Merge pull request #26 from SynBioDex/3-Package-the-functions-into-a-…

…Library

initial setup to support issue #15

excel2sbol/converter/part_library_converter.py

@@ -1,5 +1,5 @@
 
 class PartLibraryConverter(object):
-
+    DARPA_TEMPLATE = ''
     def __init__(self):
         pass

excel2sbol/converter/template.py

@@ -0,0 +1,5 @@
+
+class Template(object):
+
+    def __init__(self):
+        pass

excel2sbol/converter/template_factory.py

@@ -0,0 +1,7 @@
+class TemplateFactory(object):
+
+    def __init__(self):
+        pass
+
+    def create_darpa_template(self):
+        pass

excel2sbol/main.py

@@ -1,4 +1,67 @@
 import argparse
+import excel2sbol.utils.converter_utils as converter_utils
+import pandas as pd
+
+def convert_part_library(template_file: str, input_excel: str):
+    # Read in template and filled spreadsheet for the Parts library
+    start_row = 13
+    nrows = 8
+    description_row = 9
+    filled_library, filled_library_metadata, filled_description = converter_utils.read_library(input_excel,
+                                                                               start_row=start_row, nrows=nrows,
+                                                                               description_row=description_row)
+    blank_library, blank_library_metadata, blank_description = converter_utils.read_library(template_file,
+                                                                            start_row=start_row, nrows=nrows,
+                                                                            description_row=description_row)
+
+    ontology = pd.read_excel(input_excel, header=None, sheet_name="Ontology Terms", skiprows=3, index_col=0)
+    ontology = ontology.to_dict("dict")[1]
+
+    converter_utils.quality_check(filled_library,
+                                  blank_library,
+                                  filled_library_metadata,
+                                  blank_library_metadata,
+                                  filled_description,
+                                  blank_description, nrows, description_row)
+
+    # Create SBOL document
+    doc = converter_utils.write_sbol(filled_library, filled_library_metadata, filled_description, ontology)
+    return doc
+
+def convert_composition_reading(template_file: str, input_excel: str):
+    # Load Data
+    startrow_composition = 9
+    sheet_name = "Composite Parts"
+    nrows = 8
+    use_cols = [0, 1]
+    # read in whole composite sheet below metadata
+    table = pd.read_excel(input_excel, sheet_name=sheet_name,
+                          header=None, skiprows=startrow_composition)
+
+    # Load Metadata
+    filled_composition_metadata = pd.read_excel(input_excel, sheet_name=sheet_name,
+                                                header=None, nrows=nrows, usecols=use_cols)
+    blank_composition_metadata = pd.read_excel(template_file, sheet_name=sheet_name,
+                                               header=None, nrows=nrows, usecols=use_cols)
+
+    # Compare the metadata to the template
+    converter_utils.quality_check_metadata(filled_composition_metadata, blank_composition_metadata)
+
+    # Load Libraries required for Parts
+    libraries = converter_utils.load_libraries(table)
+
+    # Loop over all rows and find those where each block begins
+    compositions, list_of_rows = converter_utils.get_data(table)
+
+    # Extract parts from table
+    compositions, all_parts = converter_utils.get_parts(list_of_rows, table, compositions)
+
+    # Check if Collection names are alphanumeric and separated by underscore
+    compositions = converter_utils.check_name(compositions)
+
+    # Create sbol
+    doc = converter_utils.write_sbol_comp(libraries, compositions, all_parts)
+    return doc
 
 def main():
     parser = argparse.ArgumentParser(description='Creates libraries of basic parts by converting a spreadsheet to SBOL.')

