Merge pull request #95 from czbiohub-sf/dev

src/rapidqcms/AutoQCProcessing.py

@@ -35,7 +35,6 @@ def sequence_is_valid(filename, contents, vendor="Thermo Fisher"):
     Returns:
         True if sequence table is valid, otherwise False.
     """
-
     if ".csv" not in filename:
         return False
 
@@ -44,15 +43,15 @@ def sequence_is_valid(filename, contents, vendor="Thermo Fisher"):
 
         # Attempt to load sequence file as a pandas DataFrame
         try:
+            #Remove the bracket_type header from the Xcalibur export/import
+            bracket_type = contents.readline()
+            log.debug("Sequence_is_valid bracket_type = {}".format(bracket_type))
             df_sequence = pd.read_csv(contents, index_col=False)
         except Exception as error:
             print("Sequence file could not be read.")
             traceback.print_exc()
             return False
 
-        df_sequence.columns = df_sequence.iloc[0]
-        df_sequence = df_sequence.drop(df_sequence.index[0])
-
         # Define required columns and columns found in sequence file
         required_columns = ["File Name", "Path", "Instrument Method", "Position", "Inj Vol"]
         sequence_file_columns = df_sequence.columns.tolist()
@@ -188,9 +187,10 @@ def convert_sequence_to_json(sequence_contents, vendor="Thermo Fisher"):
 
     # Select columns from sequence using correct vendor software nomenclature
     if vendor == "Thermo Fisher":
+        bracket_type = sequence_contents.readline()
+        log.debug("convert_sequence_to_json bracket_type is = {}".format(bracket_type))
         df_sequence = pd.read_csv(sequence_contents, index_col=False)
-        df_sequence.columns = df_sequence.iloc[0]
-        df_sequence = df_sequence.drop(df_sequence.index[0])
+
 
     # Convert DataFrames to JSON strings
     return df_sequence.to_json(orient="split")

src/rapidqcms/DatabaseFunctions.py

@@ -1258,15 +1258,15 @@ def get_md5(instrument_id, sample_id):
     engine = sa.create_engine(database)
 
     # Check if sample is a biological standard
-    table = "sample_qc_results"
+    # can't parameterize tablenames
+    query = sa.text("SELECT * FROM sample_qc_results WHERE sample_id=:sample_id").bindparams(sample_id=sample_id)
 
     for identifier in get_biological_standard_identifiers().keys():
         if identifier in sample_id:
-            table = "bio_qc_results"
+            query = sa.text("SELECT * FROM bio_qc_results WHERE sample_id=:sample_id").bindparams(sample_id=sample_id)
             break
 
     # Get sample from correct table
-    query = sa.text("SELECT * FROM :table WHERE sample_id = :sample_id").bindparams(table=table, sample_id=sample_id)
     df_sample_qc_results = pd.read_sql(query, engine)
 
     return df_sample_qc_results["md5"].astype(str).values[0]