embulk 0.6.3 → 0.6.4

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: b37c9dd1d3a700e0057040d27f0a29e917e21b13
-  data.tar.gz: 3372de3c3f382dc6f83bea6936d84af3b815194c
+  metadata.gz: de4102fca39496965dc800236bce8dae92e68a9c
+  data.tar.gz: 637887dd9dc0ab4e7f1d886736fba913aee8ee4b
 SHA512:
-  metadata.gz: 7d0c416b6c063508b95d23941c5cf97149bcf6fd11134392f79d0d7540f106df019e502fc7296ba47a94a945a64c8b34a4d4aaf682227d390300592d598c0f1a
-  data.tar.gz: b370deb8322442973cc3109ca2a0b8eb3931d11840f55e7d230f56c10de45c93a71d39cb892dad491ef67870c9e77932fabee4d82cf99ea601ba3417ea3e7cc8
+  metadata.gz: 4708b0f2cb6a7440d146605a1a50f67b1d52d1218f8f07b212eeb315f71befa2f1e08327e585277bbe55ca799aea7db65dc896f0c22eb6cb54aaaec03d9c4e77
+  data.tar.gz: c16df22dc21a912e86bc44289ec3741e803a20ef0cf19e5227467dc5f908d3043f6b6b8394d0696ba87e3ee4f8eb3b8465e9a8742164d5d47d8d154723975e26

data/build.gradle

@@ -11,7 +11,7 @@ def release_projects = [project(":embulk-core"), project(":embulk-standards")]
 
 allprojects {
     group = 'org.embulk'
-    version = '0.6.3'
+    version = '0.6.4'
 
     ext {
         jrubyVersion = '1.7.19'

data/embulk-docs/src/release.rst

@@ -4,6 +4,7 @@ Release Notes
 .. toctree::
     :maxdepth: 1
 
+    release/release-0.6.4
     release/release-0.6.3
     release/release-0.6.2
     release/release-0.6.1

data/embulk-docs/src/release/release-0.6.4.rst

@@ -0,0 +1,13 @@
+Release 0.6.4
+==================================
+
+Built-in plugins
+------------------
+
+* ``guess-csv`` keeps existent configurations such as ``null_string`` if they are already set.
+* ``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.
+* Fixed a problem where ``guess-csv`` can't handle quoted values (@y-ken++)
+
+Release Date
+------------------
+2015-04-21

data/lib/embulk/guess/csv.rb

@@ -37,17 +37,23 @@ module Embulk
         end
 
         parser_config = config["parser"] || {}
-        parser_guessed = DataSource.new.merge({"type" => "csv", "delimiter" => delim})
+        parser_guessed = DataSource.new.merge(parser_config).merge({"type" => "csv", "delimiter" => delim})
 
-        quote = guess_quote(sample_lines, delim)
-        parser_guessed["quote"] = quote ? quote : ''
+        unless parser_guessed.has_key?("quote")
+          quote = guess_quote(sample_lines, delim)
+          parser_guessed["quote"] = quote ? quote : ''
+        end
 
-        escape = guess_escape(sample_lines, delim, quote)
-        parser_guessed["escape"] = escape ? escape : ''
+        unless parser_guessed.has_key?("escape")
+          escape = guess_escape(sample_lines, delim, quote)
+          parser_guessed["escape"] = escape ? escape : ''
+        end
 
-        null_string = guess_null_string(sample_lines, delim)
-        parser_guessed["null_string"] = null_string if null_string
-        # don't even set null_string to avoid confusion of null and 'null' in YAML format
+        unless parser_guessed.has_key?("null_string")
+          null_string = guess_null_string(sample_lines, delim)
+          parser_guessed["null_string"] = null_string if null_string
+          # don't even set null_string to avoid confusion of null and 'null' in YAML format
+        end
 
         sample_records = split_lines(parser_guessed, sample_lines, delim)
         skip_header_lines = guess_skip_header_lines(sample_records)
@@ -102,14 +108,19 @@ module Embulk
         rows = []
         while tokenizer.nextFile
           while tokenizer.nextRecord
-            columns = []
-            while true
-              begin
-                columns << tokenizer.nextColumn
-              rescue java.lang.IllegalStateException  # TODO exception class
-                rows << columns
-                break
+            begin
+              columns = []
+              while true
+                begin
+                  columns << tokenizer.nextColumn
+                rescue org.embulk.standards.CsvTokenizer::TooFewColumnsException
+                  rows << columns
+                  break
+                end
               end
+            rescue org.embulk.standards.CsvTokenizer::InvalidValueException
+              # TODO warning
+              tokenizer.skipCurrentLine
             end
           end
         end

data/lib/embulk/version.rb

@@ -1,3 +1,3 @@
 module Embulk
-  VERSION = '0.6.3'
+  VERSION = '0.6.4'
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: embulk
 version: !ruby/object:Gem::Version
-  version: 0.6.3
+  version: 0.6.4
 platform: ruby
 authors:
 - Sadayuki Furuhashi
@@ -293,6 +293,7 @@ files:
 - embulk-docs/src/release/release-0.6.1.rst
 - embulk-docs/src/release/release-0.6.2.rst
 - embulk-docs/src/release/release-0.6.3.rst
+- embulk-docs/src/release/release-0.6.4.rst
 - embulk-standards/build.gradle
 - embulk-standards/src/main/java/org/embulk/standards/CsvFormatterPlugin.java
 - embulk-standards/src/main/java/org/embulk/standards/CsvParserPlugin.java
@@ -398,8 +399,8 @@ files:
 - classpath/bval-jsr303-0.5.jar
 - classpath/commons-beanutils-core-1.8.3.jar
 - classpath/commons-lang3-3.1.jar
-- classpath/embulk-core-0.6.3.jar
-- classpath/embulk-standards-0.6.3.jar
+- classpath/embulk-core-0.6.4.jar
+- classpath/embulk-standards-0.6.4.jar
 - classpath/guava-18.0.jar
 - classpath/guice-3.0.jar
 - classpath/guice-multibindings-3.0.jar