bmg 0.18.13 → 0.19.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/lib/bmg/reader/csv.rb +49 -14
- data/lib/bmg/reader/excel.rb +43 -28
- data/lib/bmg/relation/materialized.rb +3 -2
- data/lib/bmg/sql/processor/semi_join.rb +0 -3
- data/lib/bmg/version.rb +2 -2
- metadata +2 -2
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 5d3871be740059340140a52f8b47892ef64effee
|
4
|
+
data.tar.gz: 721d3073d321a0d5b6bc3a1a8426522e35cc7138
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 28e1cd068d476e15f0577f70d9e84ca74f2db6e4dc849945c6c94bcf280ad76cc160276d00705cb98a2a5c61db785352a805c3c76034251b1da41c5f511669d5
|
7
|
+
data.tar.gz: b36c7e59b259c5072a37b64f33b422c376794bca64ed02623f7124acd786c1e5f3792a9264ce6cc1f672c2dd281c34e806965a7f0a67bb585afd81a67b830caa
|
data/lib/bmg/reader/csv.rb
CHANGED
@@ -10,20 +10,18 @@ module Bmg
|
|
10
10
|
}
|
11
11
|
|
12
12
|
def initialize(type, path_or_io, options = {})
|
13
|
-
|
13
|
+
require 'csv'
|
14
|
+
|
14
15
|
@path_or_io = path_or_io
|
15
|
-
@options =
|
16
|
-
|
17
|
-
@options[:col_sep] ||= infer_col_sep
|
18
|
-
@options[:quote_char] ||= infer_quote_char
|
19
|
-
end
|
16
|
+
@options = handle_options(options)
|
17
|
+
@type = handle_type(type)
|
20
18
|
end
|
21
19
|
|
22
20
|
def each
|
23
21
|
return to_enum unless block_given?
|
24
|
-
|
25
|
-
|
26
|
-
|
22
|
+
|
23
|
+
with_csv do |csv|
|
24
|
+
csv.each do |row|
|
27
25
|
yield tuple(row)
|
28
26
|
end
|
29
27
|
end
|
@@ -44,33 +42,70 @@ module Bmg
|
|
44
42
|
row.to_hash.each_with_object({}){|(k,v),h| h[k.to_sym] = v }
|
45
43
|
end
|
46
44
|
|
45
|
+
def handle_type(type)
|
46
|
+
return type if type.knows_attrlist?
|
47
|
+
|
48
|
+
type.with_attrlist(infer_attrlist)
|
49
|
+
end
|
50
|
+
|
51
|
+
def infer_attrlist
|
52
|
+
with_csv do |csv|
|
53
|
+
csv.each do |row|
|
54
|
+
return tuple(row).keys
|
55
|
+
end
|
56
|
+
end
|
57
|
+
end
|
58
|
+
|
59
|
+
def handle_options(options)
|
60
|
+
options = DEFAULT_OPTIONS.merge(options)
|
61
|
+
if options[:smart] && !@path_or_io.is_a?(IO)
|
62
|
+
options[:col_sep] ||= infer_col_sep
|
63
|
+
options[:quote_char] ||= infer_quote_char(options[:col_sep])
|
64
|
+
end
|
65
|
+
options
|
66
|
+
end
|
67
|
+
|
47
68
|
def infer_col_sep
|
48
69
|
sniff(text_portion, [",","\t",";"], ",")
|
49
70
|
end
|
50
71
|
|
51
|
-
def infer_quote_char
|
52
|
-
sniff(text_portion, ["'
|
72
|
+
def infer_quote_char(col_sep)
|
73
|
+
sniff(text_portion, ['"',"'"], '"'){|quote|
|
74
|
+
/#{quote}#{col_sep}#{quote}|^#{quote}|#{quote}$/
|
75
|
+
}
|
53
76
|
end
|
54
77
|
|
55
78
|
def text_portion
|
56
|
-
@text_portion ||= with_io{|io| io.readlines(
|
79
|
+
@text_portion ||= with_io{|io| io.readlines(50).join("\n") }
|
57
80
|
end
|
58
81
|
|
59
82
|
def with_io(&bl)
|
60
83
|
case @path_or_io
|
61
84
|
when IO, StringIO
|
85
|
+
@path_or_io.rewind if @path_or_io.respond_to?(:rewind)
|
62
86
|
bl.call(@path_or_io)
|
63
87
|
else
|
64
88
|
File.open(@path_or_io, "r", &bl)
|
65
89
|
end
|
66
90
|
end
|
67
91
|
|
92
|
+
def with_csv(&bl)
|
93
|
+
with_io do |io|
|
94
|
+
yield ::CSV.new(io, **csv_options)
|
95
|
+
end
|
96
|
+
end
|
97
|
+
|
68
98
|
# Finds the best candidate among `candidates` for a separator
|
69
99
|
# found in `str`. If none is found, returns `default`.
|
70
|
-
def sniff(str, candidates, default)
|
100
|
+
def sniff(str, candidates, default, &bl)
|
71
101
|
snif = {}
|
72
102
|
candidates.each {|delim|
|
73
|
-
|
103
|
+
counter = bl ? bl.call(delim) : delim
|
104
|
+
snif[delim] = if counter.is_a?(Regexp)
|
105
|
+
str.scan(counter).length
|
106
|
+
else
|
107
|
+
str.count(counter)
|
108
|
+
end
|
74
109
|
}
|
75
110
|
snif = snif.sort {|a,b| b[1] <=> a[1] }
|
76
111
|
snif.size > 0 ? snif[0][0] : default
|
data/lib/bmg/reader/excel.rb
CHANGED
@@ -10,32 +10,27 @@ module Bmg
|
|
10
10
|
}
|
11
11
|
|
12
12
|
def initialize(type, path, options = {})
|
13
|
-
|
13
|
+
require 'roo'
|
14
14
|
@path = path
|
15
15
|
@options = DEFAULT_OPTIONS.merge(options)
|
16
|
+
@type = type.knows_attrlist? ? type : type.with_attrlist(infer_attrlist)
|
16
17
|
end
|
17
18
|
|
18
19
|
def each
|
19
20
|
return to_enum unless block_given?
