embulk-parser-csv_guessable 0.1.4 → 0.1.5

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 CHANGED
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  SHA1:
3
- metadata.gz: 9cfb187d0ece1ab6bc1a9798e671c1beef48c58b
4
- data.tar.gz: e4027715432a5a797ffffc67366863fc35a93c54
3
+ metadata.gz: 07a5d30689afe074b0db47f61c04651e74b76024
4
+ data.tar.gz: b16fda4794ed77f2111d4e047210c8966f0fed2e
5
5
  SHA512:
6
- metadata.gz: 5b82123b220cd203b749ea8604983eac5c0aab4352b5b5f484b35e78ad7f462a964c39b7be98f314b446b306104478dbba3b2724a5181bc7f971f1a38da2c156
7
- data.tar.gz: 9646c871c87790b9d36c804c9080144f12f2a2ffe0ee8ef8a16e71ca2ebac69be391e9a3397edbc8ecdc5be8290fe4bc453d05f77d804c4291365063f4f17db1
6
+ metadata.gz: ca548cf755f02e6be06bef5664754271ac1f5041e4baa0dd015e546ec4e00396051a6fc8d532603d01a778069baf9398ae132b1770b70c6eb1790954cf6eafb3
7
+ data.tar.gz: 368cb17eb071324704ff2ac131511c4f96e67f3a8eb109fbe9e7dec549757dc0b10cbed1176246d1db18f43f48ad98a4b4213f8f482d70f12a2ee2f5e7283473
@@ -0,0 +1,21 @@
1
+ version: 2
2
+ jobs:
3
+ build:
4
+ docker:
5
+ - image: circleci/openjdk:8-jdk
6
+ working_directory: ~/repo
7
+ environment:
8
+ JVM_OPTS: -Xmx3200m
9
+ TERM: dumb
10
+ steps:
11
+ - checkout
12
+ - restore_cache:
13
+ keys:
14
+ - v1-dependencies-{{ checksum "build.gradle" }}
15
+ - v1-dependencies-
16
+ - run: gradle dependencies
17
+ - save_cache:
18
+ paths:
19
+ - ~/.m2
20
+ key: v1-dependencies-{{ checksum "build.gradle" }}
21
+ - run: gradle test
data/README.md CHANGED
@@ -1,3 +1,6 @@
1
+ [![Gem Version](https://badge.fury.io/rb/embulk-parser-csv_guessable.svg)](https://badge.fury.io/rb/embulk-parser-csv_guessable)
2
+ [![CircleCI](https://circleci.com/gh/koooge/embulk-parser-csv_guessable.svg?style=svg)](https://circleci.com/gh/koooge/embulk-parser-csv_guessable)
3
+
1
4
  # Guessable csv parser plugin for Embulk
2
5
  **embulk-parser-csv_guessable** (runtime)guesses and parses csv which has schema in header.
3
6
 
@@ -24,8 +27,6 @@ It behaves as original csv parser when **embulk-parser-csv_guessable** conifgs(`
24
27
  - **date**: Set date part if the format doesn't include date part
25
28
  - any other csv configs: see [www.embulk.org](http://www.embulk.org/docs/built-in.html#csv-parser-plugin)
26
29
 
27
- The `columns`
28
-
29
30
  ## Example
30
31
  test.csv (There is a schema at the first line.)
31
32
 
@@ -88,8 +89,21 @@ $ embulk gem install embulk-parser-csv_guessable
88
89
  $ embulk guess -g csv_guessable config.yml -o guessed.yml
89
90
  -->
90
91
 
92
+ ## Sample
93
+
94
+ ```
95
+ $ cd samples/sample2
96
+ $ embulk run -L ../../ config_rename.yml -l debug
97
+ ```
98
+
91
99
  ## Build
92
100
 
93
101
  ```
94
102
  $ ./gradlew gem # -t to watch change of files and rebuild continuously
95
103
  ```
104
+
105
+ ## Test
106
+
107
+ ```
108
+ $ ./gradlew test
109
+ ```
@@ -13,16 +13,16 @@ configurations {
13
13
  provided
14
14
  }
15
15
 
