Update strings.py

strings.py

@@ -1,3 +1,13 @@
+def pygen_func(nl_code_intent):
+    pass # TODO: generate code PL from intent NL + search in corpus
+    # inputs = {'code_nl': code_nl}    
+    # payload = json.dumps(inputs)
+    # prediction = req.request(CT5_METHOD, CT5_URL, data=payload)
+    # prediction = req.request(CT5_METHOD, CT5_URL, json=req_data)
+    # answer = json.loads(prediction.content.decode("utf-8"))
+    # return str(answer)
+    # CT5_URL = "https://api-inference.huggingface.co/models/nielsr/codet5-small-code-summarization-ruby"
+
 dfs_code = r"""
 def dfs(visited, graph, node):  #function for dfs 
     if node not in visited:
@@ -5,4 +15,137 @@ def dfs(visited, graph, node):  #function for dfs
         visited.add(node)
         for neighbour in graph[node]:
             dfs(visited, graph, neighbour)
-"""
+"""
+
+function_code = r"""
+def write_documents(self, documents: Union[List[dict], List[Document]], index: Optional[str] = None,
+                        batch_size: int = 10_000, duplicate_documents: Optional[str] = None):
+
+        if index and not self.client.indices.exists(index=index):
+            self._create_document_index(index)
+
+        if index is None:
+            index = self.index
+        duplicate_documents = duplicate_documents or self.duplicate_documents
+        assert duplicate_documents in self.duplicate_documents_options, 
+            f"duplicate_documents parameter must be {', '.join(self.duplicate_documents_options)}"
+
+        field_map = self._create_document_field_map()
+        document_objects = [Document.from_dict(d, field_map=field_map) if isinstance(d, dict) else d for d in documents]
+        document_objects = self._handle_duplicate_documents(documents=document_objects,
+                                                            index=index,
+                                                            duplicate_documents=duplicate_documents)
+        documents_to_index = []
+        for doc in document_objects:
+            _doc = {
+                "_op_type": "index" if duplicate_documents == 'overwrite' else "create",
+                "_index": index,
+                **doc.to_dict(field_map=self._create_document_field_map())
+            }  # type: Dict[str, Any]
+
+            # cast embedding type as ES cannot deal with np.array
+            if _doc[self.embedding_field] is not None:
+                if type(_doc[self.embedding_field]) == np.ndarray:
+                    _doc[self.embedding_field] = _doc[self.embedding_field].tolist()
+
+            # rename id for elastic
+            _doc["_id"] = str(_doc.pop("id"))
+
+            # don't index query score and empty fields
+            _ = _doc.pop("score", None)
+            _doc = {k:v for k,v in _doc.items() if v is not None}
+
+            # In order to have a flat structure in elastic + similar behaviour to the other DocumentStores,
+            # we "unnest" all value within "meta"
+            if "meta" in _doc.keys():
+                for k, v in _doc["meta"].items():
+                    _doc[k] = v
+                _doc.pop("meta")
+            documents_to_index.append(_doc)
+
+            # Pass batch_size number of documents to bulk
+            if len(documents_to_index) % batch_size == 0:
+                bulk(self.client, documents_to_index, request_timeout=300, refresh=self.refresh_type)
+                documents_to_index = []
+
+        if documents_to_index:
+            bulk(self.client, documents_to_index, request_timeout=300, refresh=self.refresh_type)
+
+"""
+
+real_docstring = r"""
+        Indexes documents for later queries in Elasticsearch.
+
+        Behaviour if a document with the same ID already exists in ElasticSearch:
+        a) (Default) Throw Elastic's standard error message for duplicate IDs.
+        b) If `self.update_existing_documents=True` for DocumentStore: Overwrite existing documents.
+        (This is only relevant if you pass your own ID when initializing a `Document`.
+        If don't set custom IDs for your Documents or just pass a list of dictionaries here,
+        they will automatically get UUIDs assigned. See the `Document` class for details)
+
+        :param documents: a list of Python dictionaries or a list of Haystack Document objects.
+                          For documents as dictionaries, the format is {"content": "<the-actual-text>"}.
+                          Optionally: Include meta data via {"content": "<the-actual-text>",
+                          "meta":{"name": "<some-document-name>, "author": "somebody", ...}}
+                          It can be used for filtering and is accessible in the responses of the Finder.
+                          Advanced: If you are using your own Elasticsearch mapping, the key names in the dictionary
+                          should be changed to what you have set for self.content_field and self.name_field.
+        :param index: Elasticsearch index where the documents should be indexed. If not supplied, self.index will be used.
+        :param batch_size: Number of documents that are passed to Elasticsearch's bulk function at a time.
+        :param duplicate_documents: Handle duplicates document based on parameter options.
+                                    Parameter options : ( 'skip','overwrite','fail')
+                                    skip: Ignore the duplicates documents
+                                    overwrite: Update any existing documents with the same ID when adding documents.
+                                    fail: an error is raised if the document ID of the document being added already
+                                    exists.
+        :raises DuplicateDocumentError: Exception trigger on duplicate document
+        :return: None
+"""
+
+tree_code = r"""
+class Tree:
+    def __init__(self):
+        self.val = None
+        self.left = None
+        self.right = None    
+"""
+
+insert_code = r"""
+def insert(self, val):
+    if self.val:
+        if val < self.val:
+            if self.left is None:
+                self.left = Tree(val)
+            else:
+                self.left.insert(val)
+        elif val > self.val:
+            if self.right is None:
+                self.right = Tree(val)
+            else:
+                self.right.insert(val)
+    else:
+        self.val = val
+"""
+
+display_code = r"""
+def display_tree(self: Tree, prefix='value: '):
+    current_node = self.val
+    
+    if self.left:
+        self.left.display_tree()
+    
+    print(prefix, current_node)
+    
+    if self.right:
+        self.right.display_tree()
+    
+"""
+
+article_string = r"""CodeXGLLUE task definition (and dataset): **Code summarization (CodeSearchNet)**: 
+    
+_A model is given the task to generate natural language comments for a programming language code input._
+    
+For further details, see the [CodeXGLUE](https://github.com/microsoft/CodeXGLUE) benchmark dataset and open challenge for code intelligence. 
+"""
+
+descr_string = 'The application takes as input the python code for a function, or a class, and generates a documentation string, or code comment, for it using codeT5 fine tuned for code2text generation. Code to text generation, or code summarization, is a CodeXGLUE generation, or sequence to sequence, downstream task. CodeXGLUE stands for General Language Understanding Evaluation benchmark *for code*, which includes diversified code intelligence downstream inference tasks and datasets.'