Last active
December 15, 2015 14:09
-
-
Save vsizov/5271991 to your computer and use it in GitHub Desktop.
duke config
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
<duke> | |
<schema> | |
<threshold>0.8</threshold> | |
<path>temp</path> | |
<property type="id"> | |
<name>ID</name> | |
</property> | |
<property> | |
<name>FIRST_NAME</name> | |
<comparator>no.priv.garshol.duke.comparators.ExactComparator</comparator> | |
<low>0.2</low> | |
<high>0.9</high> | |
</property> | |
<property> | |
<name>LAST_NAME</name> | |
<comparator>no.priv.garshol.duke.comparators.ExactComparator</comparator> | |
<low>0.2</low> | |
<high>0.9</high> | |
</property> | |
<property> | |
<name>ZIPCODE</name> | |
<comparator>no.priv.garshol.duke.comparators.ExactComparator</comparator> | |
<low>0.4</low> | |
<high>0.8</high> | |
</property> | |
<property> | |
<name>CITY</name> | |
<comparator>no.priv.garshol.duke.comparators.ExactComparator</comparator> | |
<low>0.4</low> | |
<high>0.8</high> | |
</property> | |
<property> | |
<name>STATE</name> | |
<comparator>no.priv.garshol.duke.comparators.ExactComparator</comparator> | |
<low>0.4</low> | |
<high>0.8</high> | |
</property> | |
<property> | |
<name>ADDRESS</name> | |
<comparator>no.priv.garshol.duke.comparators.WeightedLevenshtein</comparator> | |
<low>0.4</low> | |
<high>0.8</high> | |
</property> | |
<property> | |
<name>AGE</name> | |
<comparator>no.priv.garshol.duke.comparators.ExactComparator</comparator> | |
<low>0.4</low> | |
<high>0.8</high> | |
</property> | |
</schema> | |
<group> | |
<jdbc> | |
<param name="driver-class" value="com.mysql.jdbc.Driver"/> | |
<param name="connection-string" value="jdbc:mysql://localhost/duke_test"/> | |
<param name="user-name" value="root"/> | |
<param name="password" value="1"/> | |
<param name="query" value=" | |
SELECT *, CONCAT_WS(', ', address1, address2) address, (YEAR(CURDATE())-YEAR(birthday)) as age FROM users | |
"/> | |
<column name="id" property="ID"/> | |
<column name="first_name" property="FIRST_NAME" cleaner="no.priv.garshol.duke.cleaners.LowerCaseNormalizeCleaner" /> | |
<column name="last_name" property="LAST_NAME" cleaner="no.priv.garshol.duke.cleaners.LowerCaseNormalizeCleaner" /> | |
<column name="zipcode" property="ZIPCODE" cleaner="no.priv.garshol.duke.cleaners.LowerCaseNormalizeCleaner" /> | |
<column name="city" property="CITY" cleaner="no.priv.garshol.duke.cleaners.LowerCaseNormalizeCleaner" /> | |
<column name="statecode" property="STATE" cleaner="no.priv.garshol.duke.cleaners.LowerCaseNormalizeCleaner" /> | |
<column name="address" property="ADDRESS" cleaner="no.priv.garshol.duke.cleaners.LowerCaseNormalizeCleaner" /> | |
<column name="age" property="AGE" cleaner="no.priv.garshol.duke.cleaners.DigitsOnlyCleaner" /> | |
... | |
</jdbc> | |
</group> | |
<group> | |
<jdbc> | |
<param name="driver-class" value="com.mysql.jdbc.Driver"/> | |
<param name="connection-string" value="jdbc:mysql://localhost/duke_test"/> | |
<param name="user-name" value="root"/> | |
<param name="password" value="1"/> | |
<param name="query" value=" | |
select offender_id, firstname, lastname, zipcode, city, state, if(dob='0000-00-00', null, dob) as dob, street1, age | |
FROM family_watchdog_offender | |
"/> | |
<column name="offender_id" property="ID"/> | |
<column name="firstname" property="FIRST_NAME" cleaner="no.priv.garshol.duke.cleaners.LowerCaseNormalizeCleaner" /> | |
<column name="lastname" property="LAST_NAME" cleaner="no.priv.garshol.duke.cleaners.LowerCaseNormalizeCleaner" /> | |
<column name="zipcode" property="ZIPCODE" cleaner="no.priv.garshol.duke.cleaners.LowerCaseNormalizeCleaner" /> | |
<column name="city" property="CITY" cleaner="no.priv.garshol.duke.cleaners.LowerCaseNormalizeCleaner" /> | |
<column name="state" property="STATE" cleaner="no.priv.garshol.duke.cleaners.LowerCaseNormalizeCleaner" /> | |
<column name="street1" property="ADDRESS" cleaner="no.priv.garshol.duke.cleaners.LowerCaseNormalizeCleaner" /> | |
<column name="age" property="AGE" cleaner="no.priv.garshol.duke.cleaners.DigitsOnlyCleaner" /> | |
... | |
</jdbc> | |
</group> | |
</duke> |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment