Merge pull request #90 from dcppc/add-dates-and-subgroups-to-emails

Add dates and subgroups to emails

centillion_search.py

@@ -21,6 +21,8 @@ import dateutil.parser
 
 from whoosh.qparser import MultifieldParser, QueryParser
 from whoosh.analysis import StemmingAnalyzer
+from whoosh.qparser.dateparse import DateParserPlugin
+from whoosh import fields, index
 
 
 """
@@ -180,30 +182,38 @@ class Search:
         # is defined.
 
         schema = Schema(
-                id = ID(stored=True, unique=True),
+                id = fields.ID(stored=True, unique=True),
-                kind = ID(stored=True),
+                kind = fields.ID(stored=True),
 
-                created_time = ID(stored=True),
+                created_time = fields.DATETIME(stored=True),
-                modified_time = ID(stored=True),
+                modified_time = fields.DATETIME(stored=True),
-                indexed_time = ID(stored=True),
+                indexed_time = fields.DATETIME(stored=True),
                 
-                title = TEXT(stored=True, field_boost=100.0),
+                title = fields.TEXT(stored=True, field_boost=100.0),
-                url = ID(stored=True, unique=True),
-                
-                mimetype=ID(stored=True),
-                owner_email=ID(stored=True),
-                owner_name=TEXT(stored=True),
-                
-                repo_name=TEXT(stored=True),
-                repo_url=ID(stored=True),
 
-                github_user=TEXT(stored=True),
+                url = fields.ID(stored=True),
+                
+                mimetype = fields.TEXT(stored=True),
+
+                owner_email = fields.ID(stored=True),
+                owner_name = fields.TEXT(stored=True),
+
+                # mainly for email threads, groups.io, hypothesis
+                group = fields.ID(stored=True),
+
+                repo_name = fields.TEXT(stored=True),
+                repo_url = fields.ID(stored=True),
+                github_user = fields.TEXT(stored=True),
+
+                tags = fields.KEYWORD(commas=True,
+                                      stored=True,
+                                      lowercase=True),
 
                 # comments only
-                issue_title=TEXT(stored=True, field_boost=100.0),
+                issue_title = fields.TEXT(stored=True, field_boost=100.0),
-                issue_url=ID(stored=True),
+                issue_url = fields.ID(stored=True),
                 
-                content=TEXT(stored=True, analyzer=stemming_analyzer)
+                content = fields.TEXT(stored=True, analyzer=stemming_analyzer)
         )
 
 
@@ -243,24 +253,32 @@ class Search:
             writer.delete_by_term('id',item['id'])
 
             # Index a plain google drive file
-            writer.add_document(
+            created_time = dateutil.parser.parse(item['createdTime'])
-                    id = item['id'],
+            modified_time = dateutil.parser.parse(item['modifiedTime'])
-                    kind = 'gdoc',
+            indexed_time = datetime.now().replace(microsecond=0)
-                    created_time = item['createdTime'],
+            try:
-                    modified_time = item['modifiedTime'],
+                writer.add_document(
-                    indexed_time = datetime.now().replace(microsecond=0).isoformat(),
+                        id = item['id'],
-                    title = item['name'],
+                        kind = 'gdoc',
-                    url = item['webViewLink'],
+                        created_time = created_time,
-                    mimetype = mimetype,
+                        modified_time = modified_time,
-                    owner_email = item['owners'][0]['emailAddress'],
+                        indexed_time = indexed_time,
-                    owner_name = item['owners'][0]['displayName'],
+                        title = item['name'],
-                    repo_name='',
+                        url = item['webViewLink'],
-                    repo_url='',
+                        mimetype = mimetype,
-                    github_user='',
+                        owner_email = item['owners'][0]['emailAddress'],
-                    issue_title='',
+                        owner_name = item['owners'][0]['displayName'],
-                    issue_url='',
+                        group='',
-                    content = content
+                        repo_name='',
-            )
+                        repo_url='',
+                        github_user='',
+                        issue_title='',
+                        issue_url='',
+                        content = content
+                )
+            except ValueError as e:
+                print(repr(e))
+                print(" > XXXXXX Failed to index Google Drive file \"%s\""%(item['name']))
 
 
         else:
@@ -314,7 +332,7 @@ class Search:
                 )
                 assert output == ""
             except RuntimeError:
-                print(" > XXXXXX Failed to index document \"%s\""%(item['name']))
+                print(" > XXXXXX Failed to index Google Drive document \"%s\""%(item['name']))
 
