wip part 2

extract-data.py

@@ -14,6 +14,11 @@ def find_py_files(dir):
                 yield os.path.join(cwd, file)
 
 
+def keep_name(name):
+    return not name.startswith("_") and not "main" in str(name).lower() and \
+        "test" not in str(name).lower()
+
+
 class FeatureVisitor(ast.NodeVisitor):
 
     def __init__(self, filename):
@@ -21,6 +26,7 @@ class FeatureVisitor(ast.NodeVisitor):
         self.rows = []
 
     def visit_FunctionDef(self, node):
+        if keep_name(node.name):
             self.rows.append({
                 "name": node.name, 
                 "file": self.filename,
@@ -29,16 +35,8 @@ class FeatureVisitor(ast.NodeVisitor):
                 "comment": ast.get_docstring(node)
             })
 
-    def visit_MethodDef(self, node):
-        self.rows.append({
-            "name": node.name,
-            "file": self.filename,
-            "line": node.lineno,
-            "type": "method",
-            "comment": ast.get_docstring(node)
-        })
-    
     def visit_ClassDef(self, node):
+        if keep_name(node.name):
             self.rows.append({
                 "name": node.name,
                 "file": self.filename,
@@ -46,6 +44,17 @@ class FeatureVisitor(ast.NodeVisitor):
                 "type": "class",
                 "comment": ast.get_docstring(node)
             })
+            for nd in ast.walk(node):
+                if isinstance(nd, ast.FunctionDef):
+                    if keep_name(nd.name):
+                        self.rows.append({
+                            "name": nd.name,
+                            "file": self.filename,
+                            "line": nd.lineno,
+                            "type": "method",
+                            "comment": ast.get_docstring(nd)
+                        })
+
 
 
 def main():

search-data.py

@@ -0,0 +1,23 @@
+import re
+import argparse
+import os
+import pandas as pd
+
+SCRIPT_DIR = os.path.abspath(os.path.dirname(__file__))
+IN_DATASET = os.path.join(SCRIPT_DIR, "data.csv")
+
+
+def search(query):
+    df = pd.read_csv(IN_DATASET)
+    
+
+
+def main():
+    parser = argparse.ArgumentParser()
+    parser.add_argument("query", help="the query to search the corpus with", type=str)
+    args = parser.parse_args()
+    search(query)
+
+
+if __name__ == "__main__":
+    main()