|
20
|
-
|
21
|
-
|
22
|
-
headers =
|
23
|
-
|
24
|
-
|
25
|
-
|
26
|
-
.
|
27
|
-
|
28
|
-
|
29
|
-
|
30
|
-
|
31
|
-
|
32
|
-
|
33
|
-
.each_with_object(init){|i,t|
|
34
|
-
t[headers[i]] = row[i]
|
35
|
-
}
|
36
|
-
yield(tuple)
|
37
|
-
end
|
38
|
-
end
|
21
|
+
|
22
|
+
headers = type.attrlist
|
23
|
+
headers = headers[1..-1] if generate_row_num?
|
24
|
+
start_at = @options[:skip] + 2
|
25
|
+
end_at = spreadsheet.last_row
|
26
|
+
(start_at..end_at).each do |i|
|
27
|
+
row = spreadsheet.row(i)
|
28
|
+
init = init_tuple(i - start_at + 1)
|
29
|
+
tuple = (0...headers.size).each_with_object(init){|i,t|
|
30
|
+
t[headers[i]] = row[i]
|
31
|
+
}
|
32
|
+
yield(tuple)
|
33
|
+
end
|
39
34
|
end
|
40
35
|
|
41
36
|
def to_ast
|
@@ -49,17 +44,37 @@ module Bmg
|
|
49
44
|
|
50
45
|
private
|
51
46
|
|
52
|
-
def
|
47
|
+
def spreadsheet
|
48
|
+
@spreadsheet ||= Roo::Spreadsheet
|
49
|
+
.open(@path, @options)
|
50
|
+
.sheet(@options[:sheet])
|
51
|
+
end
|
52
|
+
|
53
|
+
def infer_attrlist
|
54
|
+
row = spreadsheet.row(1+@options[:skip])
|
55
|
+
attrlist = row.map{|c| c.to_s.strip.to_sym }
|
56
|
+
attrlist.unshift(row_num_name) if generate_row_num?
|
57
|
+
attrlist
|
58
|
+
end
|
59
|
+
|
60
|
+
def generate_row_num?
|
61
|
+
!!@options[:row_num]
|
62
|
+
end
|
63
|
+
|
64
|
+
def row_num_name
|
53
65
|
case as = @options[:row_num]
|
54
|
-
when TrueClass
|
55
|
-
|
56
|
-
|
57
|
-
{}
|
58
|
-
when Symbol
|
59
|
-
{ :"#{as}" => i }
|
66
|
+
when TrueClass then :row_num
|
67
|
+
when Symbol then as
|
68
|
+
else nil
|
60
69
|
end
|
61
70
|
end
|
62
71
|
|
72
|
+
def init_tuple(i)
|
73
|
+
return {} unless generate_row_num?
|
74
|
+
|
75
|
+
{ row_num_name => i }
|
76
|
+
end
|
77
|
+
|
63
78
|
end # class Excel
|
64
79
|
end # module Reader
|
65
|
-
end # module Bmg
|
80
|
+
end # module Bmg
|
@@ -5,6 +5,7 @@ module Bmg
|
|
5
5
|
|
6
6
|
def initialize(operand)
|
7
7
|
@operand = operand
|
8
|
+
@materialized = nil
|
8
9
|
end
|
9
10
|
|
10
11
|
def type
|
@@ -40,9 +41,9 @@ module Bmg
|
|
40
41
|
private
|
41
42
|
|
42
43
|
def _materialize
|
43
|
-
return @
|
44
|
+
return @materialized if @materialized
|
44
45
|
|
45
|
-
@
|
46
|
+
@materialized = Relation::InMemory.new(operand.type, operand.to_a)
|
46
47
|
end
|
47
48
|
|
48
49
|
end # class Materialized
|
@@ -39,9 +39,6 @@ module Bmg
|
|
39
39
|
subquery = All.new(builder).call(subquery)
|
40
40
|
if commons.size == 0
|
41
41
|
builder.exists(subquery)
|
42
|
-
elsif commons.size == 1
|
43
|
-
identifier = left.desaliaser(true)[commons.to_a.first]
|
44
|
-
Predicate::Factory.in(identifier, Predicate::Factory.opaque(subquery))
|
45
42
|
else
|
46
43
|
join_pre = join_predicate(left, subquery, commons)
|
47
44
|
subquery = expand_where_clause(subquery, join_pre)
|
data/lib/bmg/version.rb
CHANGED
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: bmg
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.
|
4
|
+
version: 0.19.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Bernard Lambeau
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2022-
|
11
|
+
date: 2022-04-21 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: predicate
|