 
             # If export was successful, read contents of markdown
@@ -342,24 +360,33 @@ class Search:
             else:
                 print(" > Creating a new record")
 
-            writer.add_document(
+            try:
-                    id = item['id'],
+                created_time = dateutil.parser.parse(item['createdTime'])
-                    kind = 'gdoc',
+                modified_time = dateutil.parser.parse(item['modifiedTime'])
-                    created_time = item['createdTime'],
+                indexed_time = datetime.now()
-                    modified_time = item['modifiedTime'],
+                writer.add_document(
-                    indexed_time = datetime.now().replace(microsecond=0).isoformat(),
+                        id = item['id'],
-                    title = item['name'],
+                        kind = 'gdoc',
-                    url = item['webViewLink'],
+                        created_time = created_time,
-                    mimetype = mimetype,
+                        modified_time = modified_time,
-                    owner_email = item['owners'][0]['emailAddress'],
+                        indexed_time = indexed_time,
-                    owner_name = item['owners'][0]['displayName'],
+                        title = item['name'],
-                    repo_name='',
+                        url = item['webViewLink'],
-                    repo_url='',
+                        mimetype = mimetype,
-                    github_user='',
+                        owner_email = item['owners'][0]['emailAddress'],
-                    issue_title='',
+                        owner_name = item['owners'][0]['displayName'],
-                    issue_url='',
+                        group='',
-                    content = content
+                        repo_name='',
-            )
+                        repo_url='',
+                        github_user='',
+                        issue_title='',
+                        issue_url='',
+                        content = content
+                )
+            except ValueError as e:
+                print(repr(e))
+                print(" > XXXXXX Failed to index Google Drive file \"%s\""%(item['name']))
+
 
 
 
@@ -393,31 +420,36 @@ class Search:
                 issue_comment_content += comment.body.rstrip()
                 issue_comment_content += "\n"
 
-        # Now create the actual search index record
+        # Now create the actual search index record.
-        created_time = clean_timestamp(issue.created_at)
-        modified_time = clean_timestamp(issue.updated_at)
-        indexed_time = clean_timestamp(datetime.now())
-
         # Add one document per issue thread,
         # containing entire text of thread.
-        writer.add_document(
+
-                id = issue.html_url,
+        created_time = issue.created_at
-                kind = 'issue',
+        modified_time = issue.updated_at
-                created_time = created_time,
+        indexed_time = datetime.now()
-                modified_time = modified_time,
+        try:
-                indexed_time = indexed_time,
+            writer.add_document(
-                title = issue.title,
+                    id = issue.html_url,
-                url = issue.html_url,
+                    kind = 'issue',
-                mimetype='',
+                    created_time = created_time,
-                owner_email='',
+                    modified_time = modified_time,
-                owner_name='',
+                    indexed_time = indexed_time,
-                repo_name = repo_name,
+                    title = issue.title,
-                repo_url = repo_url,
+                    url = issue.html_url,
-                github_user = issue.user.login,
+                    mimetype='',
-                issue_title = issue.title,
+                    owner_email='',
-                issue_url = issue.html_url,
+                    owner_name='',
-                content = issue_comment_content
+                    group='',
-        )
+                    repo_name = repo_name,
+                    repo_url = repo_url,
+                    github_user = issue.user.login,
+                    issue_title = issue.title,
+                    issue_url = issue.html_url,
+                    content = issue_comment_content
+            )
+        except ValueError as e:
+            print(repr(e))
+            print(" > XXXXXX Failed to index Github issue \"%s\""%(issue.title))
 
 
 
@@ -447,7 +479,8 @@ class Search:
             print(" > XXXXXXXX Failed to find file info.")
             return
 