16
- version = "0.1.4"
16
+ version = "0.1.5"
17
17
 
18
18
  sourceCompatibility = 1.7
19
19
  targetCompatibility = 1.7
20
20
 
21
21
  dependencies {
22
- compile "org.embulk:embulk-core:0.8.22"
23
- compile "org.embulk:embulk-standards:0.8.22"
22
+ compile "org.embulk:embulk-core:0.8.+"
23
+ compile "org.embulk:embulk-standards:0.8.+"
24
24
  compile "com.opencsv:opencsv:3.9"
25
- provided "org.embulk:embulk-core:0.8.22"
25
+ provided "org.embulk:embulk-core:0.8.+"
26
26
  testCompile "junit:junit:4.+"
27
27
  testCompile "org.embulk:embulk-core:0.8.+:tests"
28
28
  testCompile "org.embulk:embulk-standards:0.8.+:tests"
@@ -1,6 +1,5 @@
1
- #Sun Jan 08 00:35:58 PST 2017
1
+ distributionUrl=https\://services.gradle.org/distributions/gradle-4.2.1-bin.zip
2
2
  distributionBase=GRADLE_USER_HOME
3
3
  distributionPath=wrapper/dists
4
- zipStoreBase=GRADLE_USER_HOME
5
4
  zipStorePath=wrapper/dists
6
- distributionUrl=https\://services.gradle.org/distributions/gradle-3.2.1-bin.zip
5
+ zipStoreBase=GRADLE_USER_HOME
data/gradlew CHANGED
@@ -1,4 +1,4 @@
1
- #!/usr/bin/env bash
1
+ #!/usr/bin/env sh
2
2
 
3
3
  ##############################################################################
4
4
  ##
@@ -33,11 +33,11 @@ DEFAULT_JVM_OPTS=""
33
33
  # Use the maximum available, or set MAX_FD != -1 to use that value.
34
34
  MAX_FD="maximum"
35
35
 
36
- warn ( ) {
36
+ warn () {
37
37
  echo "$*"
38
38
  }
39
39
 
40
- die ( ) {
40
+ die () {
41
41
  echo
42
42
  echo "$*"
43
43
  echo
@@ -154,16 +154,19 @@ if $cygwin ; then
154
154
  esac
155
155
  fi
156
156
 
157
- # Split up the JVM_OPTS And GRADLE_OPTS values into an array, following the shell quoting and substitution rules
158
- function splitJvmOpts() {
159
- JVM_OPTS=("$@")
157
+ # Escape application args
158
+ save () {
159
+ for i do printf %s\\n "$i" | sed "s/'/'\\\\''/g;1s/^/'/;\$s/\$/' \\\\/" ; done
160
+ echo " "
160
161
  }
161
- eval splitJvmOpts $DEFAULT_JVM_OPTS $JAVA_OPTS $GRADLE_OPTS
162
- JVM_OPTS[${#JVM_OPTS[*]}]="-Dorg.gradle.appname=$APP_BASE_NAME"
162
+ APP_ARGS=$(save "$@")
163
+
164
+ # Collect all arguments for the java command, following the shell quoting and substitution rules
165
+ eval set -- $DEFAULT_JVM_OPTS $JAVA_OPTS $GRADLE_OPTS "\"-Dorg.gradle.appname=$APP_BASE_NAME\"" -classpath "\"$CLASSPATH\"" org.gradle.wrapper.GradleWrapperMain "$APP_ARGS"
163
166
 
164
167
  # by default we should be in the correct project dir, but when run from Finder on Mac, the cwd is wrong
165
- if [[ "$(uname)" == "Darwin" ]] && [[ "$HOME" == "$PWD" ]]; then
168
+ if [ "$(uname)" = "Darwin" ] && [ "$HOME" = "$PWD" ]; then
166
169
  cd "$(dirname "$0")"
167
170
  fi
168
171
 
