added a preliminary cfood for testing

setup.py

@@ -71,7 +71,7 @@ def setup_package():
         package_data={},
         entry_points={
             "console_scripts": [
-                "crawl = crawl.__main__:main",
+                "crawl = src.__main__:main",
             ]
         }
     )

src/crawl.py

@@ -5,8 +5,32 @@
 import argparse
 import os
 import sys
+import yaml
 import re
 
+def crawl_cfood(dirname: str,
+                cfood: str):
+    """
+    Crawl a single cfood.
+    """
+
+    # Load the cfood from a yaml file:
+    with open(cfood, "r") as f:
+        cf = yaml.load(f, Loader=yaml.SafeLoader)
+
+    for currentpath, dirs, files in os.walk(dirname):
+        # for current nodes of type dir look in the list of dirs for matches
+        # dir is the default
+        if current_node["type"] == "dir":
+            for dirname in dirs:
+                pass
+        elif current_node["type"] == "file":
+            for filename in files:
+                pass
+        else:
+            # work in progress
+            pass
+            
 
 def crawl(dirname: str,
           cfoods: list[str]):
@@ -17,10 +41,12 @@ def crawl(dirname: str,
     cfoods  : a list of filenames of cfood files
     """
 
-    pass
+    # simplified for testing:
+    for cfood in cfoods:
+        crawl_cfood(dirname, cfood)
 
 def main():
-    pass
+    crawl(sys.args[1], [sys.args[2]])
 
 
 if __name__ == "__main__":

test/scifolder_cfood.yml

+
+DataAnalysis:
+
+  children:
+    project_dir:
+      re: (?P<date>.*?)_(?P<identifier>.*)
+      handlers:
+      - type: identifiable
+        name: idf_project
+
+      children:
+        single:
+          re: (?P<date>.*?)_(?P<identifier>.*)
+
+          children:
+
+            README:
+              type: file
+              case: insensitive
+              re: README\.md
+
+              children:
+              - description:
+                type: TEXT
+              - responsible:
+                children:
+                  type: TEXT
+                  re: (?P<first_name>.+) (?P<last_name>.+)
+                  handlers:
+                    type: identifiable
+                    name: idf_person