-        indexed_time = clean_timestamp(datetime.now())
+
+        indexed_time = datetime.now()
 
         if fext in MARKDOWN_EXTS:
             print("Indexing markdown doc %s from repo %s"%(fname,repo_name))
@@ -476,24 +509,31 @@ class Search:
             usable_url = "https://github.com/%s/blob/master/%s"%(repo_name, fpath)
 
             # Now create the actual search index record
-            writer.add_document(
+            try:
-                    id = fsha,
+                writer.add_document(
-                    kind = 'markdown',
+                        id = fsha,
-                    created_time = '',
+                        kind = 'markdown',
-                    modified_time = '',
+                        created_time = None,
-                    indexed_time = indexed_time,
+                        modified_time = None,
-                    title = fname,
+                        indexed_time = indexed_time,
-                    url = usable_url,
+                        title = fname,
-                    mimetype='',
+                        url = usable_url,
-                    owner_email='',
+                        mimetype='',
-                    owner_name='',
+                        owner_email='',
-                    repo_name = repo_name,
+                        owner_name='',
-                    repo_url = repo_url,
+                        group='',
-                    github_user = '',
+                        repo_name = repo_name,
-                    issue_title = '',
+                        repo_url = repo_url,
-                    issue_url = '',
+                        github_user = '',
-                    content = content
+                        issue_title = '',
-            )
+                        issue_url = '',
+                        content = content
+                )
+            except ValueError as e:
+                print(repr(e))
+                print(" > XXXXXX Failed to index Github markdown file \"%s\""%(fname))
+
+
 
         else:
             print("Indexing github file %s from repo %s"%(fname,repo_name))
@@ -501,24 +541,29 @@ class Search:
             key = fname+"_"+fsha
 
             # Now create the actual search index record
-            writer.add_document(
+            try:
-                    id = key,
+                writer.add_document(
-                    kind = 'ghfile',
+                        id = key,
-                    created_time = '',
+                        kind = 'ghfile',
-                    modified_time = '',
+                        created_time = None,
-                    indexed_time = indexed_time,
+                        modified_time = None,
-                    title = fname,
+                        indexed_time = indexed_time,
-                    url = repo_url,
+                        title = fname,
-                    mimetype='',
+                        url = repo_url,
-                    owner_email='',
+                        mimetype='',
-                    owner_name='',
+                        owner_email='',
-                    repo_name = repo_name,
+                        owner_name='',
-                    repo_url = repo_url,
+                        group='',
-                    github_user = '',
+                        repo_name = repo_name,
-                    issue_title = '',
+                        repo_url = repo_url,
-                    issue_url = '',
+                        github_user = '',
-                    content = ''
+                        issue_title = '',
-            )
+                        issue_url = '',
+                        content = ''
+                )
+            except ValueError as e:
+                print(repr(e))
+                print(" > XXXXXX Failed to index Github file \"%s\""%(fname))
 
 
 
@@ -532,28 +577,42 @@ class Search:
         Use a Github file API record to add a filename
         to the search index.
         """
-        indexed_time = clean_timestamp(datetime.now())
+        if 'created_time' in d.keys() and d['created_time'] is not None:
+            created_time = d['created_time']
+        else:
+            created_time = None
+
+        if 'modified_time' in d.keys() and d['modified_time'] is not None:
+            modified_time = d['modified_time']
+        else:
+            modified_time = None
+
+        indexed_time = datetime.now()
 
         # Now create the actual search index record
-        writer.add_document(
+        try:
-                id = d['permalink'],
+            writer.add_document(
-                kind = 'emailthread',
+                    id = d['permalink'],
-                created_time = '',
+                    kind = 'emailthread',
-                modified_time = '',
+                    created_time = created_time,
-                indexed_time = indexed_time,
+                    modified_time = modified_time,
-                title = d['subject'],
+                    indexed_time = indexed_time,
-                url = d['permalink'],
+                    title = d['subject'],
-                mimetype='',
+                    url = d['permalink'],
-                owner_email='',
+                    mimetype='',
-                owner_name=d['original_sender'],
+                    owner_email='',
-                repo_name = '',
+                    owner_name=d['original_sender'],
-                repo_url = '',
+                    group=d['subgroup'],
-                github_user = '',
+                    repo_name = '',
-                issue_title = '',
+                    repo_url = '',
-                issue_url = '',
+                    github_user = '',
-                content = d['content']
+                    issue_title = '',
-        )
+                    issue_url = '',
-
+                    content = d['content']
+            )
+        except ValueError as e:
+            print(repr(e))
+            print(" > XXXXXX Failed to index Groups.io thread \"%s\""%(d['subject']))
 
