This is an automated email from the ASF dual-hosted git repository.

hansva pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/incubator-hop.git


The following commit(s) were added to refs/heads/master by this push:
     new 9064a72  HOP-2842: add secondstring lib and create integration test
     new 70f79aa  Merge pull request #792 from hansva/master
9064a72 is described below

commit 9064a7284e983a860f9980d06990073d5965f199
Author: Hans Van Akelyen <[email protected]>
AuthorDate: Thu May 6 15:13:19 2021 +0200

    HOP-2842: add secondstring lib and create integration test
---
 assemblies/plugins/transforms/fuzzymatch/pom.xml   |   5 +
 .../fuzzymatch/src/assembly/assembly.xml           |   7 +
 integration-tests/transforms/0007-fuzzymatch.hpl   | 271 +++++++++++++++++++++
 .../transforms/datasets/golden-fuzzymatch.csv      | 101 ++++++++
 .../transforms/main-0007-fuzzymatch.hwf            |  61 +++++
 .../metadata/dataset/golden-fuzzymatch.json        | 104 ++++++++
 .../metadata/unit-test/0007-fuzzymatch UNIT.json   |  72 ++++++
 7 files changed, 621 insertions(+)

diff --git a/assemblies/plugins/transforms/fuzzymatch/pom.xml 
b/assemblies/plugins/transforms/fuzzymatch/pom.xml
index dd768f5..69905de 100644
--- a/assemblies/plugins/transforms/fuzzymatch/pom.xml
+++ b/assemblies/plugins/transforms/fuzzymatch/pom.xml
@@ -42,5 +42,10 @@
             <artifactId>hop-transform-fuzzymatch</artifactId>
             <version>${project.version}</version>
         </dependency>
+        <dependency>
+            <groupId>com.wcohen</groupId>
+            <artifactId>com.wcohen.secondstring</artifactId>
+            <version>0.1</version>
+        </dependency>
     </dependencies>
 </project>
\ No newline at end of file
diff --git a/assemblies/plugins/transforms/fuzzymatch/src/assembly/assembly.xml 
b/assemblies/plugins/transforms/fuzzymatch/src/assembly/assembly.xml
index 59d8389..aa971c0 100644
--- a/assemblies/plugins/transforms/fuzzymatch/src/assembly/assembly.xml
+++ b/assemblies/plugins/transforms/fuzzymatch/src/assembly/assembly.xml
@@ -46,5 +46,12 @@
                 <include>org.apache.hop:hop-transform-fuzzymatch:jar</include>
             </includes>
         </dependencySet>
+        <dependencySet>
+            <useProjectArtifact>false</useProjectArtifact>
+            <outputDirectory>lib</outputDirectory>
+            <includes>
+                <include>com.wcohen:com.wcohen.secondstring:jar</include>
+            </includes>
+        </dependencySet>
     </dependencySets>
 </assembly>
\ No newline at end of file
diff --git a/integration-tests/transforms/0007-fuzzymatch.hpl 
b/integration-tests/transforms/0007-fuzzymatch.hpl
new file mode 100644
index 0000000..5906317
--- /dev/null
+++ b/integration-tests/transforms/0007-fuzzymatch.hpl
@@ -0,0 +1,271 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<pipeline>
+  <info>
+    <name>0007-fuzzymatch</name>
+    <name_sync_with_filename>Y</name_sync_with_filename>
+    <description/>
+    <extended_description/>
+    <pipeline_version/>
+    <pipeline_type>Normal</pipeline_type>
+    <parameters>
+    </parameters>
+    <capture_transform_performance>N</capture_transform_performance>
+    
<transform_performance_capturing_delay>1000</transform_performance_capturing_delay>
+    
