IssueID #1487: removed redundant reliance on original list file

scripts/pipeline2.py

@@ -6,27 +6,24 @@ import lxml.etree as lxml
 from constants import *
 
 arg_parser = argparse.ArgumentParser(description='Assign parsed Slovene strings to structures and generate lexicon.')
-arg_parser.add_argument('-inlist', type=str, help='Original input list file')
 arg_parser.add_argument('-intei', type=str, help='Parsed and manually edited TEI file')
 arg_parser.add_argument('-outstructures', type=str, help='Output structure file')
 arg_parser.add_argument('-outlexicon', type=str, help='Output lexicon file')
 arguments = arg_parser.parse_args()
-input_list_file_name = arguments.inlist
 input_tei_file_name = arguments.intei
 output_structure_file_name = arguments.outstructures
 output_lexicon_file_name = arguments.outlexicon
 
-def run_pipeline(input_list_file_name, input_tei_file_name, output_lexicon_file_name, output_structure_file_name):
+def run_pipeline(input_tei_file_name, output_lexicon_file_name, output_structure_file_name):
     shutil.rmtree(TMP_DIRECTORY, True)
     os.makedirs(TMP_DIRECTORY, exist_ok=True)
-    shutil.copyfile(input_list_file_name, STRING_LIST_FILE_NAME)
     shutil.copyfile(input_tei_file_name, TEI_INIT_FILE_NAME)
     run_mwe_extraction(STRUCTURE_CURRENT_FILE_NAME, TEI_INIT_FILE_NAME, MWE_CSV_1_FILE_NAME)
-    run_structure_assignment(STRING_LIST_FILE_NAME, TEI_INIT_FILE_NAME, MWE_CSV_1_FILE_NAME, TEI_STRUCTURE_1_FILE_NAME)
+    run_structure_assignment(TEI_INIT_FILE_NAME, MWE_CSV_1_FILE_NAME, TEI_STRUCTURE_1_FILE_NAME)
     run_structure_creation(STRUCTURE_CURRENT_FILE_NAME, TEI_STRUCTURE_1_FILE_NAME, STRUCTURE_NEW_FILE_NAME)
     validate_structures(STRUCTURE_NEW_FILE_NAME)
     run_mwe_extraction(STRUCTURE_NEW_FILE_NAME, TEI_INIT_FILE_NAME, MWE_CSV_2_FILE_NAME)
-    run_structure_assignment(STRING_LIST_FILE_NAME, TEI_INIT_FILE_NAME, MWE_CSV_2_FILE_NAME, TEI_STRUCTURE_2_FILE_NAME)
+    run_structure_assignment(TEI_INIT_FILE_NAME, MWE_CSV_2_FILE_NAME, TEI_STRUCTURE_2_FILE_NAME)
     run_dictionary_conversion(TEI_STRUCTURE_2_FILE_NAME, DICTIONARY_XML_FILE_NAME)
     validate_dictionary(DICTIONARY_XML_FILE_NAME)
     shutil.copyfile(DICTIONARY_XML_FILE_NAME, output_lexicon_file_name)
@@ -44,9 +41,9 @@ def validate_structures(structure_file_name):
     xml_tree = lxml.parse(structure_file_name)
     xml_schema.assertValid(xml_tree)
 
-def run_structure_assignment(input_file_name, tei_file_name, mwe_csv_file_name, output_file_name):
+def run_structure_assignment(tei_file_name, mwe_csv_file_name, output_file_name):
     print('Assigning structure ids ...')
-    assignment_command = ' '.join(['python', STRUCTURE_ASSIGNMENT_SCRIPT_NAME, input_file_name, tei_file_name, mwe_csv_file_name, output_file_name])
+    assignment_command = ' '.join(['python', STRUCTURE_ASSIGNMENT_SCRIPT_NAME, tei_file_name, mwe_csv_file_name, output_file_name])
     os.system(assignment_command)
 
 def run_structure_creation(input_file_name, tei_file_name, output_file_name):
@@ -65,4 +62,4 @@ def validate_dictionary(dictionary_file_name):
     xml_tree = lxml.parse(dictionary_file_name)
     xml_schema.assertValid(xml_tree)
 
-run_pipeline(input_list_file_name, input_tei_file_name, output_lexicon_file_name, output_structure_file_name)
+run_pipeline(input_tei_file_name, output_lexicon_file_name, output_structure_file_name)