 
 
@@ -631,10 +690,10 @@ class Search:
                 full_items[f['id']] = f
             
             ## Shorter:
-            #break
+            break
-            # Longer:
+            ## Longer:
-            if nextPageToken is None:
+            #if nextPageToken is None:
-                break
+            #    break
 
 
         writer = self.ix.writer()
@@ -642,34 +701,41 @@ class Search:
         temp_dir = tempfile.mkdtemp(dir=os.getcwd())
         print("Temporary directory: %s"%(temp_dir))
 
+        try:
+
+            # Drop any id in indexed_ids
+            # not in remote_ids
+            drop_ids = indexed_ids - remote_ids
+            for drop_id in drop_ids:
+                writer.delete_by_term('id',drop_id)
 
 
-        # Drop any id in indexed_ids
+            # Update any id in indexed_ids
-        # not in remote_ids
+            # and in remote_ids
-        drop_ids = indexed_ids - remote_ids
+            update_ids = indexed_ids & remote_ids
-        for drop_id in drop_ids:
+            for update_id in update_ids:
-            writer.delete_by_term('id',drop_id)
+                # cop out
+                writer.delete_by_term('id',update_id)
+                item = full_items[update_id]
+                self.add_drive_file(writer, item, temp_dir, config, update=True)
+                count += 1
 
 
-        # Update any id in indexed_ids
+            # Add any id not in indexed_ids
-        # and in remote_ids
+            # and in remote_ids
-        update_ids = indexed_ids & remote_ids
+            add_ids = remote_ids - indexed_ids
-        for update_id in update_ids:
+            for add_id in add_ids:
-            # cop out
+                item = full_items[add_id]
-            writer.delete_by_term('id',update_id)
+                self.add_drive_file(writer, item, temp_dir, config, update=False)
-            item = full_items[update_id]
+                count += 1
-            self.add_drive_file(writer, item, temp_dir, config, update=True)
-            count += 1
-
-
-        # Add any id not in indexed_ids
-        # and in remote_ids
-        add_ids = remote_ids - indexed_ids
-        for add_id in add_ids:
-            item = full_items[add_id]
-            self.add_drive_file(writer, item, temp_dir, config, update=False)
-            count += 1
 
+        except Exception as e:
+            print("ERROR: While adding Google Drive files to search index")
+            print("-"*40)
+            print(repr(e))
+            print("-"*40)
+            print("Continuing...")
+            pass
 
         print("Cleaning temporary directory: %s"%(temp_dir))
         subprocess.call(['rm','-fr',temp_dir])
@@ -1074,7 +1140,7 @@ class Search:
         elif doctype=='issue':
             item_keys = ['title','repo_name','repo_url','url','created_time','modified_time']
         elif doctype=='emailthread':
-            item_keys = ['title','owner_name','url']
+            item_keys = ['title','owner_name','url','created_time','modified_time']
         elif doctype=='ghfile':
             item_keys = ['title','repo_name','repo_url','url']
         elif doctype=='markdown':
@@ -1091,11 +1157,7 @@ class Search:
             for r in results:
                 d = {}
                 for k in item_keys:
-                    if k=='created_time' or k=='modified_time':
+                    d[k] = r[k]
-                        #d[k] = r[k]
-                        d[k] = dateutil.parser.parse(r[k]).strftime("%Y-%m-%d")
-                    else:
-                        d[k] = r[k]
                 json_results.append(d)
 
