pidibble 1.3.2__tar.gz → 1.4.0__tar.gz

{pidibble-1.3.2 → pidibble-1.4.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pidibble
-Version: 1.3.2
+Version: 1.4.0
 Summary: A complete Protein Data Bank (PDB) file parser
 Project-URL: Source, https://github.com/cameronabrams/pidibble
 Project-URL: Documentation, https://pidibble.readthedocs.io/en/latest/
@@ -91,6 +91,10 @@ ATOM
 ```
 
 ## Release History
+* 1.4.0
+   * Introduced `PDBRecordList` and `PDBRecordDict` classes
+* 1.3.3
+   * fixed bugs regarding assuming missing records actually present in mmcif parsing
 * 1.3.2
    * implemented `filepath` parameter in `PDBParser()` to make
      reading local files more transparent

{pidibble-1.3.2 → pidibble-1.4.0}/README.md

@@ -73,6 +73,10 @@ ATOM
 ```
 
 ## Release History
+* 1.4.0
+   * Introduced `PDBRecordList` and `PDBRecordDict` classes
+* 1.3.3
+   * fixed bugs regarding assuming missing records actually present in mmcif parsing
 * 1.3.2
    * implemented `filepath` parameter in `PDBParser()` to make
      reading local files more transparent

{pidibble-1.3.2 → pidibble-1.4.0}/pidibble/mmcif_parse.py

@@ -9,7 +9,7 @@
 """
 
 from collections import UserDict
-from .pdbrecord import PDBRecord
+from .pdbrecord import PDBRecord, PDBRecordDict, PDBRecordList
 from .baserecord import BaseRecord
 import logging
 logger=logging.getLogger(__name__)
@@ -214,8 +214,9 @@ class MMCIF_Parser:
         spawns_on=mapspec.get('spawns_on',None)
         allcaps=mapspec.get('allcaps',[])
         if_dot_replace_with=mapspec.get('if_dot_replace_with',{})
+        logger.debug(f'getting cifrec for {mapspec["data_obj"]}')
         cifrec=self.cif_data.getObj(mapspec['data_obj'])
-        if not tables:
+        if not tables and cifrec is not None:
             for idx in range(len(cifrec)):
                 if not use_signal or (cifrec.getValue(sigattr,idx)==sigval):
                     if global_maps:
@@ -334,18 +335,18 @@ class MMCIF_Parser:
 
         Returns
         -------
-        dict
-            A dictionary where keys are record types and values are lists of :class:`pdbrecord.sPDBRecord` instances.
+        PDBRecordDict
+            A dictionary where keys are record types and values are lists of :class:`pdbrecord.PDBRecord` instances.
         """
-        recdict={}
+        recdict=PDBRecordDict()
         for rectype,mapspec in self.formats.items():
             idicts=self.gen_dict(mapspec)
             for idict in idicts:
                 this_key=idict.get('tmp_label','')
                 reckey=rectype if not this_key else f'{rectype}.{this_key}'
                 if reckey in recdict:
-                    if not type(recdict[reckey])==list:
-                        recdict[reckey]=[recdict[reckey]]
+                    if not type(recdict[reckey])==PDBRecordList:
+                        recdict[reckey]=PDBRecordList([recdict[reckey]])
                     idict['key']=reckey
                     recdict[reckey].append(PDBRecord(idict))
                 else:

{pidibble-1.3.2 → pidibble-1.4.0}/pidibble/pdbparse.py

@@ -14,10 +14,11 @@ import yaml
 import numpy as np
 from pathlib import Path
 from mmcif.io.IoAdapterCore import IoAdapterCore
+from typing import List, Dict
 from . import resources
 from .baseparsers import ListParsers, ListParser, str2int_sig, safe_float
 from .baserecord import BaseRecordParser
-from .pdbrecord import PDBRecord
+from .pdbrecord import PDBRecord, PDBRecordDict, PDBRecordList
 from .mmcif_parse import MMCIF_Parser
 from pidibble import resources
 logger=logging.getLogger(__name__)
@@ -35,9 +36,10 @@ class PDBParser:
 
     Attributes
     ----------
-    
-    parsed : dict
-        A dictionary to store parsed records, where keys are record types and values are lists of :class:`.pdbrecord.PDBRecord` instances. Empty if no input file is provided.
+
+    parsed : PDBRecordDict
+        A dictionary containing parsed records, where keys are record types and values are :class:`.pdbrecord.PDBRecord` instances or lists of instances.
+        This dictionary is populated after parsing the PDB or mmCIF file.
 
     mappers : dict
         A dictionary of mappers for parsing different data types, including custom formats and delimiters.
@@ -75,7 +77,7 @@ class PDBParser:
         self.pdb_lines=[]
         self.cif_data={}
 
-        self.parsed={}
+        self.parsed=PDBRecordDict()
         self.pdb_format_file=pdb_format_file
         if not os.path.isfile(self.pdb_format_file):
             # if pdb_format_file is not a file in the CWD, assume it is a relative path to the resources directory
@@ -262,7 +264,7 @@ class PDBParser:
                             if tok[0]==group_open_record.key:
                                 groupid=getattr(group_open_record,tok[1])
                                 setattr(new_record,group_open_record.key.lower(),groupid)
-                    self.parsed[key]=[new_record]
+                    self.parsed[key]=PDBRecordList([new_record])
                 else:
                     # this is either
                     # (a) a continuation record of a given key.(determinants)
@@ -328,7 +330,7 @@ class PDBParser:
                 rf=p.format
                 if 'embedded_records' in rf:
                     new_parsed_records.update(p.parse_embedded(self.pdb_format_dict['record_formats'],self.mappers))
-            elif type(p)==list:
+            elif type(p)==PDBRecordList:
                 for q in p:
                     rf=q.format
                     if 'embedded_records' in rf:
@@ -361,7 +363,7 @@ class PDBParser:
         It updates the :attr:`PDBParser.parsed` dictionary with the new parsed records.
         """
         for key,p in self.parsed.items():
-            if type(p)==list:
+            if type(p)==PDBRecordList:
                 continue # don't expect to read a table from a multiple-record entry
             rf=p.format
             if 'tables' in rf:

{pidibble-1.3.2 → pidibble-1.4.0}/pidibble/pdbrecord.py

@@ -7,7 +7,7 @@
 .. moduleauthor: Cameron F. Abrams, <cfa22@drexel.edu>
 
 """
-
+from collections import UserList, UserDict
 from .baserecord import BaseRecord, BaseRecordParser
 from .baseparsers import StringParser
 import logging
@@ -442,6 +442,79 @@ class PDBRecord(BaseRecord):
                     if not all([x=='' for x in parsedrow.__dict__.values()]):
                         self.tables[tname].append(parsedrow)
 
+class PDBRecordList(UserList):
+    """
+    A class representing a list of PDBRecord instances, inheriting from UserList.
+    It provides methods for parsing and handling multiple PDB records.
+    """
+    def __init__(self, initlist=None):
+        if initlist is not None:
+            self._validate_all(initlist)
+        super().__init__(initlist or [])
+
+    def _validate(self, item):
+        if not isinstance(item, PDBRecord):
+            raise TypeError(f"All items must be instances of PDBRecord, got {type(item)}")
+
+    def _validate_all(self, iterable):
+        for item in iterable:
+            self._validate(item)
+
+    def __setitem__(self, index, item):
+        # Support slice assignment
+        if isinstance(index, slice):
+            self._validate_all(item)
+        else:
+            self._validate(item)
+        super().__setitem__(index, item)
+
+    def append(self, item):
+        self._validate(item)
+        super().append(item)
+
+    def insert(self, index, item):
+        self._validate(item)
+        super().insert(index, item)
+
+    def extend(self, other):
+        self._validate_all(other)
+        super().extend(other)
+
+    def __add__(self, other):
+        self._validate_all(other)
+        return AList(super().__add__(other))
+
+    def __iadd__(self, other):
+        self._validate_all(other)
+        return super().__iadd__(other)
+    
+class PDBRecordDict(UserDict):
+    """
+    A class representing a dictionary of PDBRecord or PDBRecordList instances, inheriting from UserDict.
+    It provides methods for parsing and handling multiple PDB records stored in a dictionary.
+    """
+    def __init__(self, *args, **kwargs):
+        super().__init__()
+        self.update(*args, **kwargs)
+
+    def _validate(self, value):
+        if not isinstance(value, (PDBRecord, PDBRecordList)):
+            raise TypeError(f"Values must be PDBRecord or PDBRecordList, got {type(value)}")
+
+    def __setitem__(self, key, value):
+        self._validate(value)
+        super().__setitem__(key, value)
+
+    def update(self, *args, **kwargs):
+        other = dict(*args, **kwargs)
+        for key, value in other.items():
+            self[key] = value  # Triggers __setitem__
+
+    def setdefault(self, key, default=None):
+        if key not in self:
+            self[key] = default  # Triggers __setitem__
+        return self[key]
+
 def header_check(record,headers,parse,hold=[]):
     """
     Check if a record is a header line and parse it accordingly.

{pidibble-1.3.2 → pidibble-1.4.0}/pyproject.toml

@@ -3,7 +3,7 @@ requires = ["hatchling"]
 build-backend = "hatchling.build"
 [project]
 name = "pidibble"
-version = "1.3.2"
+version = "1.4.0"
 authors = [
   { name="Cameron F Abrams", email="cfa22@drexel.edu" },
 ]