X-Git-Url: https://wannabe.guru.org/gitweb/?a=blobdiff_plain;f=logical_search.py;h=0cfbc8d22624bffe9bc227e3ffde0abc0f313053;hb=24b9bcb2a4b74d2c242c8b4172f295b57c09b46d;hp=b55e68901501ad2e68a7f45df034866072c3f61b;hpb=e8fbbb7306430478dec55d2c963eed116d8330cc;p=python_utils.git

diff --git a/logical_search.py b/logical_search.py
index b55e689..0cfbc8d 100644
--- a/logical_search.py
+++ b/logical_search.py
@@ -1,15 +1,19 @@
 #!/usr/bin/env python3
 
+# © Copyright 2021-2022, Scott Gasch
+
 """This is a module concerned with the creation of and searching of a
 corpus of documents.  The corpus is held in memory for fast
-searching."""
+searching.
 
-from __future__ import annotations
+"""
 
+from __future__ import annotations
 import enum
 import sys
 from collections import defaultdict
-from typing import Any, Dict, List, NamedTuple, Optional, Sequence, Set, Tuple, Union
+from dataclasses import dataclass, field
+from typing import Any, Dict, List, Optional, Sequence, Set, Tuple, Union
 
 
 class ParseError(Exception):
@@ -20,13 +24,22 @@ class ParseError(Exception):
         self.message = message
 
 
-class Document(NamedTuple):
-    """A tuple representing a searchable document."""
+@dataclass
+class Document:
+    """A class representing a searchable document."""
+
+    # A unique identifier for each document.
+    docid: str = ''
 
-    docid: str  # a unique idenfier for the document
-    tags: Set[str]  # an optional set of tags
-    properties: List[Tuple[str, str]]  # an optional set of key->value properties
-    reference: Any  # an optional reference to something else
+    # A set of tag strings for this document.  May be empty.
+    tags: Set[str] = field(default_factory=set)
+
+    # A list of key->value strings for this document.  May be empty.
+    properties: List[Tuple[str, str]] = field(default_factory=list)
+
+    # An optional reference to something else; interpreted only by
+    # caller code, ignored here.
+    reference: Optional[Any] = None
 
 
 class Operation(enum.Enum):
@@ -91,6 +104,10 @@ class Corpus(object):
     ...          )
     >>> c.query('author:Scott and important')
     {1}
+    >>> c.query('*')
+    {1, 2, 3}
+    >>> c.query('*:*')
+    {1, 2, 3}
     """
 
     def __init__(self) -> None:
@@ -143,7 +160,6 @@ class Corpus(object):
 
     def get_docids_by_exact_tag(self, tag: str) -> Set[str]:
         """Return the set of docids that have a particular tag."""
-
         return self.docids_by_tag[tag]
 
     def get_docids_by_searching_tags(self, tag: str) -> Set[str]:
@@ -173,7 +189,7 @@ class Corpus(object):
     def invert_docid_set(self, original: Set[str]) -> Set[str]:
         """Invert a set of docids."""
 
-        return set([docid for docid in self.documents_by_docid.keys() if docid not in original])
+        return {docid for docid in self.documents_by_docid if docid not in original}
 
     def get_doc(self, docid: str) -> Optional[Document]:
         """Given a docid, retrieve the previously added Document."""
@@ -344,12 +360,22 @@ class Node(object):
                             key, value = tag.split(":")
                         except ValueError as v:
                             raise ParseError(f'Invalid key:value syntax at "{tag}"') from v
-                        if value == "*":
-                            r = self.corpus.get_docids_with_property(key)
+                        if key == '*':
+                            r = set()
+                            for s in self.corpus.docids_by_tag.values():
+                                r.update(s)
                         else:
-                            r = self.corpus.get_docids_by_property(key, value)
+                            if value == '*':
+                                r = self.corpus.get_docids_with_property(key)
+                            else:
+                                r = self.corpus.get_docids_by_property(key, value)
                     else:
-                        r = self.corpus.get_docids_by_exact_tag(tag)
+                        if tag == '*':
+                            r = set()
+                            for s in self.corpus.docids_by_tag.values():
+                                r.update(s)
+                        else:
+                            r = self.corpus.get_docids_by_exact_tag(tag)
                     retval.update(r)
                 else:
                     raise ParseError(f"Unexpected query {tag}")