         return json_results
@@ -1108,7 +1170,9 @@ class Search:
             query_string = " ".join(query_list)
             query = None
             if ":" in query_string:
-                query = QueryParser("content", self.schema).parse(query_string)
+                query = QueryParser("content", self.schema)
+                query.add_plugin(DateParserPlugin(free=True))
+                query = query.parse(query_string)
             elif len(fields) == 1 and fields[0] == "filename":
                 pass
             elif len(fields) == 2:
@@ -1116,9 +1180,12 @@ class Search:
             else:
                 # If the user does not specify a field,
                 # these are the fields that are actually searched
-                fields = ['title', 'content','owner_name','owner_email','url']
+                fields = ['title', 'content','owner_name','owner_email','url','created_date','modified_date']
             if not query:
-                query = MultifieldParser(fields, schema=self.ix.schema).parse(query_string)
+                query = MultifieldParser(fields, schema=self.ix.schema)
+                query.add_plugin(DateParserPlugin(free=True))
+                query = query.parse(query_string)
+                #query = MultifieldParser(fields, schema=self.ix.schema).parse(query_string) 
             parsed_query = "%s" % query
             print("query: %s" % parsed_query)
             results = searcher.search(query, terms=False, scored=True, groupedby="kind")

groupsio_util.py

@@ -1,5 +1,7 @@
 import requests, os, re
 from bs4 import BeautifulSoup
+import dateutil.parser
+import datetime
 
 class GroupsIOException(Exception):
     pass
@@ -64,7 +66,7 @@ class GroupsIOArchivesCrawler(object):
 
             ## Short circuit
             ## for debugging purposes
-            #break
+            break
 
         return subgroups
 
@@ -251,7 +253,7 @@ class GroupsIOArchivesCrawler(object):
             subject = soup.find('title').text
 
             # Extract information for the schema:
-            # - permalink for thread (done)
+            # - permalink for thread (done above)
             # - subject/title (done)
             # - original sender email/name (done)
             # - content (done)
@@ -266,11 +268,35 @@ class GroupsIOArchivesCrawler(object):
                     pass
                 else:
                     # found an email!
-                    # this is a maze, thanks groups.io
+                    # this is a maze, not amazing.
+                    # thanks groups.io!
                     td = tr.find('td')
-                    divrow = td.find('div',{'class':'row'}).find('div',{'class':'pull-left'})
+
+                    sender_divrow = td.find('div',{'class':'row'})
+                    sender_divrow = sender_divrow.find('div',{'class':'pull-left'})
                     if (i+1)==1:
-                        original_sender = divrow.text.strip()
+                        original_sender = sender_divrow.text.strip()
+
+                    date_divrow = td.find('div',{'class':'row'})
+                    date_divrow = date_divrow.find('div',{'class':'pull-right'})
+                    date_divrow = date_divrow.find('font',{'class':'text-muted'})
+                    date_divrow = date_divrow.find('script').text
+                    try:
+                        time_seconds = re.search(' [0-9]{1,} ',date_divrow).group(0)
+                        time_seconds = time_seconds.strip()
+                        # Thanks groups.io for the weird date formatting
+                        time_seconds = time_seconds[:10]
+                        mmicro_seconds = time_seconds[10:]
+                        if (i+1)==1:
+                            created_time  = datetime.datetime.utcfromtimestamp(int(time_seconds))
+                            modified_time = datetime.datetime.utcfromtimestamp(int(time_seconds))
+                        else:
+                            modified_time = datetime.datetime.utcfromtimestamp(int(time_seconds))
+
+                    except AttributeError:
+                        created_time = None
+                        modified_time = None
+
                     for div in td.find_all('div'):
                         if div.has_attr('id'):
 