<transform_performance_capturing_size_limit>100</transform_performance_capturing_size_limit>
+    <created_user>-</created_user>
+    <created_date>2021/04/19 12:06:20.350</created_date>
+    <modified_user>-</modified_user>
+    <modified_date>2021/04/19 12:06:20.350</modified_date>
+    <key_for_session_key>H4sIAAAAAAAAAAMAAAAAAAAAAAA=</key_for_session_key>
+    <is_key_private>N</is_key_private>
+  </info>
+  <notepads>
+  </notepads>
+  <order>
+    <hop>
+      <from>Fuzzy match</from>
+      <to>Output</to>
+      <enabled>Y</enabled>
+    </hop>
+    <hop>
+      <from>files/customers-100.txt</from>
+      <to>Fuzzy match</to>
+      <enabled>Y</enabled>
+    </hop>
+    <hop>
+      <from>Data grid</from>
+      <to>Fuzzy match</to>
+      <enabled>Y</enabled>
+    </hop>
+  </order>
+  <transform>
+    <name>Fuzzy match</name>
+    <type>FuzzyMatch</type>
+    <description/>
+    <distribute>Y</distribute>
+    <custom_distribution/>
+    <copies>1</copies>
+    <partitioning>
+      <method>none</method>
+      <schema_name/>
+    </partitioning>
+    <from>Data grid</from>
+    <lookupfield>name</lookupfield>
+    <mainstreamfield>name</mainstreamfield>
+    <outputmatchfield>match</outputmatchfield>
+    <outputvaluefield>measure value</outputvaluefield>
+    <caseSensitive>N</caseSensitive>
+    <closervalue>Y</closervalue>
+    <minimalValue>0</minimalValue>
+    <maximalValue>1</maximalValue>
+    <separator>,</separator>
+    <algorithm>soundex</algorithm>
+    <lookup>
+    </lookup>
+    <attributes/>
+    <GUI>
+      <xloc>304</xloc>
+      <yloc>64</yloc>
+    </GUI>
+  </transform>
+  <transform>
+    <name>Output</name>
+    <type>Dummy</type>
+    <description/>
+    <distribute>Y</distribute>
+    <custom_distribution/>
+    <copies>1</copies>
+    <partitioning>
+      <method>none</method>
+      <schema_name/>
+    </partitioning>
+    <attributes/>
+    <GUI>
+      <xloc>528</xloc>
+      <yloc>64</yloc>
+    </GUI>
+  </transform>
+  <transform>
+    <name>files/customers-100.txt</name>
+    <type>CSVInput</type>
+    <description/>
+    <distribute>Y</distribute>
+    <custom_distribution/>
+    <copies>1</copies>
+    <partitioning>
+      <method>none</method>
+      <schema_name/>
+    </partitioning>
+    <filename>${PROJECT_HOME}/files/customers-100.txt</filename>
+    <filename_field/>
+    <rownum_field/>
+    <include_filename>N</include_filename>
+    <separator>;</separator>
+    <enclosure>"</enclosure>
+    <header>Y</header>
+    <buffer_size>50000</buffer_size>
+    <lazy_conversion>N</lazy_conversion>
+    <add_filename_result>N</add_filename_result>
+    <parallel>N</parallel>
+    <newline_possible>N</newline_possible>
+    <encoding/>
+    <fields>
+      <field>
+        <name>id</name>
+        <type>Integer</type>
+        <format> #</format>
+        <currency>$</currency>
+        <decimal>.</decimal>
+        <group>,</group>
+        <length>15</length>
+        <precision>0</precision>
+        <trim_type>none</trim_type>
+      </field>
+      <field>
+        <name>name</name>
+        <type>String</type>
+        <format/>
+        <currency>$</currency>
+        <decimal>.</decimal>
+        <group>,</group>
+        <length>50</length>
+        <precision>-1</precision>
+        <trim_type>none</trim_type>
+      </field>
+      <field>
+        <name>firstname</name>