169
- exec "$JAVACMD" "${JVM_OPTS[@]}" -classpath "$CLASSPATH" org.gradle.wrapper.GradleWrapperMain "$@"
172
+ exec "$JAVACMD" "$@"
@@ -1,84 +1,84 @@
1
- @if "%DEBUG%" == "" @echo off
2
- @rem ##########################################################################
3
- @rem
4
- @rem Gradle startup script for Windows
5
- @rem
6
- @rem ##########################################################################
7
-
8
- @rem Set local scope for the variables with windows NT shell
9
- if "%OS%"=="Windows_NT" setlocal
10
-
11
- set DIRNAME=%~dp0
12
- if "%DIRNAME%" == "" set DIRNAME=.
13
- set APP_BASE_NAME=%~n0
14
- set APP_HOME=%DIRNAME%
15
-
16
- @rem Add default JVM options here. You can also use JAVA_OPTS and GRADLE_OPTS to pass JVM options to this script.
17
- set DEFAULT_JVM_OPTS=
18
-
19
- @rem Find java.exe
20
- if defined JAVA_HOME goto findJavaFromJavaHome
21
-
22
- set JAVA_EXE=java.exe
23
- %JAVA_EXE% -version >NUL 2>&1
24
- if "%ERRORLEVEL%" == "0" goto init
25
-
26
- echo.
27
- echo ERROR: JAVA_HOME is not set and no 'java' command could be found in your PATH.
28
- echo.
29
- echo Please set the JAVA_HOME variable in your environment to match the
30
- echo location of your Java installation.
31
-
32
- goto fail
33
-
34
- :findJavaFromJavaHome
35
- set JAVA_HOME=%JAVA_HOME:"=%
36
- set JAVA_EXE=%JAVA_HOME%/bin/java.exe
37
-
38
- if exist "%JAVA_EXE%" goto init
39
-
40
- echo.
41
- echo ERROR: JAVA_HOME is set to an invalid directory: %JAVA_HOME%
42
- echo.
43
- echo Please set the JAVA_HOME variable in your environment to match the
44
- echo location of your Java installation.
45
-
46
- goto fail
47
-
48
- :init
49
- @rem Get command-line arguments, handling Windows variants
50
-
51
- if not "%OS%" == "Windows_NT" goto win9xME_args
52
-
53
- :win9xME_args
54
- @rem Slurp the command line arguments.
55
- set CMD_LINE_ARGS=
56
- set _SKIP=2
57
-
58
- :win9xME_args_slurp
59
- if "x%~1" == "x" goto execute
60
-
61
- set CMD_LINE_ARGS=%*
62
-
63
- :execute
64
- @rem Setup the command line
65
-
66
- set CLASSPATH=%APP_HOME%\gradle\wrapper\gradle-wrapper.jar
67
-
68
- @rem Execute Gradle
69
- "%JAVA_EXE%" %DEFAULT_JVM_OPTS% %JAVA_OPTS% %GRADLE_OPTS% "-Dorg.gradle.appname=%APP_BASE_NAME%" -classpath "%CLASSPATH%" org.gradle.wrapper.GradleWrapperMain %CMD_LINE_ARGS%
70
-
71
- :end
72
- @rem End local scope for the variables with windows NT shell
73
- if "%ERRORLEVEL%"=="0" goto mainEnd
74
-
75
- :fail
76
- rem Set variable GRADLE_EXIT_CONSOLE if you need the _script_ return code instead of
77
- rem the _cmd.exe /c_ return code!
78
- if not "" == "%GRADLE_EXIT_CONSOLE%" exit 1
79
- exit /b 1
80
-
81
- :mainEnd
82
- if "%OS%"=="Windows_NT" endlocal
83
-
84
- :omega
1
+ @if "%DEBUG%" == "" @echo off
2
+ @rem ##########################################################################
3
+ @rem
4
+ @rem Gradle startup script for Windows
5
+ @rem
6
+ @rem ##########################################################################
7
+
8
+ @rem Set local scope for the variables with windows NT shell
9
+ if "%OS%"=="Windows_NT" setlocal
10
+
11
+ set DIRNAME=%~dp0
12
+ if "%DIRNAME%" == "" set DIRNAME=.
13
+ set APP_BASE_NAME=%~n0
14
+ set APP_HOME=%DIRNAME%
15
+
16
+ @rem Add default JVM options here. You can also use JAVA_OPTS and GRADLE_OPTS to pass JVM options to this script.
17
+ set DEFAULT_JVM_OPTS=
18
+
19
+ @rem Find java.exe
20
+ if defined JAVA_HOME goto findJavaFromJavaHome
21
+
22
+ set JAVA_EXE=java.exe
23
+ %JAVA_EXE% -version >NUL 2>&1
24
+ if "%ERRORLEVEL%" == "0" goto init
25
+
26
+ echo.
27
+ echo ERROR: JAVA_HOME is not set and no 'java' command could be found in your PATH.
28
+ echo.
29
+ echo Please set the JAVA_HOME variable in your environment to match the
30
+ echo location of your Java installation.
31
+
32
+ goto fail
33
+
34
+ :findJavaFromJavaHome
35
+ set JAVA_HOME=%JAVA_HOME:"=%
36
+ set JAVA_EXE=%JAVA_HOME%/bin/java.exe
37
+
38
+ if exist "%JAVA_EXE%" goto init
39
+
40
+ echo.
41
+ echo ERROR: JAVA_HOME is set to an invalid directory: %JAVA_HOME%
42
+ echo.
43
+ echo Please set the JAVA_HOME variable in your environment to match the
44
+ echo location of your Java installation.
45
+
46
+ goto fail
47
+
48
+ :init
49
+ @rem Get command-line arguments, handling Windows variants
50
+
51
+ if not "%OS%" == "Windows_NT" goto win9xME_args
52
+
53
+ :win9xME_args
54
+ @rem Slurp the command line arguments.
55
+ set CMD_LINE_ARGS=
56
+ set _SKIP=2
57
+
58
+ :win9xME_args_slurp
59
+ if "x%~1" == "x" goto execute
60
+
61
+ set CMD_LINE_ARGS=%*
62
+
63
+ :execute
64
+ @rem Setup the command line
65
+
66
+ set CLASSPATH=%APP_HOME%\gradle\wrapper\gradle-wrapper.jar
67
+
68
+ @rem Execute Gradle
69
+ "%JAVA_EXE%" %DEFAULT_JVM_OPTS% %JAVA_OPTS% %GRADLE_OPTS% "-Dorg.gradle.appname=%APP_BASE_NAME%" -classpath "%CLASSPATH%" org.gradle.wrapper.GradleWrapperMain %CMD_LINE_ARGS%
70
+
71
+ :end
72
+ @rem End local scope for the variables with windows NT shell
73
+ if "%ERRORLEVEL%"=="0" goto mainEnd
74
+
75
+ :fail
76
+ rem Set variable GRADLE_EXIT_CONSOLE if you need the _script_ return code instead of
77
+ rem the _cmd.exe /c_ return code!
78
+ if not "" == "%GRADLE_EXIT_CONSOLE%" exit 1
79
+ exit /b 1
80
+
81
+ :mainEnd
82
+ if "%OS%"=="Windows_NT" endlocal
83
+
84
+ :omega
@@ -0,0 +1,9 @@
1
+ in:
2
+ type: file
3
+ path_prefix: "./sample"
4
+ parser:
5
+ type: csv_guessable
6
+ schema_file: sample1.csv
7
+ charset: MS932
8
+ out:
9
+ type: stdout
@@ -0,0 +1,13 @@
1
+ in:
2
+ type: file
3
+ path_prefix: "./sample"
4
+ parser:
5
+ type: csv_guessable
6
+ schema_file: sample1.csv
7
+ charset: MS932
8
+ columns:
9
+ - {name: 'ken-code', type: long}
10
+ - {name: 'sityouson-code', type: long}
11
+ - {name: 'tiiki-code', type: long}
12
+ out:
13
+ type: stdout
@@ -0,0 +1,10 @@
1
+ ken-code,sityouson-code,tiiki-code,ken-name,sityouson-name1,sityouson-name2,sityouson-name3,yomigana
2
+ 1,0,1000,�k�C��,,,,�ق������ǂ�
3
+ 1,100,1100,�k�C��,�D�y�s,,,�����ۂ낵
4
+ 1,101,1101,�k�C��,�D�y�s,,������,���イ������
5
+ 1,102,1102,�k�C��,�D�y�s,,�k��,������
6
+ 1,103,1103,�k�C��,�D�y�s,,����,�Ђ�����
7
+ 1,104,1104,�k�C��,�D�y�s,,���΋�,���낢����
8
+ 1,105,1105,�k�C��,�D�y�s,,�L����,�Ƃ�Ђ炭
9
+ 1,106,1106,�k�C��,�D�y�s,,���,�݂Ȃ݂�
10
+ 1,107,1107,�k�C��,�D�y�s,,����,�ɂ���
@@ -0,0 +1,18 @@
1
+ in:
2
+ type: file
3
+ path_prefix: "./sample"
4
+ parser:
5
+ type: csv_guessable
6
+ schema_file: sample2.csv
7
+ charset: MS932
8
+ columns:
9
+ - {value_name: '県コード', name: 'ken-code', type: long}
10
+ - {value_name: '市町村コード', name: 'sityouson-code', type: long}
11
+ - {value_name: '地域コード', name: 'tiiki-code', type: long}
12
+ - {value_name: '県名', name: 'ken-name', type: string}
13
+ - {value_name: '市町村名1', name: 'sityouson-name1', type: string}
14
+ - {value_name: '市町村名2', name: 'sityouson-name2', type: string}
15
+ - {value_name: '市町村名3', name: 'sityouson-name3', type: string}
16
+ - {value_name: '読み仮名', name: 'yomigana', type: string}
17
+ out:
18
+ type: stdout
@@ -0,0 +1,10 @@
1
+ ���R�[�h,�s�����R�[�h,�n��R�[�h,����,�s������1,�s������2,�s������3,�ǂ݉���
2
+ 1,0,1000,�k�C��,,,,�ق������ǂ�
3
+ 1,100,1100,�k�C��,�D�y�s,,,�����ۂ낵
4
+ 1,101,1101,�k�C��,�D�y�s,,������,���イ������
5
+ 1,102,1102,�k�C��,�D�y�s,,�k��,������
6
+ 1,103,1103,�k�C��,�D�y�s,,����,�Ђ�����
7
+ 1,104,1104,�k�C��,�D�y�s,,���΋�,���낢����
8
+ 1,105,1105,�k�C��,�D�y�s,,�L����,�Ƃ�Ђ炭
9
+ 1,106,1106,�k�C��,�D�y�s,,���,�݂Ȃ݂�
10
+ 1,107,1107,�k�C��,�D�y�s,,����,�ɂ���
@@ -135,7 +135,9 @@ public class CsvGuessableParserPlugin
135
135
 
