added mssing doc strings, tidy a regex in mzIdParser, rename variable…

… in schema_validate.py

config/config_parser.py

@@ -1,8 +1,17 @@
+"""
+config_parser.py
+"""
 from configparser import ConfigParser
 import os
 
 
 def parse_config(filename, section='postgresql'):
+    """
+    Parse database.ini file
+    :param filename:
+    :param section:
+    :return:
+    """
     # create a parser
     parser = ConfigParser()
     # read config file

config/database.py

@@ -1,3 +1,6 @@
+"""
+sessions used by sqlalchemy
+"""
 from sqlalchemy import create_engine
 from sqlalchemy.orm import sessionmaker
 from config_parser import get_conn_str

config/index.py

@@ -1,8 +1,14 @@
+"""
+index.py
+This file contains helper function to get database session
+"""
 from config.database import SessionLocal
 
 
-# Helper function to get database session
 def get_session():
+    """
+    Helper function to get database session
+    """
     session = SessionLocal()
     try:
         yield session

models/analysiscollectionspectrumidentification.py

@@ -1,3 +1,7 @@
+"""
+This file contains the AnalysisCollectionSpectrumIdentification class,
+which is a SQLAlchemy model for the analysiscollectionspectrumidentification table in the database.
+"""
 from sqlalchemy.orm import Mapped, mapped_column
 from sqlalchemy import ForeignKey, Text, ForeignKeyConstraint, Integer, Any, JSON
 from models.base import Base

models/base.py

@@ -1,3 +1,6 @@
+"""
+Base class for all models.
+"""
 from sqlalchemy.orm import DeclarativeBase
 
 

models/dbsequence.py

@@ -1,3 +1,4 @@
+"""This file contains the DBSequence class, which is a SQLAlchemy model for the dbsequence table in the database."""
 from sqlalchemy.orm import Mapped, mapped_column
 from sqlalchemy import ForeignKey, Text, Integer
 from models.base import Base

models/enzyme.py

@@ -1,3 +1,4 @@
+"""This file contains the Enzyme class, which is a SQLAlchemy model for the enzyme table in the database."""
 from sqlalchemy.orm import Mapped, mapped_column
 from sqlalchemy import ForeignKey, Text, BOOLEAN, ForeignKeyConstraint, Integer
 from models.base import Base

models/match.py

@@ -1,3 +1,4 @@
+"""This file contains the Match class, which is a SQLAlchemy model for the match table in the database."""
 from sqlalchemy.orm import Mapped, mapped_column
 from sqlalchemy import ForeignKey, Text, FLOAT, JSON, BOOLEAN, Integer, ForeignKeyConstraint, CHAR, Index
 from models.base import Base

models/modifiedpeptide.py

@@ -1,3 +1,7 @@
+"""
+This file contains the ModifiedPeptide class,
+which is a SQLAlchemy model for the modifiedpeptide table in the database.
+"""
 from sqlalchemy.orm import Mapped, mapped_column
 from sqlalchemy import ForeignKey, Text, Integer, JSON, FLOAT, Index
 from models.base import Base

models/peptideevidence.py

@@ -1,3 +1,7 @@
+"""
+This file contains the PeptideEvidence class,
+which is a SQLAlchemy model for the peptideevidence table in the database.
+"""
 from sqlalchemy.orm import Mapped, mapped_column
 from sqlalchemy import ForeignKey, Text, Integer, BOOLEAN, ForeignKeyConstraint, Index
 from models.base import Base

models/spectradata.py

@@ -1,5 +1,5 @@
 from sqlalchemy.orm import Mapped, mapped_column
-from sqlalchemy import ForeignKey, Text, Integer, UniqueConstraint
+from sqlalchemy import ForeignKey, Text, Integer
 from models.base import Base
 
 

parser/APIWriter.py

@@ -1,3 +1,4 @@
+"""APIWriter.py - Class for writing results via an API."""
 import traceback
 import requests
 import json
@@ -117,6 +118,13 @@ def write_mzid_info(self, analysis_software_list, spectra_formats,
             return None
 
     def write_other_info(self, contains_crosslinks, upload_warnings, upload_id):
+        """
+        Update Upload row with remaining info.
+        :param contains_crosslinks:
+        :param upload_warnings:
+        :param upload_id:
+        :return:
+        """
         response = None
         try:
             # todo: use urljoin

parser/DatabaseWriter.py

@@ -1,3 +1,4 @@
+"""DatabaseWriter class for writing results to a postgresql relational database."""
 from sqlalchemy import create_engine, MetaData
 from sqlalchemy import Table
 
@@ -42,6 +43,12 @@ def write_data(self, table, data):
             conn.close()
 
     def write_new_upload(self, table, data):
+        """
+        Insert data into upload table and return the id of the new row.
+        :param table:
+        :param data:
+        :return:
+        """
         table = Table(table, self.meta, autoload_with=self.engine, quote=False)
         with self.engine.connect() as conn:
             statement = table.insert().values(data).returning(table.columns[0])  # RETURNING id AS upload_id
@@ -54,8 +61,6 @@ def write_mzid_info(self, analysis_software_list, spectra_formats,
                         provider, audits, samples, bib, upload_id):
         """
         Update Upload row with mzid info.
-
-        ToDo: have this explicitly or create update func?
         :param analysis_software_list: (list) List of analysis software used.
         :param spectra_formats:
         :param provider:
@@ -66,6 +71,7 @@ def write_mzid_info(self, analysis_software_list, spectra_formats,
         :return:
         """
         upload = Table("upload", self.meta, autoload_with=self.engine, quote=False)
+        # noinspection PyTypeChecker
         stmt = upload.update().where(upload.c.id == str(upload_id)).values(
             analysis_software_list=analysis_software_list,
             spectra_formats=spectra_formats,
@@ -90,6 +96,7 @@ def write_other_info(self, contains_crosslinks, upload_warnings, upload_id):
         """
         upload = Table("upload", self.meta, autoload_with=self.engine, quote=False)
         with self.engine.connect() as conn:
+            # noinspection PyTypeChecker
             stmt = upload.update().where(upload.c.id == str(upload_id)).values(
                 contains_crosslinks=contains_crosslinks,
                 upload_warnings=upload_warnings,

