Merge branch 'use-datetime' into merge-datetime-into-disqus

* use-datetime:
  extract date and time from email threads pages
  add groups and tags to schema; update how we determine timestamps; handle exceptions when we add the document to the writer, rather than elsewhere
  move where exception is caught (exception was also incorrect.)
  switched created_time, modified_time, indexed_time over to DATETIME. added DateParserPlugin to query QueryParser. added time fields to those being searched by default. tests do not seem to be working.

centillion_search.py

@@ -24,6 +24,8 @@ import dateutil.parser
 from whoosh import query
 from whoosh.qparser import MultifieldParser, QueryParser
 from whoosh.analysis import StemmingAnalyzer, LowercaseFilter, StopFilter
+from whoosh.qparser.dateparse import DateParserPlugin
+from whoosh import fields, index
 
 
 """
@@ -195,30 +197,38 @@ 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)
         )
 
 
@@ -258,24 +268,32 @@ 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:
@@ -329,7 +347,7 @@ 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
@@ -357,24 +375,33 @@ 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']))
+
 
 
 
@@ -408,31 +435,36 @@ 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))
 
 
 
@@ -462,7 +494,8 @@ 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))
@@ -491,24 +524,31 @@ 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))
@@ -516,24 +556,29 @@ 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))
 
 
 
@@ -547,28 +592,42 @@ class Search:
         Use a Groups.io email thread record to add 
         an email thread 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']))
 
 
     # ------------------------------
@@ -581,28 +640,33 @@ class Search:
         to add a disqus comment thread to the
         search index.
         """
-        indexed_time = clean_timestamp(datetime.now())
+        indexed_time = datetime.now()
+
+        # created_time is already a timestamp
 
         # Now create the actual search index record
-        writer.add_document(
+        try:
-                id = d['id'],
+            writer.add_document(
-                kind = 'disqus',
+                    id = d['id'],
-                created_time = d['created_time'],
+                    kind = 'disqus',
-                modified_time = '',
+                    created_time = d['created_time'],
-                indexed_time = indexed_time,
+                    modified_time = None,
-                title = d['title'],
+                    indexed_time = indexed_time,
-                url = d['link'],
+                    title = d['title'],
-                mimetype='',
+                    url = d['link'],
-                owner_email='',
+                    mimetype='',
-                owner_name='',
+                    owner_email='',
-                repo_name = '',
+                    owner_name='',
-                repo_url = '',
+                    repo_name = '',
-                github_user = '',
+                    repo_url = '',
-                issue_title = '',
+                    github_user = '',
-                issue_url = '',
+                    issue_title = '',
-                content = d['content']
+                    issue_url = '',
-        )
+                    content = d['content']
-
+            )
+        except ValueError as e:
+            print(repr(e))
+            print(" > XXXXXX Failed to index Disqus comment thread \"%s\""%(d['title']))
 
 
 
@@ -680,10 +744,10 @@ 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()
@@ -691,34 +755,41 @@ 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])
@@ -1176,7 +1247,7 @@ 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=='disqus':
             item_keys = ['title','created_time','url']
         elif doctype=='ghfile':
@@ -1195,11 +1266,7 @@ 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
@@ -1212,13 +1279,16 @@ 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,
                                     termclass=query.Variations
-                ).parse(query_string)
+                )
+                query.add_plugin(DateParserPlugin(free=True))
+                query = query.parse(query_string)
             elif len(fields) == 1 and fields[0] == "filename":
                 pass
             elif len(fields) == 2:
@@ -1226,9 +1296,12 @@ 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")

disqus_util.py

@@ -1,6 +1,7 @@
 import os, re
 import requests
 import json
+import dateutil.parser
 
 from pprint import pprint
 
@@ -123,7 +124,7 @@ class DisqusCrawler(object):
                         # We need to make this value a dictionary
                         thread_info = dict(
                                 id = response['id'],
-                                created_time = response['createdAt'],
+                                created_time = dateutil.parser.parse(response['createdAt']),
                                 title = response['title'],
                                 forum = response['forum'],
                                 link = clean_link,

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