136
136
  if (task.getSchemaFile().isPresent()) {
137
137
  int schemaLine = task.getSchemaLine();
138
- task.setSkipHeaderLines(schemaLine); // TODO: use 'skip_header_line'
138
+ if (schemaLine > task.getSkipHeaderLines()) {
139
+ task.setSkipHeaderLines(schemaLine);
140
+ }
139
141
 
140
142
  String header = readHeader(task.getSchemaFile().get().getPath(), schemaLine, task.getCharset());
141
143
  log.debug(header);
@@ -6,13 +6,16 @@ import org.embulk.config.ConfigException;
6
6
  import org.embulk.config.ConfigLoader;
7
7
  import org.embulk.config.ConfigSource;
8
8
  import org.embulk.config.TaskSource;
9
+ import org.embulk.spi.Column;
9
10
  import org.embulk.spi.Exec;
10
11
  import org.embulk.spi.FileInput;
11
12
  import org.embulk.spi.ParserPlugin;
12
13
  import org.embulk.spi.Schema;
13
14
  import org.embulk.spi.TestPageBuilderReader.MockPageOutput;
15
+ import org.embulk.spi.type.Types;
14
16
  import org.embulk.spi.util.InputStreamFileInput;
15
- import org.embulk.standards.TestCsvParserPlugin;
17
+ import org.embulk.spi.util.Pages;
18
+ //import org.embulk.standards.TestCsvParserPlugin;
16
19
  import org.junit.Before;
17
20
  import org.junit.Rule;
18
21
  import org.junit.Test;
@@ -22,13 +25,14 @@ import java.io.File;
22
25
  import java.io.FileInputStream;
23
26
  import java.io.IOException;
24
27
  import java.io.InputStream;
28
+ import java.util.List;
25
29
 
26
30
  import static org.embulk.parser.csv_guessable.CsvGuessableParserPlugin.PluginTask;
27
31
  import static org.junit.Assert.assertEquals;
28
32
  import static org.junit.Assert.assertNull;
29
33
 
30
34
  public class TestCsvGuessableParserPlugin
31
- extends TestCsvParserPlugin
35
+ // extends TestCsvParserPlugin
32
36
  {
33
37
  @Rule
34
38
  public EmbulkTestRuntime runtime = new EmbulkTestRuntime();
@@ -38,6 +42,7 @@ public class TestCsvGuessableParserPlugin
38
42
 
39
43
  private CsvGuessableParserPlugin plugin;
40
44
  private MockPageOutput output;
45
+ private Schema schema;
41
46
 
