From be64055cfe212bcfc945da6fa53c76e15f977b8b Mon Sep 17 00:00:00 2001 From: "miriam.baglioni" Date: Mon, 14 Feb 2022 15:49:44 +0100 Subject: [PATCH] [OpenCitation] changed the name of destination folders --- .../actionmanager/opencitations/ReadCOCI.java | 2 +- .../opencitations/model/COCI.java | 2 +- .../opencitations/ReadCOCITest.java | 20 +++++++++--------- .../opencitations/inputFiles/input1 | 8 ------- .../opencitations/inputFiles/input1.gz | Bin 0 -> 422 bytes .../opencitations/inputFiles/input2 | 8 ------- .../opencitations/inputFiles/input2.gz | Bin 0 -> 378 bytes .../opencitations/inputFiles/input3 | 9 -------- .../opencitations/inputFiles/input3.gz | Bin 0 -> 395 bytes .../opencitations/inputFiles/input4 | 2 -- .../opencitations/inputFiles/input4.gz | Bin 0 -> 179 bytes .../opencitations/inputFiles/input5 | 2 -- .../opencitations/inputFiles/input5.gz | Bin 0 -> 150 bytes 13 files changed, 12 insertions(+), 41 deletions(-) delete mode 100644 dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/actionmanager/opencitations/inputFiles/input1 create mode 100644 dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/actionmanager/opencitations/inputFiles/input1.gz delete mode 100644 dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/actionmanager/opencitations/inputFiles/input2 create mode 100644 dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/actionmanager/opencitations/inputFiles/input2.gz delete mode 100644 dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/actionmanager/opencitations/inputFiles/input3 create mode 100644 dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/actionmanager/opencitations/inputFiles/input3.gz delete mode 100644 dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/actionmanager/opencitations/inputFiles/input4 create mode 100644 dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/actionmanager/opencitations/inputFiles/input4.gz delete mode 100644 dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/actionmanager/opencitations/inputFiles/input5 create mode 100644 dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/actionmanager/opencitations/inputFiles/input5.gz diff --git a/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/opencitations/ReadCOCI.java b/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/opencitations/ReadCOCI.java index fd83f7072..3fd6e8e9a 100644 --- a/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/opencitations/ReadCOCI.java +++ b/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/opencitations/ReadCOCI.java @@ -73,7 +73,7 @@ public class ReadCOCI implements Serializable { String delimiter) throws IOException { for(String inputFile : inputFiles){ - String p_string = workingPath + "/" + inputFile ; + String p_string = workingPath + "/" + inputFile + ".gz"; Dataset cociData = spark .read() diff --git a/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/opencitations/model/COCI.java b/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/opencitations/model/COCI.java index bad4a5a3b..ce087ce22 100644 --- a/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/opencitations/model/COCI.java +++ b/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/opencitations/model/COCI.java @@ -37,5 +37,5 @@ public class COCI implements Serializable { this.cited = cited; } - + } diff --git a/dhp-workflows/dhp-aggregation/src/test/java/eu/dnetlib/dhp/actionmanager/opencitations/ReadCOCITest.java b/dhp-workflows/dhp-aggregation/src/test/java/eu/dnetlib/dhp/actionmanager/opencitations/ReadCOCITest.java index 53af074e1..629e95c8e 100644 --- a/dhp-workflows/dhp-aggregation/src/test/java/eu/dnetlib/dhp/actionmanager/opencitations/ReadCOCITest.java +++ b/dhp-workflows/dhp-aggregation/src/test/java/eu/dnetlib/dhp/actionmanager/opencitations/ReadCOCITest.java @@ -78,37 +78,37 @@ public class ReadCOCITest { fs .copyFromLocalFile( false, new org.apache.hadoop.fs.Path(getClass() - .getResource("/eu/dnetlib/dhp/actionmanager/opencitations/inputFiles/input1") + .getResource("/eu/dnetlib/dhp/actionmanager/opencitations/inputFiles/input1.gz") .getPath()), - new