@@ -299,7 +325,10 @@ class GroupsIOArchivesCrawler(object):
 
             thread = {
                     'permalink' : permalink,
+                    'created_time' : created_time,
+                    'modified_time' : modified_time,
                     'subject' : subject,
+                    'subgroup' : subgroup_name,
                     'original_sender' : original_sender,
                     'content' : full_content
             }
@@ -324,11 +353,13 @@ class GroupsIOArchivesCrawler(object):
 
         results = []
         for row in rows:
-            # We don't care about anything except title and ugly link
+            # This is where we extract
+            # a list of thread titles 
+            # and corresponding links.
             subject = row.find('span',{'class':'subject'})
             title = subject.get_text()
             link = row.find('a')['href']
-            #print(title)
+
             results.append((title,link))
 
         return results

quality/Readme.md

@@ -1,181 +0,0 @@
-# Centillion Quality Engineering Plan
-
-Table of Contents
--------
-
-*   [Centillion Quality Engineering Plan](#centillion-quality-engineering-plan)
-    *   [Summary](#summary)
-    *   [Tracking Bugs and Issues](#tracking-bugs-and-issues)
-    *   [Branches, Versioning, and Git Workflow](#branches-versioning-and-git-workflow)
-    *   [Communication and Mailing Lists](#communication-and-mailing-lists)
-    *   [Checklists](#checklists)
-    *   [Documentation](#documentation)
-    *   [Configuration Management Tools](#configuration-management-tools)
-    *   [Tests](#tests)
-    *   [Code Reviews](#code-reviews)
-    *   [Formal Release Process](#formal-release-process)
-    *   [Continual Process Improvement](#continual-process-improvement)
-
-Summary
--------
-
-This document contains a quality engineering plan for centillion, the
-Data Commons search engine.
-
-Tracking Bugs and Issues
-------------------------
-
-We utilize the [issues
-section](https://github.com/dcppc/centillion/issues) of the centillion
-repository to keep track of bugs and feature requests.
-
-Branches, Versioning, and Git Workflow
---------------------------------------
-
-All code is kept under version control in the
-[dcppc/centillion](https://github.com/dcppc/centillion) Github
-repository.
-
-**Primary Git Branches:**
-
-We utillize a git branch pattern that has two primary branches: a
-development branch and a stable branch.
-
--   The primary **development branch** is `dcppc` and is actively
-    developed and deployed to <https://betasearch.nihdatacommons.us>.
-
--   The primary **stable branch** is `releases/v1` and is stable and
-    deployed to <https://search.nihdatacommons.us>.
-
-All tagged versions of Centillion exist on the stable branch. Only
-tagged versions of centillion are run on
-<https://search.nihdatacommons.us>.
-
-**Other Branches:**
-
-Features are developed by creating a new branch from `dcppc`, working on
-the feature, and opening a pull request. When the pull request is
-approved, it can be merged into the `dcppc` branch.
-
-When features have accumulated and a new version is ready, a new
-pre-release branch will be made to prepare for a new release. When the
-pre-release branch is ready, it is merged into the stable branch in a
-single merge commit and a new version of centillion is tagged. The new
-version is deployed on <https://search.nihdatacommons.us>.
-
-Commits to fix bugs (hotfixes) may need to be applied to both the stable
-and development branches. In this case, a hotfix branch should be
-created from the head commit of the stable branch, and the appropriate
-changes should be made on the branch. A pull request should be opened to