42
47
  @Before
43
48
  public void createResouce()
@@ -46,12 +51,6 @@ public class TestCsvGuessableParserPlugin
46
51
  output = new MockPageOutput();
47
52
  }
48
53
 
49
- private ConfigSource getConfigFromYaml(String yaml)
50
- {
51
- ConfigLoader loader = new ConfigLoader(Exec.getModelManager());
52
- return loader.fromYamlString(yaml);
53
- }
54
-
55
54
  @Test(expected = ConfigException.class)
56
55
  public void checkColumnsRequired()
57
56
  {
@@ -102,27 +101,175 @@ public class TestCsvGuessableParserPlugin
102
101
  "schema_file: src/test/resources/org/embulk/parser/csv_guessable/data/test.csv\n" + // TODO: FIX PATH
103
102
  "schema_line: 1";
104
103
  ConfigSource config = getConfigFromYaml(configYaml);
105
- PluginTask task = config.loadConfig(PluginTask.class);
106
- // transaction(config, fileInput(new File(this.getClass().getResource("data/test.csv").getPath())));
104
+ transaction(config, fileInput("data/test.csv"));
105
+ List<Object[]> records = Pages.toObjects(schema, output.pages);
106
+ assertEquals(2, records.size());
107
+
108
+ Object[] record;
109
+ {
110
+ record = records.get(0);
111
+ assertEquals("100", record[0]);
112
+ assertEquals("test-title", record[1]);
113
+ assertEquals("ok", record[2]);
114
+ }
115
+ {
116
+ record = records.get(1);
117
+ assertEquals("191", record[0]);
118
+ assertEquals("title2", record[1]);
119
+ assertEquals("ng", record[2]);
120
+ }
121
+ }
122
+
123
+ @Test
124
+ public void specifyType()
125
+ throws Exception
126
+ {
127
+ String configYaml = "" +
128
+ "type: csv_guessable\n" +
129
+ "schema_file: src/test/resources/org/embulk/parser/csv_guessable/data/test.csv\n" +
130
+ "columns:\n" +
131
+ " - {name: 'id', type: long}\n" +
132
+ " - {name: 'title', type: string}\n" +
133
+ " - {name: 'status', type: string}";
134
+
135
+ ConfigSource config = getConfigFromYaml(configYaml);
136
+ transaction(config, fileInput("data/test.csv"));
137
+ List<Object[]> records = Pages.toObjects(schema, output.pages);
107
138
 
108
- // TODO: impl
139
+ Column column;
140
+ {
141
+ column = schema.getColumn(0);
142
+ assertEquals(Types.LONG, column.getType());
143
+ }
144
+ {
145
+ column = schema.getColumn(1);
146
+ assertEquals(Types.STRING, column.getType());
147
+ }
148
+ {
149
+ column = schema.getColumn(2);
150
+ assertEquals(Types.STRING, column.getType());
151
+ }
152
+
153
+ assertEquals(2, records.size());
154
+
155
+ Object[] record;
156
+ {
157
+ record = records.get(0);
158
+ assertEquals(100L, record[0]);
159
+ assertEquals("test-title", record[1]);
160
+ assertEquals("ok", record[2]);
161
+ }
162
+ {
163
+ record = records.get(1);
164
+ assertEquals(191L, record[0]);
165
+ assertEquals("title2", record[1]);
166
+ assertEquals("ng", record[2]);
167
+ }
109
168
  }
110
169
 