org.apache.hadoop.fs.Path(workingDir + "/COCI/input1")); + new org.apache.hadoop.fs.Path(workingDir + "/COCI/input1.gz")); fs .copyFromLocalFile( false, new org.apache.hadoop.fs.Path(getClass() - .getResource("/eu/dnetlib/dhp/actionmanager/opencitations/inputFiles/input2") + .getResource("/eu/dnetlib/dhp/actionmanager/opencitations/inputFiles/input2.gz") .getPath()), - new org.apache.hadoop.fs.Path(workingDir + "/COCI/input2")); + new org.apache.hadoop.fs.Path(workingDir + "/COCI/input2.gz")); fs .copyFromLocalFile( false, new org.apache.hadoop.fs.Path(getClass() - .getResource("/eu/dnetlib/dhp/actionmanager/opencitations/inputFiles/input3") + .getResource("/eu/dnetlib/dhp/actionmanager/opencitations/inputFiles/input3.gz") .getPath()), - new org.apache.hadoop.fs.Path(workingDir + "/COCI/input3")); + new org.apache.hadoop.fs.Path(workingDir + "/COCI/input3.gz")); fs .copyFromLocalFile( false, new org.apache.hadoop.fs.Path(getClass() - .getResource("/eu/dnetlib/dhp/actionmanager/opencitations/inputFiles/input4") + .getResource("/eu/dnetlib/dhp/actionmanager/opencitations/inputFiles/input4.gz") .getPath()), - new org.apache.hadoop.fs.Path(workingDir + "/COCI/input4")); + new org.apache.hadoop.fs.Path(workingDir + "/COCI/input4.gz")); fs .copyFromLocalFile( false, new org.apache.hadoop.fs.Path(getClass() - .getResource("/eu/dnetlib/dhp/actionmanager/opencitations/inputFiles/input5") + .getResource("/eu/dnetlib/dhp/actionmanager/opencitations/inputFiles/input5.gz") .getPath()), - new org.apache.hadoop.fs.Path(workingDir + "/COCI/input5")); + new org.apache.hadoop.fs.Path(workingDir + "/COCI/input5.gz")); ReadCOCI .main( diff --git a/dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/actionmanager/opencitations/inputFiles/input1 b/dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/actionmanager/opencitations/inputFiles/input1 deleted file mode 100644 index d93d6fd99..000000000 --- a/dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/actionmanager/opencitations/inputFiles/input1 +++ /dev/null @@ -1,8 +0,0 @@ -oci,citing,cited,creation,timespan,journal_sc,author_sc -02001000007362801000805046300010563030608046333-0200101010136193701050501630209010637020000083700020400083733,10.1007/s10854-015-3684-x,10.1111/j.1551-2916.2008.02408.x,2015-09-01,P7Y2M,no,no -02001000007362801000805046300010563030608046333-02001000007362801000805046300010463020101046309,10.1007/s10854-015-3684-x,10.1007/s10854-014-2114-9,2015-09-01,P1Y2M4D,yes,no -02001000007362801000805046300010563030608046333-020010001063619371214271022182329370200010337000937000609,10.1007/s10854-015-3684-x,10.1016/j.ceramint.2013.09.069,2015-09-01,P1Y6M,no,no -02001000007362801000805046300010563030608046333-02001000007362801000805046300000963090901036304,10.1007/s10854-015-3684-x,10.1007/s10854-009-9913-4,2015-09-01,P6Y3M10D,yes,no -02001000007362801000805046300010563030608046333-02001000106360000030863010009085807025909000307006305,10.1007/s10854-015-3684-x,10.1016/0038-1098(72)90370-5,2015-09-01,P43Y8M,no,no -02001000007362801000805046300010563030608056309-02001000106361937281010370200010437000937000308,10.1007/s10854-015-3685-9,10.1016/j.saa.2014.09.038,2015-09-03,P0Y7M,no,no -02001000007362801000805046300010563030608056309-0200100010636193722102912171027370200010537000437000106,10.1007/s10854-015-3685-9,10.1016/j.matchar.2015.04.016,2015-09-03,P0Y2M,no,no \ No newline at end of file diff --git a/dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/actionmanager/opencitations/inputFiles/input1.gz b/dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/actionmanager/opencitations/inputFiles/input1.gz new file mode 100644 index 0000000000000000000000000000000000000000..7a734f4e201d4520ede681fcda66aa75e2fb8706 GIT binary patch literal 422 zcmV;X0a^YZiwFqDY6@Zi18Ht>b#yTRwUk>=tuPRU-~A<;v^bZxwC}!}_`07=!y$?