forked from agilescientific/fuzzylas
-
Notifications
You must be signed in to change notification settings - Fork 1
/
main.py
191 lines (159 loc) · 6.17 KB
/
main.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
#!/usr/bin/env python
# -*- coding: utf-8 -*-
############################
# fuzzylas
# by Matt, December 2012
# Looks up curve mnemonics
# Using data from spwla.org
############################
# Import libraries
import webapp2
import logging
import json
import fuzzylas
import csv
import jinja2
import os
import time
from google.appengine.api import search
#from google.appengine.ext import db
def datetimeformat(value, format='%H:%M on %d.%m.%Y'):
return value.strftime(format)
############################
# Set up the template stuff
template_dir = os.path.join(os.path.dirname(__file__), 'templates')
jinja_env = jinja2.Environment(loader = jinja2.FileSystemLoader(template_dir),
autoescape = True)
jinja_env.filters['datetimeformat'] = datetimeformat
class Handler(webapp2.RequestHandler):
def write(self, *a, **kw):
self.response.out.write(*a, **kw)
def render_str(self, template, **params):
t = jinja_env.get_template(template)
return t.render(params)
def render(self, template, **kw):
self.write(self.render_str(template, **kw))
############################
# Read the datafile and build a data store
# Use a dictionary since we don't need a dynamic store
# I'm pretty sure it only does this once, on deployment
data_file = os.path.join(os.path.dirname(__file__), 'data', 'curves.csv')
with open(data_file,'r') as dbfile:
reader = csv.reader(dbfile)
curves = {}
for row in reader:
record = {"company": row[0].decode('latin-1'),
"type": row[1].decode('latin-1'),
"method": row[2].decode('latin-1'),
"mnemonic": row[3].decode('latin-1'), # redundant but useful in result lists
"model": row[4].decode('latin-1'),
"units": row[5].decode('latin-1'),
"unittype": row[6].decode('latin-1'),
"description": row[7].decode('latin-1'),
# "remark": row[8].decode('latin-1') # handle later - some fields are blank
}
curves.setdefault(str(row[3]), []).append(record)
###############
# Uncomment this section to use GAE Search API
# It doesn't handle fuzzy string matching, however
#
# with open(data_file,'r') as dbfile:
# reader = csv.reader(dbfile)
#
# search_documents = []
# putted = 0
#
# for row in reader:
#
# if len(search_documents) == 200:
# # GAE is rate-limited to 15,000 documents per minute
# # So if we've hit the limit, let's wait
# if putted > 1000:
# break
# # putted = 0
# # time.sleep(60)
#
# try:
# index = search.Index(name='curves')
# putted += 200
# index.put(search_documents)
#
# except search.Error:
# logging.exception('Could not put document in index')
#
# search_documents = []
#
# try:
# document = search.Document(
# fields=[
# search.TextField(name='company', value=row[0].decode('latin-1')),
# search.TextField(name='type', value=row[1].decode('latin-1')),
# search.TextField(name='method', value=row[2].decode('latin-1')),
# search.TextField(name='mnemonic', value=row[3].decode('latin-1')),
# search.TextField(name='model', value=row[4].decode('latin-1')),
# search.TextField(name='units', value=row[5].decode('latin-1')),
# search.TextField(name='unittype', value=row[6].decode('latin-1')),
# search.TextField(name='description', value=row[7].decode('latin-1'))
# ])
#
# except UnicodeDecodeError:
# continue
#
# search_documents.append(document)
#
############################
# Handlers
class MainHandler(Handler):
def get(self):
self.render("index.html")
def post(self):
input = self.request.get('mnemonic').upper()
guess = fuzzylas.guess(curves,input,'simple',3)
self.render("index.html", input=input, result=guess[0], order=sorted(guess[1],key=guess[1].get))
class AboutHandler(Handler):
def get(self):
self.render("about.html")
class ApiHandler(Handler):
def get(self):
guess = None
if self.request.arguments() == []:
self.render("help.html")
else:
mnemonic = self.request.get('mnemonic')
method = self.request.get('method')
format = self.request.get('format')
guesses = self.request.get('guesses')
if mnemonic:
mnemonic = mnemonic.upper()
else:
mnemonic=""
if method:
method = method.lower()
else:
method = "simple"
if format:
format = format.lower()
if guesses:
guesses = int(guesses)
else:
guesses = 1
guess = fuzzylas.guess(curves,mnemonic,method,guesses)
if format == "json":
self.response.headers['Content-Type'] = 'application/json'
self.response.out.write(json.dumps(guess))
elif format == "csv":
dump = 'mnemonic,company,method,description,units\n'
for g in sorted(guess[1],key=guess[1].get):
for i in guess[0][g]:
dump = dump + str(g) + ',' + str(i['company']) + ',' + str(i['method']) + ',' + str(i['description'])+ ',' + str(i['units']) + '\n'
self.response.headers['Content-Type'] = 'text/plain'
self.response.out.write(dump)
else:
self.response.out.write(guess)
##############################
# This is the app itself
app = webapp2.WSGIApplication([
('/', MainHandler),
('/lookup', ApiHandler),
('/about', AboutHandler)
], debug=True)