-merge the hotfix into the release branch. A second pull request should
-be opened to merge the hotfix into the development branch. Once the
-hotfix is merged into the stable branch, a new version should be tagged.
-
-Communication and Mailing Lists
--------------------------------
-
--   No mailing list currently exists for centillion.
-
--   Github issues are the primary form of communication about
-    development of centillion. This is the best method for communicating
-    bug reports or detailed information.
-
--   The Send Feedback button on the centillion page is the primary way
-    of getting quick feedback from users about the search engine.
-
--   The [\#centillion](https://nih-dcppc.slack.com/messages/CCD64QD6G)
-    Slack channel in the DCPPC slack workspace is the best place for
-    conversations about centillion (providing feedback, answering quick
-    questions, etc.)
-
-Checklists
-----------
-
-We plan to utilize the Wiki feature of the Github repository to develop
-checlists:
-
--   Checklist for releases
--   Checklist for deployment of https://search.nihdatacommons.us nginx
-    etc.
-
-Documentation
--------------
-
-The documentation is a pile of markdown documents, turned into a static
-site using mkdocs.
-
-Configuration Management Tools
-------------------------------
-
-We do not currently utilize any configuration management software,
-because centillion is not packaged as an importable Python module.
-
-Packaging centillion is a future goal that is closely related to the
-need to improve and modularize the internal search schema/document type
-abstraction. These improvements would allow the types of collections
-being indexed to be separated from "core centillion", and core
-centillion would be packaged.
-
-Tests
------
-
-See (ref) for a full test plan with more detail.
-
-Summary of test plan:
-
--   Implement tests for the four major pages/components
-    -   Login/authentication
-    -   Search
-    -   Master List
-    -   Control Panel
--   Test authentication with two bot accounts (yammasnake and florence
-    python)
-
--   Separate frontend and backend tests
-
--   Add a test flag in the flask config file to change the backend
-    behavior of the server
-
-Code Reviews
-------------
-
-CI tests will be implemented for all pull requests.
-
-Pull requests to the **stable branch** have the following checks in
-place:
-
--   PRs to the stable branch require at least 1 PR review
--   PRs to the stable branch must pass CI tests
-
-Pull requests to the **development branch** have the following checks in
-place:
-
--   PRs to the development branch must pass CI tests
-
-Formal Release Process
-----------------------
-
-In order to ensure a stable, consistent product, we utilize the
-branching pattern described above to implement new features in the
-development branch and test them out on
-<https://betasearch.nihdatacommons.us>.
-
-Once features and bug fixes have been tested and reviewed internally,
-they are ready to be deployed. A new pre-release branch is created from
-the development branch. The pre-release branch has a feature freeze in
-place. Changes are made to the pre-release branch to prepare it for the
-next major version release.
-
-When the pre-release branch is finished, it is merged into the stable
-branch. The head commit of the stable version is tagged with the lastest
-release number.
-
-Finally, the new version is deployed on
-<https://search.nihdatacommons.us>.
-
-Continual Process Improvement
------------------------------
-
-We will utilize the centillion wiki on Github to keep track of repeated
-processes and opportunities for improvement. Feedback and ideas for
-process improvement can also be submitted via Github issues.

