tweaked some code after looking at real images and added a readme

fccs_config.py

@@ -3,6 +3,7 @@ Shared configuration, logging, and utilities for the FCCS extraction tool.
 """
 
 import os
+import re
 import sys
 import argparse
 import configparser
@@ -62,6 +63,40 @@ def load_folder_list(path):
     return folders
 
 
+def build_folder_patterns(templates):
+    """
+    Convert folder template strings into regex patterns for matching.
+
+    Templates use YYYY as a year placeholder (e.g. 'YYYY Tax Documents').
+    Non-recurring folders (no YYYY) are matched literally.
+    A built-in pattern for 'UltraTax CS MM-DD-YYYY' is always included.
+
+    Returns a list of (compiled_regex, template_name) tuples, sorted
+    longest-first to prevent partial matches.
+    """
+    patterns = []
+
+    # Built-in: UltraTax CS folders (auto-generated by UltraTax integration)
+    patterns.append((
+        re.compile(r"UltraTax CS \d{2}-\d{2}-\d{4}$"),
+        "UltraTax CS",
+    ))
+
+    for tmpl in templates:
+        if "YYYY" in tmpl:
+            # Replace YYYY with 4-digit year pattern, escape the rest
+            parts = tmpl.split("YYYY")
+            regex_str = re.escape(parts[0]) + r"\d{4}" + re.escape(parts[1])
+        else:
+            # Non-recurring folder — exact match
+            regex_str = re.escape(tmpl)
+        patterns.append((re.compile(regex_str + "$"), tmpl))
+
+    # Sort by regex pattern length (longest first) to avoid partial matches
+    patterns.sort(key=lambda p: len(p[0].pattern), reverse=True)
+    return patterns
+
+
 def load_lines(path):
     """Read non-blank, non-comment lines from a file."""
     if not os.path.exists(path):