scrub_db 2.0 → 2.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/README.md +15 -15
- data/lib/scrub_db/version.rb +1 -1
- data/scrub_db.gemspec +2 -2
- metadata +7 -8
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 4ab262f6dda53ea22b7d5add643e4328981514d2a51e4842afe60047f808b73b
|
4
|
+
data.tar.gz: b631c6c3a9f53effa4b09d021385133834ed349d286ce349246dd2ce43993b02
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: c43e4b36a05b63ddf9600c41b0c0b8e3916e08d83130ae3d232b085cb466648e1ac9acd1f42728f274f26a6302da2b9ac834e80536de04983952ebfc43276839
|
7
|
+
data.tar.gz: 4f15426f8a298a025c2fa88eb6e3d27dc0412892e840302a87f006ce6c8f41aff37ef18e80dfc12383ec3e8a03298904de9dbe065d7d974db0f904a1e6d65733
|
data/README.md
CHANGED
@@ -1,5 +1,5 @@
|
|
1
1
|
# ScrubDb
|
2
|
-
#### Scrub your database, api data, web scraping data, and web form submissions based on your
|
2
|
+
#### Scrub your database, api data, web scraping data, and web form submissions based on your custom criteria. Allows for different criteria for different jobs. Returns detailed reporting to zero-in on your data with ease, efficiency, and greater insight. Allows for option to pre-format data before scrubbing to also normalize and standardize your data sets, ex uniform URL patterns
|
3
3
|
|
4
4
|
## Installation
|
5
5
|
|
@@ -330,14 +330,14 @@ Continuing with the auto dealership example above, the following examples are to
|
|
330
330
|
First step is to load your Strings criteria in hash format. It's not required to enter all the keys below, but for those you are using, each key must be a symbol and be exactly the same as the ones below. The values must each be an array of strings.
|
331
331
|
|
332
332
|
```
|
333
|
+
pos_criteria = ["acura", "alfa romeo", "aston martin", "audi", "bmw", "bentley", "bugatti", "buick", "cdjr", "cadillac", "chevrolet", "chrysler", "dodge", "ferrari", "fiat", "ford", "gmc", "group", "group", "honda", "hummer", "hyundai", "infiniti", "isuzu", "jaguar", "jeep", "kia", "lamborghini", "lexus", "lincoln", "lotus", "mini", "maserati", "mazda", "mclaren", "mercedes-benz", "mitsubishi", "nissan", "porsche", "ram", "rolls-royce", "saab", "scion", "smart", "subaru", "suzuki", "toyota", "volkswagen", "volvo"]
|
334
|
+
|
335
|
+
neg_criteria = %w[approv avis budget collis eat enterprise facebook financ food google gourmet hertz hotel hyatt insur invest loan lube mobility motel motorola parts quick rent repair restaur rv ryder service softwar travel twitter webhost yellowpages yelp youtube]
|
336
|
+
|
333
337
|
strings_criteria = {
|
334
|
-
|
335
|
-
|
336
|
-
|
337
|
-
pos_paths: %w[team staff management],
|
338
|
-
neg_exts: %w[au ca edu es gov in ru uk us],
|
339
|
-
pos_exts: %w[com net]
|
340
|
-
}
|
338
|
+
pos_criteria: pos_criteria,
|
339
|
+
neg_criteria: neg_criteria
|
340
|
+
}
|
341
341
|
|
342
342
|
strings_obj = ScrubDb::Strings.new(strings_criteria)
|
343
343
|
```
|
@@ -466,14 +466,14 @@ This method is identical to example 2 above (Scrub Array of Strings), except thi
|
|
466
466
|
First step is to load your Strings criteria in hash format. It's not required to enter all the keys below, but for those you are using, each key must be a symbol and be exactly the same as the ones below. The values must each be an array of strings.
