oh. the add all method was........ never used.

Readme.md

@@ -4,6 +4,7 @@ use whoosh to search github issues.
 
 Implemented in **Python** using **Flask**, **Whoosh** and **Mistune**.
 
+<img src="img/screenshot.png" width="500px" />
 
 ## notes
 
@@ -35,8 +36,15 @@ summary of how to change the schema:
     - Search class defines Schema object, main definition
     - `add_issue()` (equally important) which defines how to extract the
       fields defined in the schema from the document
-    - 
-
+    - `create_search_result()` (also important) which packages up the
+      search results for the template to deal with
+- `search.html`: the search.html template uses a different variable
+  namespace than the Python file `issues_search.py` or the flask app
+    - The `create_search-result()` method of `issues_search.py`
+      defines how search results are parsed and packaged for the
+      `search.html` template
+    - Jinja variables used in `search.html` should be defined in
+      `create_search_result()` method of `issues_search.py`
 
 
 

Todo.md

@@ -0,0 +1,31 @@
+# TODO
+
+recap of round 1:
+- issues search is working well
+- indexing comments and issues
+- able to easily add new fields to schema
+- able to easily modify search + results template
+- mapping out where everything is
+
+## Round 2 (done)
+
+improvements:
+- storing comments and issues as separate objects?
+- storing a boolean? that simple? customize the output of the search result
+  based on a boolean?
+- if so, how do we pass off a search result to a template conditionally,
+  such that we can save some space (jinja question)
+
+fix stuff that isn't mine:
+- improve the readme
+- fix the config.py config file options
+
+config:
+- enable user to specify list of organizations+repos
+    - not just one org/list of repos
+
+## Round 3
+
+organization:
+- mapping out how to change the schema... now, how do we streamline it?
+- how to organize files

issues_app.py

@@ -23,10 +23,8 @@ routes:
 """
 
 def get_items():
-    repo_list = ['2018-may-workshop',  
-                 '2018-june-workshop', 
-                 '2018-july-workshop'] 
-    repo_org = 'dcppc'
+    repo_list = app.config["REPOS"]
+    repo_org =app.config["REPO_ORG"]
     
     gh_access_token = os.environ['GITHUB_TOKEN']
 
@@ -65,12 +63,10 @@ def search():
     if fields == 'None':
         fields = None
 
-    directories = []
     search = Search(app.config["INDEX_DIR"])
     if not query:
         parsed_query = ""
         result = []
-        directories=get_directories()
 
     else:
         parsed_query, result = search.search(query.split(), fields=[fields])
@@ -78,7 +74,7 @@ def search():
 
     total = search.get_document_total_count()
 
-    return render_template('search.html', entries=result, query=query, parsed_query=parsed_query, fields=fields, last_searches=get_last_searches(), directories=directories, total=total)
+    return render_template('search.html', entries=result, query=query, parsed_query=parsed_query, fields=fields, last_searches=get_last_searches(), total=total)
 
 @app.route('/open')
 def open_file():
@@ -98,7 +94,6 @@ def update_index():
     else:
         UpdateIndexTask()
         flash("Updating index, check console output")
-    store_directories()
     return render_template("search.html", query="", fields="", last_searches=get_last_searches())
 
 
@@ -111,18 +106,7 @@ def get_last_searches():
     return contents
 
 
-def get_directories():
-    '''remove for issues'''
-    if os.path.exists(directories_file):
-        with codecs.open(directories_file, 'r', encoding='utf-8') as f:
-            directories = f.readlines()
-            f.close()
-    else:
-        directories = []
-    return directories
-
 def store_search(query, fields):
-    '''remove for issues'''
     if os.path.exists(last_searches_file):
         with codecs.open(last_searches_file, 'r', encoding='utf-8') as f:
             contents = f.readlines()
@@ -136,17 +120,6 @@ def store_search(query, fields):
     with codecs.open(last_searches_file, 'w', encoding='utf-8') as f:
         f.writelines(contents[:30])
 
-def store_directories():
-    '''remove for issues'''
-    directories = []
-    for root, dirnames, files in os.walk(app.config["MARKDOWN_FILES_DIR"]):
-        if dirnames:
-            for d in dirnames:
-                if os.path.isdir(os.path.join(root, d)):
-                    directories.append("%s\n" % d.lower())
-    directories = sorted(set(directories))
-    with codecs.open(app.config["INDEX_DIR"] + "/directories.txt", 'w', encoding='utf-8') as f:
-        f.writelines(directories)
 
 if __name__ == '__main__':
     app.run()

issues_search.py

@@ -17,6 +17,16 @@ from whoosh.analysis import StemmingAnalyzer
 """
 issues-search.py Flow:
 
