💄 consolidate outname

Signed-off-by: peter szemraj <[email protected]>

utils.py

@@ -107,16 +107,16 @@ def load_example_filenames(example_path: str or Path):
 
 
 def extract_keywords(
-    text: str, num_keywords: int = 3, window_size: int = 5
+    text: str, num_keywords: int = 3, window_size: int = 5, kw_max_len: int = 20
 ) -> List[str]:
     """
     Extracts keywords from a text using a simplified TextRank algorithm.
 
     Args:
         text: The text to extract keywords from.
-        num_keywords: The number of keywords to extract. Default is 5.
-        window_size: The number of words considered for co-occurrence. Default is 5.
-
+        num_keywords: The number of keywords to extract. Default: 3
+        window_size: The number of words considered for co-occurrence. Default: 5
+        kw_max_len: The maximum length of a keyword (truncate longer keywords to max). Default: 20
     Returns:
         A list of strings, where each string is a keyword extracted from the input text.
     """
@@ -155,8 +155,8 @@ def extract_keywords(
     final_keywords = []
     for keyword in keywords:
         if not any(fuzz.ratio(keyword, other) > 70 for other in final_keywords):
-            final_keywords.append(keyword)
-    logger.debug(f"Keywords (final):\t{final_keywords}")
+            final_keywords.append(keyword[:kw_max_len])
+    logger.debug(f"Keywords (max len. {kw_max_len}):\t{final_keywords}")
     return final_keywords
 
 
@@ -177,10 +177,10 @@ def saves_summary(
     scores_text = "\n".join(sum_scores)
     full_summary = "\n".join(sum_text)
 
-    keywords = "_".join(extract_keywords(full_summary))
+    keywords = "_".join(extract_keywords(full_summary, kw_max_len=4))
     logger.debug(f"kw:\t{keywords}")
     outpath = (
-        Path.cwd() / f"document_summary_{keywords}_{get_timestamp()}.txt"
+        Path.cwd() / f"DocSummary_{keywords}_{get_timestamp()}.txt"
         if outpath is None
         else Path(outpath)
     )