|
467
467
|
|
468
468
|
```
|
469
|
+
pos_criteria = ["acura", "alfa romeo", "aston martin", "audi", "bmw", "bentley", "bugatti", "buick", "cdjr", "cadillac", "chevrolet", "chrysler", "dodge", "ferrari", "fiat", "ford", "gmc", "group", "group", "honda", "hummer", "hyundai", "infiniti", "isuzu", "jaguar", "jeep", "kia", "lamborghini", "lexus", "lincoln", "lotus", "mini", "maserati", "mazda", "mclaren", "mercedes-benz", "mitsubishi", "nissan", "porsche", "ram", "rolls-royce", "saab", "scion", "smart", "subaru", "suzuki", "toyota", "volkswagen", "volvo"]
|
470
|
+
|
471
|
+
neg_criteria = %w[approv avis budget collis eat enterprise facebook financ food google gourmet hertz hotel hyatt insur invest loan lube mobility motel motorola parts quick rent repair restaur rv ryder service softwar travel twitter webhost yellowpages yelp youtube]
|
472
|
+
|
469
473
|
strings_criteria = {
|
470
|
-
|
471
|
-
|
472
|
-
|
473
|
-
pos_paths: %w[team staff management],
|
474
|
-
neg_exts: %w[au ca edu es gov in ru uk us],
|
475
|
-
pos_exts: %w[com net]
|
476
|
-
}
|
474
|
+
pos_criteria: pos_criteria,
|
475
|
+
neg_criteria: neg_criteria
|
476
|
+
}
|
477
477
|
|
478
478
|
strings_obj = ScrubDb::Strings.new(strings_criteria)
|
479
479
|
```
|
data/lib/scrub_db/version.rb
CHANGED
data/scrub_db.gemspec
CHANGED
@@ -12,8 +12,8 @@ Gem::Specification.new do |spec|
|
|
12
12
|
spec.homepage = 'https://github.com/4rlm/scrub_db'
|
13
13
|
spec.license = "MIT"
|
14
14
|
|
15
|
-
spec.summary = %q{Scrub your database, api data, web scraping data, and web form submissions based on your
|
16
|
-
spec.description = %q{Scrub your database, api data, web scraping data, and web form submissions based on your
|
15
|
+
spec.summary = %q{Scrub your database, api data, web scraping data, and web form submissions based on your custom criteria. Allows for different criteria for different jobs. Returns detailed reporting to zero-in on your data with ease, efficiency, and greater insight.}
|
16
|
+
spec.description = %q{Scrub your database, api data, web scraping data, and web form submissions based on your custom criteria. Allows for different criteria for different jobs. Returns detailed reporting to zero-in on your data with ease, efficiency, and greater insight. Allows for option to pre-format data before scrubbing to also normalize and standardize your data sets, ex uniform URL patterns}
|
17
17
|
|
18
18
|
if spec.respond_to?(:metadata)
|
19
19
|
spec.metadata['allowed_push_host'] = 'https://rubygems.org'
|
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: scrub_db
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: '2.
|
4
|
+
version: '2.1'
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Adam Booth
|
@@ -209,10 +209,10 @@ dependencies:
|
|
209
209
|
- !ruby/object:Gem::Version
|
210
210
|
version: 0.97.4
|
211
211
|
description: Scrub your database, api data, web scraping data, and web form submissions
|
212
|
-
based on your
|
213
|
-
|
214
|
-
|
215
|
-
|
212
|
+
based on your custom criteria. Allows for different criteria for different jobs. Returns
|
213
|
+
detailed reporting to zero-in on your data with ease, efficiency, and greater insight. Allows
|
214
|
+
for option to pre-format data before scrubbing to also normalize and standardize
|
215
|
+
your data sets, ex uniform URL patterns
|
216
216
|
email:
|
217
217
|
- 4rlm@protonmail.ch
|
218
218
|
executables: []
|
@@ -263,7 +263,6 @@ rubygems_version: 2.7.6
|
|
263
263
|
signing_key:
|
264
264
|
specification_version: 4
|
265
265
|
summary: Scrub your database, api data, web scraping data, and web form submissions
|
266
|
-
based on your
|
267
|
-
|
268
|
-
and greater insight.
|
266
|
+
based on your custom criteria. Allows for different criteria for different jobs. Returns
|
267
|
+
detailed reporting to zero-in on your data with ease, efficiency, and greater insight.
|
269
268
|
test_files: []
|