+        <type>String</type>
+        <format/>
+        <currency>$</currency>
+        <decimal>.</decimal>
+        <group>,</group>
+        <length>50</length>
+        <precision>-1</precision>
+        <trim_type>none</trim_type>
+      </field>
+      <field>
+        <name>zip</name>
+        <type>String</type>
+        <format/>
+        <currency>$</currency>
+        <decimal>.</decimal>
+        <group>,</group>
+        <length>30</length>
+        <precision>0</precision>
+        <trim_type>none</trim_type>
+      </field>
+      <field>
+        <name>city</name>
+        <type>String</type>
+        <format/>
+        <currency>$</currency>
+        <decimal>.</decimal>
+        <group>,</group>
+        <length>8</length>
+        <precision>-1</precision>
+        <trim_type>none</trim_type>
+      </field>
+      <field>
+        <name>birthdate</name>
+        <type>Date</type>
+        <format>yyyy/MM/dd</format>
+        <currency>$</currency>
+        <decimal>.</decimal>
+        <group>,</group>
+        <length>-1</length>
+        <precision>-1</precision>
+        <trim_type>none</trim_type>
+      </field>
+      <field>
+        <name>street</name>
+        <type>String</type>
+        <format/>
+        <currency>$</currency>
+        <decimal>.</decimal>
+        <group>,</group>
+        <length>11</length>
+        <precision>-1</precision>
+        <trim_type>none</trim_type>
+      </field>
+      <field>
+        <name>housenr</name>
+        <type>String</type>
+        <format/>
+        <currency>$</currency>
+        <decimal>.</decimal>
+        <group>,</group>
+        <length>50</length>
+        <precision>0</precision>
+        <trim_type>none</trim_type>
+      </field>
+      <field>
+        <name>stateCode</name>
+        <type>String</type>
+        <format/>
+        <currency>$</currency>
+        <decimal>.</decimal>
+        <group>,</group>
+        <length>10</length>
+        <precision>-1</precision>
+        <trim_type>none</trim_type>
+      </field>
+      <field>
+        <name>state</name>
+        <type>String</type>
+        <format/>
+        <currency>$</currency>
+        <decimal>.</decimal>
+        <group>,</group>
+        <length>50</length>
+        <precision>-1</precision>
+        <trim_type>none</trim_type>
+      </field>
+    </fields>
+    <attributes/>
+    <GUI>
+      <xloc>112</xloc>
+      <yloc>64</yloc>
+    </GUI>
+  </transform>
+  <transform>
+    <name>Data grid</name>
+    <type>DataGrid</type>
+    <description/>
+    <distribute>Y</distribute>
+    <custom_distribution/>
+    <copies>1</copies>
+    <partitioning>
+      <method>none</method>
+      <schema_name/>
+    </partitioning>
+    <fields>
+      <field>
+        <name>name</name>
+        <type>String</type>
+        <format/>
+        <currency/>
+        <decimal/>
+        <group/>
+        <length>-1</length>
+        <precision>-1</precision>
+        <set_empty_string>N</set_empty_string>
+      </field>
+    </fields>
+    <data>
+      <line>
+        <item>jwcdf-name</item>
+      </line>
+      <line>
+        <item>rdjin-name</item>
+      </line>
+    </data>
+    <attributes/>
+    <GUI>
+      <xloc>303</xloc>
+      <yloc>162</yloc>
+    </GUI>
+  </transform>
+  <transform_error_handling>
