_text *
+                                               num_sentences_in_percent)
 
         if num_sentences_for_summary < min_num_sentences_for_summary:
             num_sentences_for_summary = min_num_sentences_for_summary

src/nlp/app/tests/test_summary_strategy_interface.py

@@ -8,7 +8,7 @@ class TestImplementationValid(ISummaryStrategy):
     """
     id = "id1"
 
-    def summarize(self, text: str) -> str:
+    def summarize(self, text: str, max_length: int) -> str:
         return text
 
 
@@ -18,7 +18,7 @@ class TestImplementationInvalidOne(ISummaryStrategy):
     This class will create a warning but the mistake is intended.
     """
 
-    def summarize(self, text: str) -> str:
+    def summarize(self, text: str, max_length: int) -> str:
         return text
 
 
@@ -35,7 +35,7 @@ class TestISummaryStrategy(TestCase):
 
         # run test functions
         ti = TestImplementationValid()
-        summary = ti.summarize(test_text)
+        summary = ti.summarize(test_text, max_length=130)
 
         # assert result
         self.assertEqual(summary, test_text)

src/nlp/app/tests/test_summary_word_embedding.py

@@ -164,5 +164,6 @@ class TestSummarizationSentenceEmbedding(TestCase):
     def test_summarize_text(self):
         summary_word_embedding = WordEmbeddingSummarizer()
 
-        summary = summary_word_embedding.summarize(self.text)
+        summary = summary_word_embedding.summarize(self.text, max_length=130)
+
         assert type(summary) == str