temporary fix to crazy file navigation

2 files changed, 54 insertions, 44 deletions

diff --git a/frontend/index.html b/frontend/index.html
index f0284eb..22c142c 100644
--- a/frontend/index.html
+++ b/frontend/index.html
@@ -84,7 +84,7 @@
         text = "";        
       }
       $("#main").html(text);
-      $("#main-title").html(res['parents'] + "/" + res['current']);
+      $("#main-title").html(res['current']);
       hljs.highlightAll();
 
       $("#talk-button").click(()=>{
diff --git a/server.py b/server.py
index 663f8b4..08f20dd 100644
--- a/server.py
+++ b/server.py
@@ -2,15 +2,15 @@ from flask import Flask, request, Response, jsonify, render_template
 import pandas as pd
 from collections import defaultdict
 import os
+import json
 import openai
 from openai.embeddings_utils import get_embedding, cosine_similarity
 openai.api_key = os.getenv('OPENAI_KEY')
 import numpy as np
+from pathlib import PurePosixPath
 
 app = Flask(__name__, template_folder="./frontend", static_folder="./frontend", static_url_path="")
 
-
-
 def search_code(df, query, n=4):
     query_embedding = get_embedding(
         query,
@@ -44,37 +44,34 @@ def generate_answer(question):
   )
   return response["choices"][0]["text"]
 
-# The above two functions should already work with the Go version.
-
-def get_code_structure(df):
-    kids_structure = defaultdict(list)
-    parents_structure = {}
-    for path in list(df['file_path'].unique()):
-        t = path.split("/")
-        for e in range(len(t)):
-            # if we know it's a dir name, record the next path component as a
-            # child of the current dir.
-            if e < len(t) - 1:
-              kids_structure[t[e]].append(t[e+1])
-            else:
-              kids_structure[t[e]] = ["file"]
-            if e == 0:
-              parents_structure[t[e]] = "./"
-            else:
-              parents_structure[t[e]] = "/".join(t[:e])
 
-    for k, v in kids_structure.items():
-        kids_structure[k] = list(set(v))
-    return dict(kids_structure), parents_structure
+def add_to_tree(tree: dict, path: str):
+    parts = PurePosixPath(path).parts
+    current = tree
+    for i, part in enumerate(parts):
+        if part not in current:
+            current[part] = {}
+            if i == len(parts) - 1:
+                current[part]["filetype"] = "file"
+            else:
+                current[part]["filetype"] = "dir"
+                current[part]["children"] = {}
+        current = current[part].get("children", {})
 
+def create_directory_tree(df):
+    paths = list(df['file_path'].unique())
+    directory_tree = {}
+    for path in paths:
+        add_to_tree(directory_tree, path)
+    return directory_tree
 
 # Nate: these are from the original project. My own csv is below
 #df = pd.read_csv("./frontend/data/embedded_summarized.csv")
 #df = pd.read_csv("./frontend/data/withsummary2.csv")
 
 # My line
-#df=pd.read_csv("./frontend/data/test_with_summary_and_embeddings.csv", converters={'embedding_summary': pd.eval})
-df=pd.read_csv("./frontend/data/rs.csv", converters={'embedding_summary': pd.eval})
+df=pd.read_csv("./frontend/data/test_with_summary_and_embeddings.csv", converters={'embedding_summary': pd.eval})
+#df=pd.read_csv("./frontend/data/rs.csv", converters={'embedding_summary': pd.eval})
 
 # need to do funny stuff to read in the data frame correctly from csv. that's
 # why the eval() is below. and pd.eval is above.
@@ -83,31 +80,44 @@ df=pd.read_csv("./frontend/data/rs.csv", converters={'embedding_summary': pd.eva
 #df['embeddings'] = df['embeddings'].apply(lambda x: eval(x))
 
 filetypes = ['.sh', '.c', '.h', '.cpp', '.cxx', '.hxx', '.hpp', '.go', '.hs', '.js', '.py', '.rs']
+def check_path(path, dirstructure):
+  children = None
+  components = PurePosixPath(path).parts
+  if(components[0] in dirstructure.keys()):
+    print('SCREAM')
+
+    currentdict = dirstructure.get(components[0]) #outermost is solitary by setup.py
+    print(len(components))
+    for component in components[1:]:
+      print('COMP', component)
+      if component in currentdict.get("children", {}):
+        currentdict = currentdict["children"][component]
+      else:
+        return False, None, children
+      if currentdict["filetype"] == "dir":
+        children = currentdict["children"]
+      return True, currentdict["filetype"], children
+  else:
+    return False, None, None
 
-# messed this area up for debugging
 @app.route('/')
 def home():
-  stub = request.args.get('path', 'hello').strip()
-  kids_structure, parents_structure = get_code_structure(df)
-  if stub not in kids_structure:
-    loctype = "nan"
-    text = [["Path not available!"], [""]]
-  elif any([stub.endswith(x) for x in filetypes]):
-    loctype = "file"
-    fullpath = f"{parents_structure[stub]}/{stub}"
-    print(fullpath)
-    text = [[x, y] for x, y in zip(
-      list(df[df['file_path'] == fullpath]['source']),
-      list(df[df['file_path'] == fullpath]['summary'])
-    )]
-  else:
+  req_path = request.args.get('path')
+  dirstructure = create_directory_tree(df)
+  if req_path is None:
     loctype = "folder"
-    text = [[x, ""] for x in kids_structure[stub]]
+    text = [[x, ""] for x in list(df['file_path'].unique())]
+  else:
+    text = [[x, y] for x, y in zip(
+      list(df[df['file_path'] == req_path]['source']),
+      list(df[df['file_path'] == req_path]['summary'])
+        )]
+    loctype = "file"
+
   res = {
-    'parents': parents_structure[stub],
     'loctype': loctype,
     'text': text,
-    'current': stub
+    'current': 'root directory' if (req_path is None) else req_path
   }
   return render_template('index.html', payload=res)