tests/Readme.md

@@ -1,196 +0,0 @@
-Centillion Tests
-================
-
-Table of Contents
-------------------
-
-*   [Centillion Tests](#centillion-tests)
-    *   [Test Plan](#test-plan)
-        *   [Local Tests](#local-tests)
-        *   [Short Tests](#short-tests)
-        *   [Long Tests](#long-tests)
-    *   [Credentials](#credentials)
-    *   [Detailed Description of Tests](#detailed-description-of-tests)
-        *   [Authentication Layer Tests](#authentication-layer-tests)
-        *   [Search Function Tests](#search-function-tests)
-        *   [Master List Endpoint Tests](#master-list-endpoint-tests)
-        *   [Control Panel Endpoint Tests](#control-panel-endpoint-tests)
-        *   [Continuous Integration Plan](#continuous-integration-plan)
-    *   [Procedure/Checklist](#procedurechecklist)
-
-
-Test Plan
----------
-
-Related: <https://github.com/dcppc/centillion/issues/82>
-
-The test suite for centillion needs to check each of the major
-components of centillion, as well as check the authentication mechanism
-using multiple login credentials.
-
-We implement the following checks:
-
-1.  Check authentication mechanism(s) (yamasnake and florence python)
-
-2.  Check search function
-
-3.  Check master list endpoint
-
-4.  Check control panel endpoint
-
-5.  Check update search index endpoints
-
-The tests are written such that the back end and front end are tested
-separately.
-
-We need also need different tiers of tests, so we don't max out API
-calls by making lots of commits to multiple PRs.
-
-We have three tiers of tests: \* Local tests - quick tests for CI, no
-API calls \* Short tests - tests using dummy API accounts \* Long tests
-- tests using DCPPC API accounts
-
-### Local Tests
-
-Local tests can be run locally without any interaction with APIs. These
-will still utilize centillion's search schema, but will load the search
-index with fake documents rather than fetching them from an API.
-
-Uncle Archie, which runs CI tests, runs local tests only (unless you
-request it to run short test or long test.)
-
-### Short Tests
-
-Short tests utilize credentials for bot accounts that have intentionally
-been set up to have a "known" corpus of test documents. These would
-provide unit-style tests for centillion - are the mechanics of indexing
-a particular type of document from a particular API working?
-
-### Long Tests
-
-Long tests are indexing the real deal, utilizing the credentials used in
-the final production centillion. This test takes longer but is more
-likely to catch corner cases specific to the DCPPC documents.
-
-Credentials
------------
-
-Running tests on centillion requires multiple sets of credentials. Let's
-lay out what is needed:
-
--   The Flask app requires a token/secret token API key pair to allow
-    users to authenticate through Github and confirm they are members of
-    the DCPPC organization. This OAuth application is owned by Charles
-    Reid (@charlesreid1).
-
--   The search index needs a Github access token so that it can
-    interface with the Github API to index files and issues. This access
-    token is specified (along with other secrets) in the Flask
-    configuration file. The access key comes from Florence Python
-    (@fp9695253).
-
--   The search index also requires a Google Drive API access token. This
-    must be an access token for a user who has authenticated with the
-    Centillion Google Drive OAuth application. This access token comes
-    from <mailroom@nihdatacommons.com>.
-
--   The search index requires API credentials for any other APIs
-    associated with other document collections (Groups.io, Hypothesis,
-    Disqus).
-
--   The backend test requires the credentials provided to Flask.
-
--   The frontend test (Selenium) needs two Github username/passwords:
-    one for Florence Python (@fp9695253) and one for Yamma Snake
-    (@yammasnake). These are required to simulate the user
-    authenticating with Github through the browser.
-    -   The frontend test credentials are a special case.
-    -   The frontend tests expect credentials to come from environment
-        variables.
-    -   These environment variables get passed in at test time.
-    -   Tests are all run on [Uncle
-        Archie](https://github.com/dcppc/uncle-archie).
-    -   Uncle Archie already has to protect a confidential config file
-        containing Github credentials, so add additional credentials for
-        frontend tests there.
-    -   Logical separation: these credentials are not needed to
-        *operate* centillion, these credentials are needed to *test*
-        centillion
-    -   Uncle Archie already requires github credentials, already
-        protects sensitive info.
-    -   Google Drive requiring its own credentials file on disk is a
-        pain.
-
-In summary: tests use the `config_flask.py` and `config_centillion.py`
-files to provide it with the API keys it needs and to instruct it on
-what to index. The credentials and config files will control what the
-search index will actually index. The Uncle Archie CI tester config file
-contains the credentials needed to run frontend tests (check the
-login/authentication layer).
-
-Detailed Description of Tests
------------------------------
-
-### Authentication Layer Tests
-
-Frontend tests run as Florence Python:
-
--   Can we log in via github and reach centillion
--   Can we reach the control panel
-
-Frontend tests run as Yamma Snake (DCPPC member):
-
--   Can we log in via github and reach centillion
--   Can we reach the control panel
-
-### Search Function Tests
-
-Frontend tests:
-
--   Can we enter something into search box and submit
--   Can we sort the results
--   Do the results look okay
-
-Backend tests:
-
--   Load the search index and run a query using whoosh API
-
-### Master List Endpoint Tests
-
-Frontend tests:
-
--   Can we get to the master list page
--   Can we sort the results
--   Do the results look okay
-
-Backend tests:
-
--   Check the output of the `/list` API endpoint
-
-### Control Panel Endpoint Tests
-
-Frontend tests:
-
--   Can we get to the control panel page
--   Can we click the button to trigger an indexing event
-
-Backend tests:
-
--   Trigger a re-index of the search index from the backend.
-
-### Continuous Integration Plan
-
-Tests are automatically run using Uncle Archie for continuous
-integration and deployment.
-
-Procedure/Checklist
--------------------
-
-Pre-release procedure:
-
--   prepare to run all test
-
--   run short tests
--   deploy to beta
--   run long tests
--   test out