+  </transform_error_handling>
+  <attributes/>
+</pipeline>
diff --git a/integration-tests/transforms/datasets/golden-fuzzymatch.csv 
b/integration-tests/transforms/datasets/golden-fuzzymatch.csv
new file mode 100644
index 0000000..879d1a9
--- /dev/null
+++ b/integration-tests/transforms/datasets/golden-fuzzymatch.csv
@@ -0,0 +1,101 @@
+id,name,firstname,zip,city,birthdate,street,housenr,stateCode,state,match,measure
 value
+" 1",jwcdf-name,fsj-firstname," 13520",oem-city,1954/02/07,amrb-street," 
145",AK,ALASKA,jwcdf-name,J315
+" 2",flhxu-name,tum-firstname," 17520",buo-city,1966/04/24,wfyz-street," 
96",GA,GEORGIA,,
+" 3",xthfg-name,gfe-firstname," 12560",vtz-city,1990/01/11,doxx-street," 
46",NJ,NEW JERSEY,,
+" 4",ulzrz-name,bnl-firstname," 11620",prz-city,1966/08/02,bxqn-street," 
104",NY,NEW YORK,,
+" 5",oxhyr-name,onx-firstname," 15180",bpn-city,1970/11/14,pksn-street," 
133",IN,INDIANA,,
+" 6",fiqjz-name,sce-firstname," 16020",fnn-city,1954/09/24,wbhg-street," 
35",MD,MARYLAND,,
+" 7",tkiat-name,xti-firstname," 12720",stt-city,1966/08/11,tvnf-street," 
21",PA,PENNSYLVANIA,,
+" 8",kljcz-name,uqd-firstname," 13340",ntt-city,1987/01/15,jyje-street," 
10",PW,PALAU,,
+" 9",pgunz-name,hcm-firstname," 16680",gxh-city,1970/11/08,shbe-street," 
184",NC,NORTH CAROLINA,,
+" 10",oyjha-name,uhj-firstname," 18880",uyg-city,1966/04/10,bjgw-street," 
176",AR,ARKANSAS,,
+" 11",igxbd-name,uph-firstname," 13480",ndh-city,1962/12/03,jdcd-street," 
151",NH,NEW HAMPSHIRE,,
+" 12",vnaov-name,wha-firstname," 13120",egm-city,1954/03/28,hpep-street," 
20",CA,CALIFORNIA,,
+" 13",dauuz-name,hwg-firstname," 13740",khn-city,1958/05/15,etqx-street," 
5",OK,OKLAHOMA,,
+" 14",gkuuo-name,kkb-firstname," 13560",xdt-city,1962/04/07,sdoj-street," 
35",MT,MONTANA,,
+" 15",wdhze-name,jjk-firstname," 16900",due-city,1970/07/17,pmmu-street," 
174",AS,AMERICAN SAMOA,,
+" 16",ncayz-name,ynb-firstname," 15720",lxj-city,1974/04/27,mdtb-street," 
109",MA,MASSACHUSETTS,,
+" 17",rdjin-name,hhu-firstname," 14480",lpc-city,1958/11/16,wxik-street," 
145",KY,KENTUCKY,rdjin-name,R325
+" 18",nxzij-name,bdl-firstname," 10740",avx-city,1958/02/20,nybz-street," 
138",WI,WISCONSIN,,
+" 19",xgrzc-name,dxw-firstname," 18900",vpq-city,1990/11/16,wzjh-street," 
58",ME,MAINE,,
+" 20",ehgrn-name,vbe-firstname," 17500",cik-city,1978/05/21,ucnw-street," 
135",MD,MARYLAND,,
+" 21",gctjx-name,upx-firstname," 11960",yqr-city,1958/03/03,rlko-street," 
141",TN,TENNESSEE,,
+" 22",ptzmg-name,hva-firstname," 15740",gux-city,1978/05/04,pugy-street," 
122",VI,VIRGIN ISLANDS,,
+" 23",eyeti-name,gnw-firstname," 17420",eko-city,1962/10/26,ylph-street," 
61",NC,NORTH CAROLINA,,
+" 24",wccwo-name,zpj-firstname," 16600",uim-city,1962/09/29,ygih-street," 
26",WA,WASHINGTON,,
+" 25",bwkoe-name,ayl-firstname," 18660",rtw-city,1978/07/16,mzww-street," 
179",CA,CALIFORNIA,,
+" 26",rezku-name,zio-firstname," 19080",nvt-city,1982/07/14,wwkd-street," 
91",CA,CALIFORNIA,,
+" 27",mjlsk-name,ecx-firstname," 10800",yxu-city,1950/12/11,vttb-street," 
195",MO,MISSOURI,,
+" 28",wdjsi-name,aoq-firstname," 13660",smo-city,1954/02/01,kako-street," 
7",NV,NEVADA,,
+" 29",mwfnd-name,nyb-firstname," 19760",bbu-city,1986/09/23,apdi-street," 
91",MS,MISSISSIPPI,,
+" 30",vtuoz-name,jhh-firstname," 17620",vad-city,1982/05/05,kzup-street," 
79",GA,GEORGIA,,
