Use new Text Entry class to track text entries in Intermediate Format

- Context
  - The app maintains all text content in a standard, intermediate format
  - The intermediate format was loaded, passed around as a dictionary
    for easier, faster updates to the intermediate format schema initially
  - The intermediate format is reasonably stable now, given it's usage
    by all 3 text content types currently implemented

- Changes
  - Concretize text entries into `Entries' class instead of using dictionaries
    - Code is updated to load, pass around entries as `Entries' objects
      instead of as dictionaries
    - `text_search' and `text_to_jsonl' methods are annotated with
       type hints for the new `Entries' type
    - Code and Tests referencing entries are updated to use class style
      access patterns instead of the previous dictionary access patterns

  - Move `mark_entries_for_update' method into `TextToJsonl' base class
    - This is a more natural location for the method as it is only
      (to be) used by `text_to_jsonl' classes
    - Avoid circular reference issues on importing `Entries' class

src/search_filter/date_filter.py

@@ -37,7 +37,7 @@ class DateFilter(BaseFilter):
         start = time.time()
         for id, entry in enumerate(entries):
             # Extract dates from entry
-            for date_in_entry_string in re.findall(r'\d{4}-\d{2}-\d{2}', entry[self.entry_key]):
+            for date_in_entry_string in re.findall(r'\d{4}-\d{2}-\d{2}', getattr(entry, self.entry_key)):
                 # Convert date string in entry to unix timestamp
                 try:
                     date_in_entry = datetime.strptime(date_in_entry_string, '%Y-%m-%d').timestamp()

src/search_filter/file_filter.py

@@ -24,7 +24,7 @@ class FileFilter(BaseFilter):
     def load(self, entries, *args, **kwargs):
         start = time.time()
         for id, entry in enumerate(entries):
-            self.file_to_entry_map[entry[self.entry_key]].add(id)
+            self.file_to_entry_map[getattr(entry, self.entry_key)].add(id)
         end = time.time()
         logger.debug(f"Created file filter index: {end - start} seconds")
 

src/search_filter/word_filter.py

@@ -29,7 +29,7 @@ class WordFilter(BaseFilter):
         entry_splitter = r',|\.| |\]|\[\(|\)|\{|\}|\<|\>|\t|\n|\:|\;|\?|\!|\(|\)|\&|\^|\$|\@|\%|\+|\=|\/|\\|\||\~|\`|\"|\''
         # Create map of words to entries they exist in
         for entry_index, entry in enumerate(entries):
-            for word in re.split(entry_splitter, entry[self.entry_key].lower()):
+            for word in re.split(entry_splitter, getattr(entry, self.entry_key).lower()):
                 if word == '':
                     continue
                 self.word_to_entry_index[word].add(entry_index)