epstein-files 1.2.1__py3-none-any.whl → 1.2.5__py3-none-any.whl

epstein_files/__init__.py

@@ -16,14 +16,18 @@ from rich.text import Text
 from epstein_files.epstein_files import EpsteinFiles, document_cls
 from epstein_files.documents.document import INFO_PADDING, Document
 from epstein_files.documents.email import Email
+from epstein_files.documents.messenger_log import MessengerLog
+from epstein_files.documents.other_file import OtherFile
 from epstein_files.util.constant.output_files import make_clean
+from epstein_files.util.constant.strings import ID_REGEX
+from epstein_files.util.data import flatten
 from epstein_files.util.env import args
 from epstein_files.util.file_helper import coerce_file_path, extract_file_id
 from epstein_files.util.logging import exit_with_error, logger
 from epstein_files.util.output import (print_emails_section, print_json_files, print_json_stats,
      print_other_files_section, print_text_messages_section, print_email_timeline, print_emailers_info,
      print_json_metadata, write_urls)
-from epstein_files.util.rich import (build_highlighter, console, print_color_key, print_title_page_header,
+from epstein_files.util.rich import (build_highlighter, console, highlighter, print_color_key, print_title_page_header,
      print_title_page_tables, print_subtitle_panel, write_html)
 from epstein_files.util.timer import Timer
 from epstein_files.util.word_count import write_word_counts_html
@@ -76,6 +80,9 @@ def generate_html() -> None:
     write_html(args.build)
     logger.warning(f"Total time: {timer.seconds_since_start_str()}")
 
+    if args.debug:
+        highlighter.print_highlight_counts(console)
+
     # JSON stats (mostly used for building pytest checks)
     if args.json_stats:
         print_json_stats(epstein_files)
@@ -90,23 +97,36 @@ def epstein_search():
     """Search the cleaned up text of the files."""
     epstein_files = EpsteinFiles.get_files()
 
+    if ID_REGEX.match(args.positional_args[0]):
+        logger.warning(f"'{args.positional_args[0]}' seems to be an ID, running epstein_show instead...")
+        epstein_show()
+        return
+
     for search_term in args.positional_args:
         temp_highlighter = build_highlighter(search_term)
         search_results = epstein_files.docs_matching(search_term, args.names)
         print_subtitle_panel(f"Found {len(search_results)} documents matching '{search_term}'")
 
         for search_result in search_results:
-            console.line()
+            document = search_result.document
+
+            if (isinstance(document, Email) and not args.output_emails) \
+                    or (isinstance(document, OtherFile) and not args.output_other) \
+                    or (isinstance(document, MessengerLog) and not args.output_texts):
+                document.warn(f"{type(document).__name__} Skipping search result...")
+                continue
 
             if args.whole_file:
-                console.print(search_result.document)
+                console.print(document)
             else:
-                console.print(search_result.document.summary_panel())
+                console.print(document.summary_panel())
 
                 for matching_line in search_result.lines:
                     line_txt = matching_line.__rich__()
                     console.print(Padding(temp_highlighter(line_txt), INFO_PADDING), style='gray37')
 
+            console.line()
+
 
 def epstein_show():
     """Show the color highlighted file. If --raw arg is passed, show the raw text of the file as well."""
@@ -114,8 +134,13 @@ def epstein_show():
     console.line()
 
     try:
-        ids = [extract_file_id(arg) for arg in args.positional_args]
-        raw_docs = [Document(coerce_file_path(id)) for id in ids]
+        if args.names:
+            people = EpsteinFiles.get_files().person_objs(args.names)
+            raw_docs = [doc for doc in flatten([p.emails for p in people])]
+        else:
+            ids = [extract_file_id(arg) for arg in args.positional_args]
+            raw_docs = [Document(coerce_file_path(id)) for id in ids]
+
         docs = Document.sort_by_timestamp([document_cls(doc)(doc.file_path) for doc in raw_docs])
     except Exception as e:
         exit_with_error(str(e))

epstein_files/documents/document.py

@@ -271,7 +271,7 @@ class Document:
         txt.append(", ").append(key_value_txt('lines', self.num_lines()))
 
         if self.config and self.config.duplicate_of_id:
-            txt.append(", ").append(key_value_txt('dupe_of', Text(self.config.duplicate_of_id, style='magenta')))
+            txt.append(", ").append(key_value_txt('dupe_of', Text(self.config.duplicate_of_id, style='cyan dim')))
 
         return txt
 
@@ -435,6 +435,10 @@ class Document:
         """Count of how many Document objects have an author attribution."""
         return len([doc for doc in docs if doc.author])
 
+    @staticmethod
+    def sort_by_id(docs: Sequence['DocumentType']) -> list['DocumentType']:
+        return sorted(docs, key=lambda d: d.file_id)
+
     @staticmethod
     def sort_by_timestamp(docs: Sequence['DocumentType']) -> list['DocumentType']:
         return sorted(docs, key=lambda doc: doc.timestamp_sort_key())