better_documentation

README.md

@@ -225,6 +225,8 @@ These functions can take parameters as input, while the first unspecified parame
 ```
 
 In addition, it is possible to run multiple functions sequentially by concatenating them with `"-->"` in the API specification document. In this case the output of the function `f_i` will becomes the input result table of the function `f_i+1`.
+
+The postprocess function should output a tuple containing the result and whether the function needs to return the type of values in the result.
 
 ## Run RAMOSE
 
@@ -319,10 +321,10 @@ call_1 = "%s/%s/%s" % (api_base_1, operation_url_1, request)
 call_2 = "%s/%s/%s" % (api_base_2, operation_url_2, request)
 
 op1 = api_manager.get_op(call_1)
-status1, result1 = op1.exec()
+status1, result1, result_format1  = op1.exec()
 
 op2 = api_manager.get_op(call_2)
-status2, result2 = op2.exec()
+status2, result2, result_format2 = op2.exec()
 ```
 
 ## Other functionalities and examples

docs/source/config.rst

@@ -257,9 +257,39 @@ Example:
 
 .. code-block:: none
 
-    #postprocess postprocess_oci(oci) --> another_process(oci)
+    #postprocess split_dois(dois)
     or
-    #postprocess postprocess_metadata(doi)
+    #postprocess distinct()
+
+The preprocess functions should return a tuple explain a tuple of values defining how the particular value passed in the dictionary must be changed.
+The postprocess functions should return a tuple having as second element a boolean for whether the function should return the type of value specified.
+Example of a preprocess and postprocess functions:
+
+.. code-block:: python
+    
+    #Preprocess
+    def split_dois(s):
+        return "\"%s\"" % "\" \"".join(s.split("__")),
+
+    #Postprocess
+    def distinct(res):
+        header = res[0]
+        doi_field = header.index("doi")
+        result = [header]
+
+        dois = set()
+        for row in res[1:]:
+            cur_doi = row[doi_field]
+            if cur_doi not in dois:
+                dois.add(cur_doi)
+                result.append(row)
+
+        return result, True
+
+    
+
+
+
 
 #method
 

pyproject.toml

@@ -18,7 +18,7 @@ itsdangerous="1.1.0"
 Jinja2="2.11.3"
 Markdown="3.1.1"
 MarkupSafe="1.1.1"
-python-dateutil="2.8.1"
+python-dateutil="^2.8.2"
 requests="^2.22.0"
 six="1.13.0"
 urllib3="1.26.5"

requirements.txt

@@ -8,7 +8,7 @@ itsdangerous==1.1.0
 Jinja2==2.11.3
 Markdown==3.1.1
 MarkupSafe==1.1.1
-python-dateutil==2.8.1
+python-dateutil==2.8.2
 requests>=2.22.0, <3.0.0
 six==1.13.0
 urllib3==1.26.5

test/ramose.py

@@ -1235,7 +1235,10 @@ def postprocess(self, res, op_item, addon):
         respectively. In addition, it is possible to run multiple functions sequentially by concatenating them
         with "-->" in the API specification document. In this case the output of the function f_i will becomes
         the input result table of the function f_i+1.
+
+        The postprocess function should output a tuple containing the result and whether the function needs to return the type of values in the result.
         """
+
         result = res
 
         if "postprocess" in op_item:
@@ -1388,7 +1391,7 @@ def remove_types(self, res):
     def exec(self, method="get", content_type="application/json"):
         """
         This method takes in input the the HTTP method to use for the call
-        and the content type to return, and execute the operation as indicated
+        and the content type to return, and executes the operation as indicated
         in the specification file, by running (in the following order):
 
         1. the methods to preprocess the query;
@@ -1471,7 +1474,9 @@ def exec(self, method="get", content_type="application/json"):
 
 
 class APIManager(object):
+
     # Fixing max size for CSV
+
     @staticmethod
     def __max_size_csv():
         from sys import maxsize
@@ -1485,7 +1490,9 @@ def __max_size_csv():
                 maxInt = int(maxInt/10)
 
     # Constructor: START
+
     def __init__(self, conf_files):
+
         """
         This is the constructor of the APIManager class. It takes in input a list of API configuration files, each
         defined according to the Hash Format and following a particular structure, and stores all the operations