Composition_reading.py → excel2sbol/resources/Composition_reading.py

@@ -8,8 +8,8 @@
 #Set up
 import os
 import pandas as pd
-from excel2sbol.functions import quality_check_metadata, load_libraries, get_data
-from excel2sbol.functions import get_parts, check_name, write_sbol_comp, fix_msec_sbol
+from excel2sbol.utils.converter_utils import quality_check_metadata, load_libraries, get_data
+from excel2sbol.utils.converter_utils import get_parts, check_name, write_sbol_comp, fix_msec_sbol
 
 cwd = os.path.dirname(os.path.abspath("__file__")) #get current working directory
 path_filled = os.path.join(cwd, "templates", "darpa_template.xlsx")

Excel.py → excel2sbol/resources/Excel.py

@@ -9,13 +9,13 @@
 #Setup
 import pandas as pd
 import os
-from excel2sbol.functions import read_library, quality_check, write_sbol
+from excel2sbol.utils.converter_utils import read_library, quality_check, write_sbol
 
 
 cwd = os.path.dirname(os.path.abspath("__file__")) #get current working directory
 path_blank = os.path.join(cwd, "templates/darpa_template_blank.xlsx")
-# path_filled = os.path.join("C:\\Users\\JVM\\Downloads\\build-request-template_BsPpVn.xlsx")
-# file_path_out = "C:\\Users\\JVM\\Downloads\\converted.xml"
+path_filled = None #os.path.join("C:\\Users\\JVM\\Downloads\\build-request-template_BsPpVn.xlsx")
+file_path_out = None #"C:\\Users\\JVM\\Downloads\\converted.xml"
 
 #Read in template and filled spreadsheet for the Parts library
 start_row = 13

excel2sbol/tests/test_golden_files.py

@@ -1,14 +1,37 @@
+import excel2sbol.main as tool
 import os
 import unittest
 
 class GoldenFileTest(unittest.TestCase):
 
-    def setup(self):
+    @classmethod
+    def setUpClass(cls):
+        pass
+
+    def setUp(self):
         curr_path = os.path.dirname(os.path.realpath(__file__))
         self.data_dir = os.path.join(curr_path, 'data')
 
     def tearDown(self):
         pass
 
-    def test_library_file(self):
-        pass
+    @classmethod
+    def tearDownClass(cls):
+        pass
+
+    def test_convert_part_library(self):
+        file = 'darpa_template.xlsx'
+        input_file_path = os.path.join(self.data_dir, file)
+        template_file = os.path.join(self.data_dir, 'darpa_template_blank.xlsx')
+        output_doc = tool.convert_part_library(template_file=template_file, input_excel=input_file_path)
+        self.assertTrue(output_doc)
+
+        dna_parts = output_doc.componentDefinitions
+        self.assertEqual(5, len(dna_parts))
+
+    def test_convert_composition_reading(self):
+        file = 'darpa_template.xlsx'
+        input_file_path = os.path.join(self.data_dir, file)
+        template_file = os.path.join(self.data_dir, 'darpa_template_blank.xlsx')
+        output_doc = tool.convert_composition_reading(template_file=template_file, input_excel=input_file_path)
+        self.assertTrue(output_doc)

excel2sbol/utils/converter_utils.py

@@ -432,19 +432,19 @@ def read_library(path, start_row, nrows, description_row, use_cols = [0, 1],
                  start_row = 13, nrows = 8, description_row = 9)
 
     """
-    basic_DNA_parts = pd.read_excel (path, sheet_name = sheet_name, 
-                                     header= 0, skiprows = start_row)
+    basic_DNA_parts = pd.read_excel(path, sheet_name=sheet_name,
+                                     header=0, skiprows=start_row)
 
-    metadata = pd.read_excel (path, sheet_name = sheet_name,
-                              header= None, nrows = nrows, usecols = use_cols)
+    metadata = pd.read_excel (path, sheet_name=sheet_name,
+                              header=None, nrows=nrows, usecols=use_cols)
 
-    description = pd.read_excel (path, sheet_name = sheet_name, skiprows = description_row,
-                                 nrows = 1, usecols = description_col)
+    description = pd.read_excel (path, sheet_name=sheet_name, skiprows=description_row,
+                                 nrows=1, usecols=description_col)
 
     return (basic_DNA_parts, metadata, description)
 
 def quality_check(filled_library, blank_library, filled_metadata, blank_metadata, filled_description,
-                  blank_description, nrows, description_row, description_col=[0], use_cols = [0,1]):
+                  blank_description, nrows, description_row, description_col=[0], use_cols=[0,1]):
     """
     the function compares the edited excel spreadsheet with the template
 

requirements.txt

@@ -1,3 +1,4 @@
 sbol2==1.0b8
 pandas==1.0.1
 numpy==1.18.1
+xlrd >= 1.0.0