Document extract.codes strategy, min/max_length, sort_order, disallow…

wrangles/extract.py

@@ -427,6 +427,20 @@ def codes(
 
     e.g. 'Something ABC123ZZ something' -> 'ABC123ZZ'
 
+    :param input: A string or list of strings to search for codes.
+    :param first_element: Get the first element from results.
+    :param min_length: Minimum length of allowed results.
+    :param max_length: Maximum length of allowed results.
+    :param strategy: Controls filtering of likely false positives such as measurements.
+        'lenient' skips this filter, while 'balanced' and 'strict' currently apply
+        the same filter. Default is 'balanced'. Unless min_length is provided,
+        minimum lengths default to 3 for lenient, 4 for balanced, and 5 for strict.
+    :param sort_order: Default is input order. Also allows 'longest' or 'shortest'.
+    :param disallowed_patterns: A pattern or JSON array of regex patterns to not include in the found codes.
+    :param include_multi_part_tokens: Whether to include multi-part tokens that have a space. Default True.
+    :param extract_raw: Whether to return tokens with their adjacent non-whitespace characters
+        included, rather than the cleaned token. Default False.
+    :return: A list of codes found.
     """
     if isinstance(input, str): 
         json_data = [input]

wrangles/recipe_wrangles/extract.py

@@ -856,7 +856,7 @@ def codes(
         description: Maximum length of allowed results
       strategy:
         type: string
-        description: How aggressive to be at removing false positives such as measurements.
+        description: Controls filtering of likely false positives such as measurements. Lenient skips this filter; balanced and strict currently apply the same filter. Default is balanced. Unless min_length is provided, minimum lengths default to 3 for lenient, 4 for balanced, and 5 for strict.
         enum:
           - lenient
           - balanced
@@ -876,7 +876,7 @@ def codes(
         description: Whether to include multi-part tokens that have a space. Default True.
       extract_raw:
         type: boolean
-        description: Whether to return tokens with their adjacent non-whitespace characters. Default False.
+        description: Whether to return tokens with their adjacent non-whitespace characters included, rather than the cleaned token. Default False.
     """
     # If output is not specified, overwrite input columns in place
     if output is None: output = input