parser/MzIdParser.py

@@ -1,3 +1,6 @@
+"""
+converts mzIdentML files to DB entries
+"""
 import base64
 import gzip
 import json
@@ -22,6 +25,7 @@
 
 
 class MzIdParseException(Exception):
+    """Exception raised when parsing mzIdentML files."""
     pass
 
 
@@ -102,6 +106,10 @@ def parse(self):
 
     @staticmethod
     def check_spectra_data_validity(sp_datum):
+        """
+        Check if the SpectraData element is valid.
+        :param sp_datum:
+        """
         # is there anything we'd like to complain about?
         # SpectrumIDFormat
         if 'SpectrumIDFormat' not in sp_datum or sp_datum['SpectrumIDFormat'] is None:
@@ -664,7 +672,7 @@ def main_loop(self):
         main_loop_start_time = time()
         self.logger.info('main loop - start')
 
-        msi_regex = re.compile(r'^([0-9]+)(?::(P|C))$')
+        msi_regex = re.compile(r'^([0-9]+):([PC])$')
 
         spec_count = 0
         spectra = []
@@ -814,6 +822,7 @@ def main_loop(self):
 
     # noinspection PyBroadException
     def upload_info(self):
+        """write mzid file level info to the DB."""
         upload_info_start_time = time()
         self.logger.info('parse upload info - start')
         self.mzid_reader.reset()
@@ -864,6 +873,9 @@ def upload_info(self):
             round(time() - upload_info_start_time, 2)))
 
     def fill_in_missing_scores(self):
+        """
+        Legacy xiSPEC, ignore
+        """
         pass
 
     def write_new_upload(self):
@@ -941,6 +953,11 @@ def get_cv_params(self, element, super_cls_accession=None):
     # split into two functions
     @staticmethod
     def extract_mzid(archive):
+        """
+        Extract the files from the archive.
+        :param archive:
+        :return:
+        """
         if archive.endswith('zip'):
             zip_ref = zipfile.ZipFile(archive, 'r')
             unzip_path = archive + '_unzip/'
@@ -1043,7 +1060,7 @@ def write_new_upload(self):
             }
             table = 'upload'
 
-            response = self.writer.write_data(table, upload_data)
+            self.writer.write_data(table, upload_data)
         except SQLAlchemyError as e:
             print(f"Error during database insert: {e}")
 

parser/SimpleFASTA.py

@@ -1,10 +1,16 @@
+"""SimpleFASTA.py - Parse a FASTA file and return a dictionary of the sequences."""
 import re
 
 
 #  why aren't we using pyteomics? todo? probably we haven't look at yet coz its only used by cvs parsers not mzid
 
 # noinspection PyUnusedLocal
 def get_db_sequence_dict(fasta_file_list):
+    """
+    Parse a FASTA file and return a dictionary of the sequences.
+    :param fasta_file_list:
+    :return: dict
+    """
     db_sequence_dict = {}
     identifier = None
     sequence = ""
@@ -39,6 +45,14 @@ def get_db_sequence_dict(fasta_file_list):
 
 
 def add_entry(identifier, sequence, description, seq_dict):
+    """
+    Add an entry to the sequence dictionary.
+    :param identifier:
+    :param sequence:
+    :param description:
+    :param seq_dict:
+    :return: None
+    """
     m = re.search(r'..\|(.*)\|(.*)\s?', identifier)
     # id = identifier
     accession = identifier

parser/Writer.py

@@ -1,26 +1,54 @@
+"""Writer.py - Abstract class for writing results to a database."""
 from abc import ABC, abstractmethod
 
 
 # Strategy interface
 class Writer(ABC):
-
+    """
+    Interface for writing results to a database.
+    """
     def __init__(self, upload_id=None, pxid=None):
         self.pxid = pxid
         self.upload_id = upload_id
 
     @abstractmethod
     def write_data(self, table, data):
+        """
+        Insert data into table.
+        :param table:
+        :param data:
+        """
         pass
 
     @abstractmethod
     def write_new_upload(self, table, data):
+        """
+        Insert data into upload table and, if postgres, return the id of the new row.
+        :param table:
+        :param data:
+        """
         pass
 
     @abstractmethod
     def write_mzid_info(self, analysis_software_list, spectra_formats,
                         provider, audits, samples, bib, upload_id):
+        """
+        Update the mzid_info table with the given data.
+        :param analysis_software_list:
+        :param spectra_formats:
+        :param provider:
+        :param audits:
+        :param samples:
+        :param bib:
+        :param upload_id:
+        """
         pass
 
     @abstractmethod
     def fill_in_missing_scores(self):
+        """
+        Legacy xiSPEC thing, can be ignored,
+        just leaving in rather than creating a backwards compatibility issue for xiSPEC
+        todo - probably remove
+        """
         pass

parser/__init__.py

@@ -1,3 +1,4 @@
+"""parser module"""
 from .csv_parser.FullCsvParser import *
 from .csv_parser.LinksOnlyCsvParser import *
 from .csv_parser.NoPeakListsCsvParser import *