} z8w{`${r9eRtH-S|UQbKPFf+i{#R^k5m~L2y@v5BqKc<`eybjZ7)?wQ(w|O)-({3K~ z-^-;ldAD9qGom9BBBnB04H9b{$&(98rQ&f`3dkX&YWMwhYT%@8>A__52_;+w zxZb80o>+1&c5u}W8vn7Xxu8w^d#C~vC)l}|xqU|V6?PAf-cKQK^V(hKxnTQ-K+fS6 Q_S4_u0fkiL0VM?h0048#m;e9( literal 0 HcmV?d00001 diff --git a/dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/actionmanager/opencitations/inputFiles/input2 b/dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/actionmanager/opencitations/inputFiles/input2 deleted file mode 100644 index 14ee8b354..000000000 --- a/dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/actionmanager/opencitations/inputFiles/input2 +++ /dev/null @@ -1,8 +0,0 @@ -oci,citing,cited,creation,timespan,journal_sc,author_sc -02001000308362804010509076300010963000003086301-0200100020936020001003227000009010004,10.1038/s41597-019-0038-1,10.1029/2010wr009104,2019-04-15,P8Y1M,no,no -02001000308362804010509076300010963000003086301-0200100010636280103060463080105025800015900000006006303,10.1038/s41597-019-0038-1,10.1016/s1364-8152(01)00060-3,2019-04-15,P17Y3M,no,no -02001000308362804010509076300010963000003086301-02001000007362800000407076300010063000401066333,10.1038/s41597-019-0038-1,10.1007/s00477-010-0416-x,2019-04-15,P8Y9M6D,no,no -02001000308362804010509076300010963000003086301-02001000007362800000700046300010363000905016308,10.1038/s41597-019-0038-1,10.1007/s00704-013-0951-8,2019-04-15,P5Y9M23D,no,no -02001000308362804010509076300010963000003086301-02001000002361924123705070707,10.1038/s41597-019-0038-1,10.1002/joc.5777,2019-04-15,P0Y8M1D,no,no -02001000308362804010509076300010963000003086301-02005010904361714282863020263040504076302000108,10.1038/s41597-019-0038-1,10.5194/hess-22-4547-2018,2019-04-15,P0Y7M18D,no,no -02001000308362804010509076300010963000003086301-02001000002361924123703050404,10.1038/s41597-019-0038-1,10.1002/joc.3544,2019-04-15,P6Y9M6D,no,no \ No newline at end of file diff --git a/dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/actionmanager/opencitations/inputFiles/input2.gz b/dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/actionmanager/opencitations/inputFiles/input2.gz new file mode 100644 index 0000000000000000000000000000000000000000..b30aa073cc3b8c0515bd3cf766e184a805a7705b GIT binary patch literal 378 zcmV-=0fqh_iwFqDY6@Zi18Ht>b#yWSt&>ep!!Qhn@B9*wn$=&4lRMW+Tz5iKnOG6D zsO+Ms?Enb@a%MhqkNQZtnW$9JWtYJ8m~~H}uuqy=|xWO<%nX`?24= zK2B}5+0VOSwABp|00IC*LISNsrtd@zu6E%@f!jJ5YuAGBpPgy7Vxg5IzGWhUGt^f09yQc2b#yZTy;DtZgD?!e@3(~D4~WTq*Gju`nh@(YrVS>b zQ-A*Kw5mogMQt^LlrKN$`Pm-Y&b8g#^=~$9UtBwGo4Ff$H+Ns#>AUIO$FLjw=JR=K zU9+3thf!A#KmZ8#5eJAMQ0d-A1lFCN+h8HV0!ykgLzH?)5EKDWBs7|}L-6X1@+cJ| zMiw9oK}z=|mWn2kvCDJ*Gb z^T)z`fwCT9{^3!nXR(C6S2yAnkJ0a!F;HFIDF#NW7*ZUh_9etMEPtk*N8&OrXcaZW zhT`K*%>Jg^G&QRT#j1331d7E{Dyi`{sh0IeiI&Q>uKrY0!6hNCb#ycUHBCtl!Y~ZH^NgNd7-uDqK;p^?RcQsOAVF>V ze;ifyZjZ+=JN@6AjSRG0rRpFDqNEyfc1|qbAdXJ8BqM hFgaomx^qF3d{I5iJElAP2j3_cu|J_U8=~j{004P1OThpD literal 0 HcmV?d00001 diff --git a/dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/actionmanager/opencitations/inputFiles/input5 b/dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/actionmanager/opencitations/inputFiles/input5 deleted file mode 100644 index 0a1cd5aca..000000000 --- a/dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/actionmanager/opencitations/inputFiles/input5 +++ /dev/null @@ -1,2 +0,0 @@ -oci,citing,cited,creation,timespan,journal_sc,author_sc -02001000007362801000805046300010563030608046333-02001000007362801000805046300010563030608046333,10.1007/s10854-015-3684-x,10.1007/s10854-015-3684-x,2015-09-01,P7Y2M,no,no \ No newline at end of file diff --git a/dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/actionmanager/opencitations/inputFiles/input5.gz b/dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/actionmanager/opencitations/inputFiles/input5.gz new file mode 100644 index 0000000000000000000000000000000000000000..2e7a6c85b1bd6f4478ad720806217cd4aa2b8779 GIT binary patch literal 150 zcmV;H0BQdpiwFqDY6@Zi18Ht>b#yfVm5NIWLNO2o_nu{k`2l0cnMH!HD;dMoq?^6&?La9jG?`4-Q%=bK(F1 E0PH42g8%>k literal 0 HcmV?d00001