+" 31",rhhxk-name,ndr-firstname," 16760",fub-city,1978/11/12,regd-street," 
55",OK,OKLAHOMA,,
+" 32",lpstk-name,mqz-firstname," 18940",tnr-city,1982/09/16,cdhf-street," 
4",SD,SOUTH DAKOTA,,
+" 33",ldhyr-name,yts-firstname," 12000",auk-city,1986/11/14,abph-street," 
147",IN,INDIANA,,
+" 34",cjdml-name,iti-firstname," 16900",wkq-city,1970/06/05,npow-street," 
96",NH,NEW HAMPSHIRE,,
+" 35",cpenz-name,sbi-firstname," 16380",ssl-city,1962/08/19,kilz-street," 
44",MS,MISSISSIPPI,,
+" 36",rxtbg-name,anr-firstname," 14720",bqc-city,1958/08/10,pudg-street," 
140",NV,NEVADA,,
+" 37",udblf-name,raa-firstname," 11500",wli-city,1978/12/13,xomd-street," 
41",PW,PALAU,,
+" 38",vvyce-name,gep-firstname," 13740",gtd-city,1982/05/23,kwbv-street," 
123",undefined,undefined,,
+" 39",kwfnz-name,ucu-firstname," 10580",sns-city,1978/08/18,nnun-street," 
20",OK,OKLAHOMA,,
+" 40",zxydx-name,tml-firstname," 14680",jda-city,1974/05/29,wfjn-street," 
157",DC,DISTRICT OF COLUMBIA,,
+" 41",bfscx-name,jnl-firstname," 16920",yyg-city,1970/11/30,cgfh-street," 
178",CO,COLORADO,,
+" 42",qitur-name,yra-firstname," 15560",ijp-city,1978/01/30,fonc-street," 
155",AK,ALASKA,,
+" 43",msixi-name,ynb-firstname," 12720",ksl-city,1958/07/17,zpjw-street," 
46",VI,VIRGIN ISLANDS,,
+" 44",wzkjq-name,rgh-firstname," 19000",hkm-city,1974/08/12,yixf-street," 
134",CA,CALIFORNIA,,
+" 45",dqfmf-name,yxr-firstname," 13840",vie-city,1962/10/23,stvx-street," 
39",TX,TEXAS,,
+" 46",biluz-name,uqe-firstname," 17760",wkq-city,1962/07/27,embn-street," 
183",PW,PALAU,,
+" 47",wahfx-name,zwd-firstname," 13240",vic-city,1974/03/27,axpw-street," 
131",UT,UTAH,,
+" 48",denwt-name,bta-firstname," 17300",hhj-city,1986/12/20,orwy-street," 
11",WV,WEST VIRGINIA,,
+" 49",akdmy-name,ybz-firstname," 14560",wtx-city,1962/11/08,nwba-street," 
123",MP,NORTHERN MARIANA ISLANDS,,
+" 50",hqafg-name,nht-firstname," 16080",gfu-city,1951/01/12,spsq-street," 
45",LA,LOUISIANA,,
+" 51",zhmbl-name,lnw-firstname," 17460",hse-city,1986/12/21,scis-street," 
97",GA,GEORGIA,,
+" 52",snwnj-name,jyy-firstname," 16400",hsz-city,1966/02/15,imhl-street," 
42",NC,NORTH CAROLINA,,
+" 53",fuyla-name,mmp-firstname," 11840",hgu-city,1986/08/16,ixiz-street," 
145",NC,NORTH CAROLINA,,
+" 54",yvfqz-name,prz-firstname," 11260",wjl-city,1982/05/06,fbzd-street," 
97",MO,MISSOURI,,
+" 55",usbgq-name,vhd-firstname," 14080",dsb-city,1958/04/01,ggoc-street," 
54",KS,KANSAS,,
+" 56",yaeni-name,zpy-firstname," 19100",sen-city,1954/12/10,sbsw-street," 
158",HI,HAWAII,,
+" 57",fgxvr-name,vzi-firstname," 17520",lcf-city,1958/11/01,nbdv-street," 
10",GU,GUAM,,
+" 58",tqpbq-name,rwr-firstname," 19140",zpd-city,1978/08/23,npvb-street," 
190",DC,DISTRICT OF COLUMBIA,,
+" 59",ieigg-name,ayq-firstname," 12960",ljc-city,1962/07/05,dnjz-street," 
163",FL,FLORIDA,,
+" 60",rfvzu-name,edm-firstname," 13340",kvz-city,1954/12/08,eijd-street," 
4",RI,RHODE ISLAND,,
+" 61",pduwm-name,gqb-firstname," 14240",cyr-city,1954/07/03,ndux-street," 
13",SD,SOUTH DAKOTA,,
+" 62",yyixf-name,yzt-firstname," 18020",lwx-city,1974/01/29,iede-street," 
120",NV,NEVADA,,
+" 63",dkszq-name,ytd-firstname," 14700",zwh-city,1979/01/11,nbjz-street," 
65",AS,AMERICAN SAMOA,,
+" 64",slkzv-name,zbg-firstname," 19880",oee-city,1978/11/01,sphg-street," 
119",OK,OKLAHOMA,,
+" 65",nvxim-name,phc-firstname," 19220",vgg-city,1991/01/24,juok-street," 
