From 5fd0aab76caef8aaf7be77843b9c9260f22dfbb7 Mon Sep 17 00:00:00 2001
From: Jules Laplace <julescarbon@gmail.com>
Date: Sat, 12 Jan 2019 18:37:43 +0100
Subject: add prefix to name search

---
 megapixels/app/models/sql_factory.py | 21 +++++++----
 megapixels/app/server/api.py         | 70 ++++++++++++++++++++++++------------
 megapixels/app/server/create.py      | 15 ++++++++
 3 files changed, 77 insertions(+), 29 deletions(-)

(limited to 'megapixels/app')

diff --git a/megapixels/app/models/sql_factory.py b/megapixels/app/models/sql_factory.py
index eb91fb37..25c7e784 100644
--- a/megapixels/app/models/sql_factory.py
+++ b/megapixels/app/models/sql_factory.py
@@ -3,7 +3,7 @@ import glob
 import time
 import pandas as pd
 
-from sqlalchemy import create_engine, Table, Column, String, Integer, DateTime, Float
+from sqlalchemy import create_engine, Table, Column, String, Integer, DateTime, Float, func
 from sqlalchemy.orm import sessionmaker
 from sqlalchemy.ext.declarative import declarative_base
 
@@ -112,7 +112,15 @@ class SqlDataset:
     Find an identity by name.
     """
     table = self.get_table('identity')
-    identity_list = table.query.filter(table.fullname.like(q)).order_by(table.fullname.desc()).limit(10)
+    identity_list = table.query.filter(table.fullname.ilike(q)).order_by(table.fullname.desc()).limit(15)
+    return identity_list
+
+  def search_description(self, q):
+    """
+    Find an identity by description.
+    """
+    table = self.get_table('identity')
+    identity_list = table.query.filter(table.description.ilike(q)).order_by(table.description.desc()).limit(15)
     return identity_list
 
   def get_file_records_for_identities(self, identity_list):
@@ -123,10 +131,11 @@ class SqlDataset:
     file_record_table = self.get_table('file_record')
     for row in identity_list:
       file_record = file_record_table.query.filter(file_record_table.identity_id == row.id).first()
-      identities.append({
-        'file_record': file_record.toJSON(),
-        'identity': row.toJSON(),
-      })
+      if file_record:
+        identities.append({
+          'file_record': file_record.toJSON(),
+          'identity': row.toJSON(),
+        })
     return identities
 
   def select(self, table, id):
diff --git a/megapixels/app/server/api.py b/megapixels/app/server/api.py
index 5f33e84b..743e06f4 100644
--- a/megapixels/app/server/api.py
+++ b/megapixels/app/server/api.py
@@ -1,3 +1,5 @@
+import logging
+import logging.handlers
 import os
 import re
 import time
@@ -141,36 +143,58 @@ def name_lookup(dataset_name):
   dataset = get_dataset(dataset_name)
 
   q = request.args.get('q')
-  q = re.sub('[^a-zA-Z ]+', '*', q)
+  q = re.sub('[^a-zA-Z. ]+', '*', q)
   terms = q.split(' ')
-  # print(q)
 
   query = {
     'q': q,
     'timing': time.time() - start,
   }
-  
-  if len(terms) == 0:
-    results = []
-  elif len(terms) == 1:
-    names = dataset.search_name('%' + terms[0] + '%') if terms[0] else []
-    results = dataset.get_file_records_for_identities(names)
-  else:
-    lookup = {}
-    results_lookup = {}
-    for i, term in enumerate(terms[0:5]):
-      search_term = '%' + term + '%'
-      names = dataset.search_name(term) if term else []
-      for name in names:
-        if name.id in lookup:
-          lookup[name.id] += 1
-        else:
-          lookup[name.id] = 1
-          results_lookup[name.id] = name
-    top_names = [results_lookup[item[0]] for item in sorted(lookup.items(), key=operator.itemgetter(1))][0:10]
-    results = dataset.get_file_records_for_identities(top_names)
 
-  # print(results)
+  print(terms)
+
+  if len(terms) == 0:
+    return jsonify({ 'query': query, 'results': [] })
+
+  lookup = {}
+  results_lookup = {}
+
+  names = dataset.search_name(q + '%')
+  for name in names:
+    if name.id in lookup:
+      print(name.fullname)
+      lookup[name.id] += 4
+    else:
+      print(name.fullname)
+      lookup[name.id] = 4
+      results_lookup[name.id] = name
+  
+  for i, term in enumerate(terms[0:5]):
+    search_term = '%' + term + '%'
+    names = dataset.search_name(search_term) if len(term) > 0 else []
+    descriptions = dataset.search_description(search_term) if len(term) > 0 else []
+    for name in names:
+      if name.id in lookup:
+        print(name.fullname)
+        lookup[name.id] += 2
+      else:
+        print(name.fullname)
+        lookup[name.id] = 2
+        results_lookup[name.id] = name
+    for name in descriptions:
+      if name.id in lookup:
+        print(name.fullname)
+        lookup[name.id] += 1
+      else:
+        print(name.fullname)
+        lookup[name.id] = 1
+        results_lookup[name.id] = name
+
+  sorted_names = sorted(lookup.items(), key=operator.itemgetter(1), reverse=True)[0:10]
+  top_names = [results_lookup[item[0]] for item in sorted_names]
+  results = dataset.get_file_records_for_identities(top_names)
+  
+  print(results)
   return jsonify({
     'query': query,
     'results': results,
diff --git a/megapixels/app/server/create.py b/megapixels/app/server/create.py
index f46bb2a0..a1ce56df 100644
--- a/megapixels/app/server/create.py
+++ b/megapixels/app/server/create.py
@@ -1,3 +1,18 @@
+import logging
+import logging.handlers
+
+logger = logging.getLogger("")
+logger.setLevel(logging.DEBUG)
+handler = logging.handlers.RotatingFileHandler("flask.log",
+    maxBytes=3000000, backupCount=2)
+formatter = logging.Formatter(
+    '[%(asctime)s] {%(filename)s:%(lineno)d} %(levelname)s - %(message)s')
+handler.setFormatter(formatter)
+logger.addHandler(handler)
+logging.getLogger().addHandler(logging.StreamHandler())
+
+logging.debug("starting app")
+
 from flask import Flask, Blueprint, jsonify, send_from_directory
 from flask_sqlalchemy import SQLAlchemy
 from app.models.sql_factory import connection_url, load_sql_datasets
-- 
cgit v1.2.3-70-g09d2