111
170
  @Test
112
- public void replaceColumnsMetadata()
171
+ public void renameColumn()
172
+ throws Exception
173
+ {
174
+ String configYaml = "" +
175
+ "type: csv_guessable\n" +
176
+ "schema_file: src/test/resources/org/embulk/parser/csv_guessable/data/test.csv\n" +
177
+ "columns:\n" +
178
+ " - {value_name: 'id', name: 'number', type: long}\n" +
179
+ " - {value_name: 'title', name: 'description', type: string}\n" +
180
+ " - {value_name: 'status', name: 'ok?', type: string}";
181
+ ConfigSource config = getConfigFromYaml(configYaml);
182
+ transaction(config, fileInput("data/test.csv"));
183
+
184
+ Column column;
185
+ {
186
+ column = schema.getColumn(0);
187
+ assertEquals("number", column.getName());
188
+ assertEquals(Types.LONG, column.getType());
189
+ }
190
+ {
191
+ column = schema.getColumn(1);
192
+ assertEquals("description", column.getName());
193
+ assertEquals(Types.STRING, column.getType());
194
+ }
195
+ {
196
+ column = schema.getColumn(2);
197
+ assertEquals("ok?", column.getName());
198
+ assertEquals(Types.STRING, column.getType());
199
+ }
200
+ }
201
+
202
+ @Test
203
+ public void renameColumnAndSpecifyType()
113
204
  throws Exception
114
205
  {
115
206
  String configYaml = "" +
116
207
  "type: csv_guessable\n" +
117
208
  "schema_file: src/test/resources/org/embulk/parser/csv_guessable/data/test.csv\n" + // TODO: FIX PATH
118
- "schema_line: 1\n" +
119
209
  "columns:\n" +
120
- "- {value_name: '#', name: 'number', type: long}\n" +
121
- "- {value_name: 'title', name: 'description', type: string}\n" +
122
- "- {value_name: 'status', name: 'ok?', type: string}";
210
+ " - {value_name: 'id', name: 'number', type: long}\n" +
211
+ " - {value_name: 'title', name: 'description', type: string}\n" +
212
+ " - {value_name: 'status', name: 'ok?', type: string}";
123
213
  ConfigSource config = getConfigFromYaml(configYaml);
214
+ transaction(config, fileInput("data/test.csv"));
124
215
 
125
- // TODO: impl
216
+ Column column;
217
+ {
218
+ column = schema.getColumn(0);
219
+ assertEquals("number", column.getName());
220
+ assertEquals(Types.LONG, column.getType());
221
+ }
222
+ {
223
+ column = schema.getColumn(1);
224
+ assertEquals("description", column.getName());
225
+ assertEquals(Types.STRING, column.getType());
226
+ }
227
+ {
228
+ column = schema.getColumn(2);
229
+ assertEquals("ok?", column.getName());
230
+ assertEquals(Types.STRING, column.getType());
231
+ }
232
+ }
233
+
234
+ @Test
235
+ public void skipHeaderLinesIsLargerThanHeaderLine()
236
+ throws Exception
237
+ {
238
+ String configYaml = "" +
239
+ "type: csv_guessable\n" +
240
+ "schema_file: src/test/resources/org/embulk/parser/csv_guessable/data/test.csv\n" + // TODO: FIX PATH
241
+ "skip_header_lines: 2\n" +
242
+ "columnes:\n" +
243
+ " - {value_name: 'id', type: long}\n" +
244
+ " - {value_name: 'title', type: string}\n" +
245
+ " - {value_name: 'status', type: string}";
246
+ ConfigSource config = getConfigFromYaml(configYaml);
247
+ transaction(config, fileInput("data/test.csv"));
248
+
249
+ List<Object[]> records = Pages.toObjects(schema, output.pages);
250
+ assertEquals(1, records.size());
251
+
252
+ Object[] record;
253
+ {
254
+ record = records.get(0);
255
+ assertEquals("191", record[0]);
256
+ assertEquals("title2", record[1]);
257
+ assertEquals("ng", record[2]);
258
+ }
259
+ }
260
+
261
+ private ConfigSource getConfigFromYaml(String yaml)
262
+ {
263
+ ConfigLoader loader = new ConfigLoader(Exec.getModelManager());
264
+ return loader.fromYamlString(yaml);
265
+ }
266
+
267
+ private FileInput fileInput(String path)
268
+ throws Exception
269
+ {
270
+ File file = new File(this.getClass().getResource(path).getPath());
271
+ FileInputStream in = new FileInputStream(file);
272
+ return new InputStreamFileInput(runtime.getBufferAllocator(), provider(in));
126
273
  }
127
274
 
128
275
  private void transaction(ConfigSource config, final FileInput input)
@@ -132,18 +279,12 @@ public class TestCsvGuessableParserPlugin
132
279
  @Override
133
280
  public void run(TaskSource taskSource, Schema schema)
134
281
  {
282
+ TestCsvGuessableParserPlugin.this.schema = schema;
135
283
  plugin.run(taskSource, schema, input, output);
136
284
  }
137
285
  });
138
286
  }
139
287
 