106",FM,FEDERATED STATES OF MICRONESIA,,
+" 66",piyfg-name,xtn-firstname," 13760",nde-city,1954/07/22,vfrv-street," 
11",NY,NEW YORK,,
+" 67",jnusz-name,mjw-firstname," 12640",nwb-city,1986/08/23,kcsa-street," 
138",VA,VIRGINIA,,
+" 68",jnypj-name,ioq-firstname," 17000",zqy-city,1986/01/09,croe-street," 
119",PW,PALAU,,
+" 69",uohts-name,btx-firstname," 13480",dal-city,1990/10/22,llyw-street," 
150",WA,WASHINGTON,,
+" 70",aavpj-name,pvw-firstname," 13780",lai-city,1954/09/23,nygu-street," 
171",FL,FLORIDA,,
+" 71",nbjcj-name,rsf-firstname," 12000",kjl-city,1986/06/30,ijsb-street," 
123",ID,IDAHO,,
+" 72",syjxh-name,gkq-firstname," 19960",rmd-city,1978/10/26,qmyp-street," 
161",MN,MINNESOTA,,
+" 73",vkojz-name,ryo-firstname," 14300",bmz-city,1954/09/11,gcpj-street," 
71",ND,NORTH DAKOTA,,
+" 74",pqzfw-name,kld-firstname," 16400",qvq-city,1962/09/09,dhbv-street," 
92",ND,NORTH DAKOTA,,
+" 75",owvjk-name,fez-firstname," 19740",ldb-city,1978/06/14,kabf-street," 
87",VA,VIRGINIA,,
+" 76",qsfih-name,ixe-firstname," 16860",qvr-city,1987/01/07,qean-street," 
159",CO,COLORADO,,
+" 77",slixq-name,gmb-firstname," 19980",ftt-city,1982/06/22,xinx-street," 
111",VT,VERMONT,,
+" 78",eegsa-name,xlc-firstname," 12680",byk-city,1954/04/23,beul-street," 
56",MD,MARYLAND,,
+" 79",phevp-name,ihs-firstname," 16120",adc-city,1978/04/25,voig-street," 
98",NM,NEW MEXICO,,
+" 80",njfoe-name,tag-firstname," 16580",tnr-city,1966/12/04,dhky-street," 
108",LA,LOUISIANA,,
+" 81",bdncx-name,hcd-firstname," 11260",xcl-city,1970/07/02,jvlp-street," 
49",GA,GEORGIA,,
+" 82",ikedo-name,tks-firstname," 17460",odl-city,1958/08/25,iaaq-street," 
8",GU,GUAM,,
+" 83",iafxy-name,vur-firstname," 11480",hgt-city,1962/08/03,hmec-street," 
164",TX,TEXAS,,
+" 84",lafhf-name,ssz-firstname," 19560",wwp-city,1951/01/25,mxmq-street," 
96",IN,INDIANA,,
+" 85",okyny-name,hbu-firstname," 16800",yok-city,1978/03/28,ipjz-street," 
135",NV,NEVADA,,
+" 86",hznby-name,fwy-firstname," 13680",wbi-city,1970/07/25,mxui-street," 
170",CT,CONNECTICUT,,
+" 87",ztpoa-name,rzk-firstname," 18500",qum-city,1970/07/26,blqr-street," 
152",ME,MAINE,,
+" 88",gitxz-name,axt-firstname," 11800",fck-city,1974/01/12,tmjw-street," 
189",SD,SOUTH DAKOTA,,
+" 89",ziomm-name,mcv-firstname," 12940",iwq-city,1950/10/22,hqgj-street," 
140",DC,DISTRICT OF COLUMBIA,,
+" 90",otncg-name,tuy-firstname," 16540",ulk-city,1971/01/24,yuia-street," 
166",TX,TEXAS,,
+" 91",cnabb-name,hoq-firstname," 16300",tuw-city,1962/06/17,ujvv-street," 
61",ME,MAINE,,
+" 92",ucogf-name,ggc-firstname," 14500",fsj-city,1978/02/08,asfi-street," 
53",WV,WEST VIRGINIA,,
+" 93",lbpmf-name,sdt-firstname," 10780",ewj-city,1978/03/08,hxsp-street," 
102",NV,NEVADA,,
+" 94",tieqq-name,uyu-firstname," 17740",wea-city,1966/10/31,abpl-street," 
187",MO,MISSOURI,,
+" 95",fsgwf-name,vjd-firstname," 12460",ads-city,1970/11/29,yeou-street," 
10",MA,MASSACHUSETTS,,
+" 96",reeba-name,kzs-firstname," 13100",zhc-city,1966/07/08,abmv-street," 
88",FL,FLORIDA,,
+" 97",shybc-name,gcp-firstname," 10660",ahg-city,1950/12/15,hrqy-street," 
174",KS,KANSAS,,
+" 98",phszr-name,sst-firstname," 13080",ydd-city,1954/09/23,quqn-street," 
2",RI,RHODE ISLAND,,
+" 99",jteco-name,fxc-firstname," 19760",agr-city,1986/05/06,dzxc-street," 
108",MD,MARYLAND,,
+" 100",qvaar-name,icx-firstname," 16120",boc-city,1978/08/04,bfzf-street," 
