embulk 0.6.3 → 0.6.4
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/build.gradle +1 -1
- data/embulk-docs/src/release.rst +1 -0
- data/embulk-docs/src/release/release-0.6.4.rst +13 -0
- data/lib/embulk/guess/csv.rb +26 -15
- data/lib/embulk/version.rb +1 -1
- metadata +4 -3
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA1:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: de4102fca39496965dc800236bce8dae92e68a9c
|
|
4
|
+
data.tar.gz: 637887dd9dc0ab4e7f1d886736fba913aee8ee4b
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: 4708b0f2cb6a7440d146605a1a50f67b1d52d1218f8f07b212eeb315f71befa2f1e08327e585277bbe55ca799aea7db65dc896f0c22eb6cb54aaaec03d9c4e77
|
|
7
|
+
data.tar.gz: c16df22dc21a912e86bc44289ec3741e803a20ef0cf19e5227467dc5f908d3043f6b6b8394d0696ba87e3ee4f8eb3b8465e9a8742164d5d47d8d154723975e26
|
data/build.gradle
CHANGED
data/embulk-docs/src/release.rst
CHANGED
|
@@ -0,0 +1,13 @@
|
|
|
1
|
+
Release 0.6.4
|
|
2
|
+
==================================
|
|
3
|
+
|
|
4
|
+
Built-in plugins
|
|
5
|
+
------------------
|
|
6
|
+
|
|
7
|
+
* ``guess-csv`` keeps existent configurations such as ``null_string`` if they are already set.
|
|
8
|
+
* ``guess-csv`` skips line if a CSV file is broken rather than falling back to ad-hoc implementation which can't deal with quoted values.
|
|
9
|
+
* Fixed a problem where ``guess-csv`` can't handle quoted values (@y-ken++)
|
|
10
|
+
|
|
11
|
+
Release Date
|
|
12
|
+
------------------
|
|
13
|
+
2015-04-21
|
data/lib/embulk/guess/csv.rb
CHANGED
|
@@ -37,17 +37,23 @@ module Embulk
|
|
|
37
37
|
end
|
|
38
38
|
|
|
39
39
|
parser_config = config["parser"] || {}
|
|
40
|
-
parser_guessed = DataSource.new.merge({"type" => "csv", "delimiter" => delim})
|
|
40
|
+
parser_guessed = DataSource.new.merge(parser_config).merge({"type" => "csv", "delimiter" => delim})
|
|
41
41
|
|
|
42
|
-
|
|
43
|
-
|
|
42
|
+
unless parser_guessed.has_key?("quote")
|
|
43
|
+
quote = guess_quote(sample_lines, delim)
|
|
44
|
+
parser_guessed["quote"] = quote ? quote : ''
|
|
45
|
+
end
|
|
44
46
|
|
|
45
|
-
|
|
46
|
-
|
|
47
|
+
unless parser_guessed.has_key?("escape")
|
|
48
|
+
escape = guess_escape(sample_lines, delim, quote)
|
|
49
|
+
parser_guessed["escape"] = escape ? escape : ''
|
|
50
|
+
end
|
|
47
51
|
|
|
48
|
-
|
|
49
|
-
|
|
50
|
-
|
|
52
|
+
unless parser_guessed.has_key?("null_string")
|
|
53
|
+
null_string = guess_null_string(sample_lines, delim)
|
|
54
|
+
parser_guessed["null_string"] = null_string if null_string
|
|
55
|
+
# don't even set null_string to avoid confusion of null and 'null' in YAML format
|
|
56
|
+
end
|
|
51
57
|
|
|
52
58
|
sample_records = split_lines(parser_guessed, sample_lines, delim)
|
|
53
59
|
skip_header_lines = guess_skip_header_lines(sample_records)
|
|
@@ -102,14 +108,19 @@ module Embulk
|
|
|
102
108
|
rows = []
|
|
103
109
|
while tokenizer.nextFile
|
|
104
110
|
while tokenizer.nextRecord
|
|
105
|
-
|
|
106
|
-
|
|
107
|
-
|
|
108
|
-
|
|
109
|
-
|
|
110
|
-
|
|
111
|
-
|
|
111
|
+
begin
|
|
112
|
+
columns = []
|
|
113
|
+
while true
|
|
114
|
+
begin
|
|
115
|
+
columns << tokenizer.nextColumn
|
|
116
|
+
rescue org.embulk.standards.CsvTokenizer::TooFewColumnsException
|
|
117
|
+
rows << columns
|
|
118
|
+
break
|
|
119
|
+
end
|
|
112
120
|
end
|
|
121
|
+
rescue org.embulk.standards.CsvTokenizer::InvalidValueException
|
|
122
|
+
# TODO warning
|
|
123
|
+
tokenizer.skipCurrentLine
|
|
113
124
|
end
|
|
114
125
|
end
|
|
115
126
|
end
|
data/lib/embulk/version.rb
CHANGED
metadata
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: embulk
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 0.6.
|
|
4
|
+
version: 0.6.4
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- Sadayuki Furuhashi
|
|
@@ -293,6 +293,7 @@ files:
|
|
|
293
293
|
- embulk-docs/src/release/release-0.6.1.rst
|
|
294
294
|
- embulk-docs/src/release/release-0.6.2.rst
|
|
295
295
|
- embulk-docs/src/release/release-0.6.3.rst
|
|
296
|
+
- embulk-docs/src/release/release-0.6.4.rst
|
|
296
297
|
- embulk-standards/build.gradle
|
|
297
298
|
- embulk-standards/src/main/java/org/embulk/standards/CsvFormatterPlugin.java
|
|
298
299
|
- embulk-standards/src/main/java/org/embulk/standards/CsvParserPlugin.java
|
|
@@ -398,8 +399,8 @@ files:
|
|
|
398
399
|
- classpath/bval-jsr303-0.5.jar
|
|
399
400
|
- classpath/commons-beanutils-core-1.8.3.jar
|
|
400
401
|
- classpath/commons-lang3-3.1.jar
|
|
401
|
-
- classpath/embulk-core-0.6.
|
|
402
|
-
- classpath/embulk-standards-0.6.
|
|
402
|
+
- classpath/embulk-core-0.6.4.jar
|
|
403
|
+
- classpath/embulk-standards-0.6.4.jar
|
|
403
404
|
- classpath/guava-18.0.jar
|
|
404
405
|
- classpath/guice-3.0.jar
|
|
405
406
|
- classpath/guice-multibindings-3.0.jar
|