140
- private FileInput fileInput(File file)
141
- throws Exception
142
- {
143
- FileInputStream in = new FileInputStream(file);
144
- return new InputStreamFileInput(runtime.getBufferAllocator(), provider(in));
145
- }
146
-
147
288
  private InputStreamFileInput.IteratorProvider provider(InputStream... inputStreams)
148
289
  throws IOException
149
290
  {
metadata CHANGED
@@ -1,43 +1,43 @@
1
1
  --- !ruby/object:Gem::Specification
2
2
  name: embulk-parser-csv_guessable
3
3
  version: !ruby/object:Gem::Version
4
- version: 0.1.4
4
+ version: 0.1.5
5
5
  platform: ruby
6
6
  authors:
7
7
  - koooge
8
8
  autorequire:
9
9
  bindir: bin
10
10
  cert_chain: []
11
- date: 2017-06-06 00:00:00.000000000 Z
11
+ date: 2017-10-15 00:00:00.000000000 Z
12
12
  dependencies:
13
13
  - !ruby/object:Gem::Dependency
14
- requirement: !ruby/object:Gem::Requirement
14
+ name: bundler
15
+ version_requirements: !ruby/object:Gem::Requirement
15
16
  requirements:
16
17
  - - ~>
17
18
  - !ruby/object:Gem::Version
18
19
  version: '1.0'
19
- name: bundler
20
- prerelease: false
21
- type: :development
22
- version_requirements: !ruby/object:Gem::Requirement
20
+ requirement: !ruby/object:Gem::Requirement
23
21
  requirements:
24
22
  - - ~>
25
23
  - !ruby/object:Gem::Version
26
24
  version: '1.0'
25
+ prerelease: false
26
+ type: :development
27
27
  - !ruby/object:Gem::Dependency
28
- requirement: !ruby/object:Gem::Requirement
28
+ name: rake
29
+ version_requirements: !ruby/object:Gem::Requirement
29
30
  requirements:
30
31
  - - '>='
31
32
  - !ruby/object:Gem::Version
32
33
  version: '10.0'
33
- name: rake
34
- prerelease: false
35
- type: :development
36
- version_requirements: !ruby/object:Gem::Requirement
34
+ requirement: !ruby/object:Gem::Requirement
37
35
  requirements:
38
36
  - - '>='
39
37
  - !ruby/object:Gem::Version
40
38
  version: '10.0'
39
+ prerelease: false
40
+ type: :development
41
41
  description: Parses Guessable Csv files read by other file input plugins.
42
42
  email:
43
43
  - koooooge@gmail.com
@@ -45,6 +45,7 @@ executables: []
45
45
  extensions: []
46
46
  extra_rdoc_files: []
47
47
  files:
48
+ - .circleci/config.yml
48
49
  - .gitignore
49
50
  - LICENSE.txt
50
51
  - README.md
@@ -57,6 +58,11 @@ files:
57
58
  - gradlew.bat
58
59
  - lib/embulk/guess/csv_guessable.rb
59
60
  - lib/embulk/parser/csv_guessable.rb
61
+ - samples/sample1/config.yml
62
+ - samples/sample1/config_set_type.yml
63
+ - samples/sample1/sample1.csv
64
+ - samples/sample2/config_rename.yml
65
+ - samples/sample2/sample2.csv
60
66
  - src/main/java/org/embulk/parser/csv_guessable/CsvGuessableParserPlugin.java
61
67
  - src/main/java/org/embulk/parser/csv_guessable/CsvTokenizer.java
62
68
  - src/test/java/org/embulk/parser/csv_guessable/TestCsvGuessableParserPlugin.java
@@ -67,11 +73,11 @@ files:
67
73
  - src/test/resources/org/embulk/parser/csv_guessable/yml/original-csv.yml
68
74
  - src/test/resources/org/embulk/parser/csv_guessable/yml/replace_column_name.yml
69
75
  - classpath/commons-lang3-3.5.jar
70
- - classpath/embulk-parser-csv_guessable-0.1.4.jar
76
+ - classpath/embulk-parser-csv_guessable-0.1.5.jar
77
+ - classpath/embulk-standards-0.8.35.jar
71
78
  - classpath/opencsv-3.9.jar
72
79
  - classpath/commons-beanutils-1.9.3.jar
73
80
  - classpath/commons-compress-1.10.jar
74
- - classpath/embulk-standards-0.8.22.jar
75
81
  - classpath/commons-collections-3.2.2.jar
76
82
  - classpath/commons-logging-1.2.jar
77
83
  homepage: https://github.com/koooge/embulk-parser-csv_guessable