12",NM,NEW MEXICO,,
diff --git a/integration-tests/transforms/main-0007-fuzzymatch.hwf 
b/integration-tests/transforms/main-0007-fuzzymatch.hwf
new file mode 100644
index 0000000..0bc5aba
--- /dev/null
+++ b/integration-tests/transforms/main-0007-fuzzymatch.hwf
@@ -0,0 +1,61 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<workflow>
+  <name>main-0007-fuzzymatch</name>
+  <name_sync_with_filename>Y</name_sync_with_filename>
+  <description/>
+  <extended_description/>
+  <workflow_version/>
+  <created_user>-</created_user>
+  <created_date>2021/04/19 12:05:51.497</created_date>
+  <modified_user>-</modified_user>
+  <modified_date>2021/04/19 12:05:51.497</modified_date>
+  <parameters>
+    </parameters>
+  <actions>
+    <action>
+      <name>Start</name>
+      <description/>
+      <type>SPECIAL</type>
+      <attributes/>
+      <repeat>N</repeat>
+      <schedulerType>0</schedulerType>
+      <intervalSeconds>0</intervalSeconds>
+      <intervalMinutes>60</intervalMinutes>
+      <hour>12</hour>
+      <minutes>0</minutes>
+      <weekDay>1</weekDay>
+      <DayOfMonth>1</DayOfMonth>
+      <parallel>N</parallel>
+      <xloc>80</xloc>
+      <yloc>80</yloc>
+      <attributes_hac/>
+    </action>
+    <action>
+      <name>Run Group By tests</name>
+      <description/>
+      <type>RunPipelineTests</type>
+      <attributes/>
+      <test_names>
+        <test_name>
+          <name>0007-fuzzymatch UNIT</name>
+        </test_name>
+      </test_names>
+      <parallel>N</parallel>
+      <xloc>304</xloc>
+      <yloc>80</yloc>
+      <attributes_hac/>
+    </action>
+  </actions>
+  <hops>
+    <hop>
+      <from>Start</from>
+      <to>Run Group By tests</to>
+      <enabled>Y</enabled>
+      <evaluation>Y</evaluation>
+      <unconditional>Y</unconditional>
+    </hop>
+  </hops>
+  <notepads>
+  </notepads>
+  <attributes/>
+</workflow>
diff --git 
a/integration-tests/transforms/metadata/dataset/golden-fuzzymatch.json 
b/integration-tests/transforms/metadata/dataset/golden-fuzzymatch.json
new file mode 100644
index 0000000..1b34987
--- /dev/null
+++ b/integration-tests/transforms/metadata/dataset/golden-fuzzymatch.json
@@ -0,0 +1,104 @@
+{
+  "base_filename": "golden-fuzzymatch.csv",
+  "name": "golden-fuzzymatch",
+  "description": "",
+  "dataset_fields": [
+    {
+      "field_comment": "",
+      "field_length": 15,
+      "field_type": 5,
+      "field_precision": 0,
+      "field_format": " #",
+      "field_name": "id"
+    },
+    {
+      "field_comment": "",
+      "field_length": 50,
+      "field_type": 2,
+      "field_precision": -1,
+      "field_format": "",
+      "field_name": "name"
+    },
+    {
+      "field_comment": "",
+      "field_length": 50,
+      "field_type": 2,
+      "field_precision": -1,
+      "field_format": "",
+      "field_name": "firstname"
+    },
+    {
+      "field_comment": "",
+      "field_length": 30,
+      "field_type": 2,
+      "field_precision": -1,
+      "field_format": "",
+      "field_name": "zip"
+    },
+    {
+      "field_comment": "",
+      "field_length": 8,
+      "field_type": 2,
+      "field_precision": -1,
+      "field_format": "",
+      "field_name": "city"
+    },
+    {
+      "field_comment": "",
+      "field_length": -1,
+      "field_type": 3,
+      "field_precision": -1,