+
+very high level description:
+    - zeroth step: create a search index
+    - first step: load a search index
+    - second step: call the search() method
+    - third step: update the search index
+
+
+
+
 program will:
    - create a Search object
    - call add_all_issues
@@ -88,6 +98,7 @@ class Search:
 
         schema = Schema(
                 url=ID(stored=True, unique=True),
+                is_comment=BOOLEAN(stored=True),
                 timestamp=STORED,
                 repo_name=TEXT(stored=True),
                 repo_url=ID(stored=True),
@@ -116,6 +127,7 @@ class Search:
 
         Schema:
         - url
+        - is_comment
         - timestamp
         - repo_name
         - repo_url
@@ -137,6 +149,7 @@ class Search:
         print("Indexing issue %s"%(issue.html_url))
         writer.add_document(
                 url = issue.html_url,
+                is_comment = False,
                 timestamp = issue.created_at,
                 repo_name = repo_name,
                 repo_url = repo_url,
@@ -155,6 +168,7 @@ class Search:
                 print(" > Indexing comment %s"%(comment.html_url))
                 writer.add_document(
                         url = comment.html_url,
+                        is_comment = True,
                         timestamp = comment.created_at,
                         repo_name = repo_name,
                         repo_url = repo_url,
@@ -168,6 +182,7 @@ class Search:
         return count
 
 
+    '''
     def add_all_issues(self, gh_access_token, list_of_repos, which_org, config, create_new_index=False):
         """
         Add all issues in a given github repo to the search index.
@@ -214,6 +229,8 @@ class Search:
 
         writer.commit()
         print("Done, added %d documents to the index" % c)
+    '''
+
 
 
     def update_index_incremental(self, gh_access_token, list_of_repos, which_org, config, create_new_index=False):
@@ -245,6 +262,12 @@ class Search:
         writer = self.ix.writer()
 
 
+
+
+        # fix this. the delete all in index
+        # is not occurring in right place.
+
+
         # Iterate over each repo
         for this_repo in list_of_repos:
 
@@ -307,6 +330,8 @@ class Search:
             sr.issue_title = r['issue_title']
             sr.issue_url = r['issue_url']
 
+            sr.is_comment = r['is_comment']
+
             sr.content = r['content']
             highlights = r.highlights('content')
             if not highlights:
@@ -360,5 +385,5 @@ if __name__ == "__main__":
     search.add_all_issues(gh_access_token,
                           repo_list,
                           repo_org,
-                         "/Users/charles/codes/markdown-search/config.py")
+                          "/Users/charles/codes/issues-search/config.py")
 

requirements.txt

@@ -0,0 +1,11 @@
+Flask>=0.12.1
+apiclient>=1.0.3
+oauth2client>=3.0.0
+httplib2>=0.10.3
+google-api-python-client
+mistune>=0.8
+whoosh>=2.7.4
+PyGithub>=1.39
+pypandoc>=1.4
+requests>=2.19
+pandoc>=1.0

templates/search.html

@@ -34,9 +34,16 @@
                 <div class="path"><a href='{{ url_for("open_file")}}?path={{e.path|urlencode}}&query={{query}}&fields={{fields}}'>{{e.path}}</a>score: {{'%d'  % e.score}}</div>
             -->
             <div class="url">
-                <a
-                    href='{{e.repo_url}}'>dcppc/{{e.repo_name}}</a>
-                    - <a href='{{e.issue_url}}'>{{e.issue_title}}</a> - <a href='{{e.url}}'>link</a><br />
+                {% if e.is_comment %}
+                    <b>Comment</b> <a href='{{e.url}}'>(comment link)</a>
+                    on issue <a href='{{e.issue_url}}'>{{e.issue_title}}</a>
+                    in repo <a href='{{e.repo_url}}'>dcppc/{{e.repo_name}}</a>
+                    <br />
+                {% else %}
+                    <b>Issue</b> <a href='{{e.issue_url}}'>{{e.issue_title}}</a>
+                    in repo <a href='{{e.repo_url}}'>dcppc/{{e.repo_name}}</a>
+                    <br />
+                {% endif %}
                 score: {{'%d'  % e.score}}
             </div>
             <div class="markdown-body">{{ e.content_highlight|safe}}</div>