+      "field_format": "yyyy/MM/dd",
+      "field_name": "birthdate"
+    },
+    {
+      "field_comment": "",
+      "field_length": 11,
+      "field_type": 2,
+      "field_precision": -1,
+      "field_format": "",
+      "field_name": "street"
+    },
+    {
+      "field_comment": "",
+      "field_length": 50,
+      "field_type": 2,
+      "field_precision": -1,
+      "field_format": "",
+      "field_name": "housenr"
+    },
+    {
+      "field_comment": "",
+      "field_length": 10,
+      "field_type": 2,
+      "field_precision": -1,
+      "field_format": "",
+      "field_name": "stateCode"
+    },
+    {
+      "field_comment": "",
+      "field_length": 50,
+      "field_type": 2,
+      "field_precision": -1,
+      "field_format": "",
+      "field_name": "state"
+    },
+    {
+      "field_comment": "",
+      "field_length": -1,
+      "field_type": 2,
+      "field_precision": -1,
+      "field_format": "",
+      "field_name": "match"
+    },
+    {
+      "field_comment": "",
+      "field_length": -1,
+      "field_type": 2,
+      "field_precision": -1,
+      "field_format": "",
+      "field_name": "measure value"
+    }
+  ],
+  "folder_name": ""
+}
\ No newline at end of file
diff --git a/integration-tests/transforms/metadata/unit-test/0007-fuzzymatch 
UNIT.json b/integration-tests/transforms/metadata/unit-test/0007-fuzzymatch 
UNIT.json
new file mode 100644
index 0000000..eb458f8
--- /dev/null
+++ b/integration-tests/transforms/metadata/unit-test/0007-fuzzymatch UNIT.json 
@@ -0,0 +1,72 @@
+{
+  "variableValues": [],
+  "database_replacements": [],
+  "autoOpening": false,
+  "basePath": "",
+  "golden_data_sets": [
+    {
+      "field_mappings": [
+        {
+          "transform_field": "birthdate",
+          "data_set_field": "birthdate"
+        },
+        {
+          "transform_field": "city",
+          "data_set_field": "city"
+        },
+        {
+          "transform_field": "firstname",
+          "data_set_field": "firstname"
+        },
+        {
+          "transform_field": "housenr",
+          "data_set_field": "housenr"
+        },
+        {
+          "transform_field": "id",
+          "data_set_field": "id"
+        },
+        {
+          "transform_field": "match",
+          "data_set_field": "match"
+        },
+        {
+          "transform_field": "measure value",
+          "data_set_field": "measure value"
+        },
+        {
+          "transform_field": "name",
+          "data_set_field": "name"
+        },
+        {
+          "transform_field": "state",
+          "data_set_field": "state"
+        },
+        {
+          "transform_field": "stateCode",
+          "data_set_field": "stateCode"
+        },
+        {
+          "transform_field": "street",
+          "data_set_field": "street"
+        },
+        {
+          "transform_field": "zip",
+          "data_set_field": "zip"
+        }
+      ],
+      "field_order": [
+        "id"
+      ],
+      "transform_name": "Output",
+      "data_set_name": "golden-fuzzymatch"
+    }
+  ],
+  "input_data_sets": [],
+  "name": "0007-fuzzymatch UNIT",
+  "description": "",
+  "trans_test_tweaks": [],
+  "persist_filename": "",
+  "pipeline_filename": "./0007-fuzzymatch.hpl",
+  "test_type": "UNIT_TEST"
+}
\ No newline at end of file

Reply via email to