Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

update parser az #817

Merged
merged 2 commits into from
Apr 24, 2024
Merged

update parser az #817

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
3f5a129
update parser az
nthu31 Apr 22, 2024
125137a
update parser az
nthu31 Apr 24, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
28 changes: 26 additions & 2 deletions az/parser.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,7 +18,7 @@ module.exports = new Parser(function analyseEC(parsedUrl, ec) {

// use console.error for debuging
// console.error(parsedUrl);

let marginal;
//let match;

if (/^\/maf\/app\/delivery\/document$/i.test(path)) {
Expand All @@ -28,7 +28,7 @@ module.exports = new Parser(function analyseEC(parsedUrl, ec) {
result.db_id = param._;
result.unitid = param.docguid;

} else if (/^\/maf\/app\/document$/i.test(path)) {
} else if (/^\/maf\/app\/document$/i.test(path) && parsedUrl.hostname == 'aranzadi.aranzadidigital.es') {
if (param.marginal) {
// http://aranzadi.aranzadidigital.es/maf/app/document?startChunk=1&endChunk=2&stid=marginal_chunk&ds=ARZ_LEGIS_CS&infotype=arz_legis&marginal=RCL\2004\1466&version=&srguid=i0ad6adc60000018b4985c8a0c99bd9dd&lang=spa&src=withinResuts&spos=1&epos=1&mdfilter=mdlegisfilter
// http://aranzadi.aranzadidigital.es/maf/app/document?startChunk=1&endChunk=2&stid=marginal_chunk&ds=ARZ_LEGIS_CS&infotype=arz_legis&marginal=RCL\1979\2289&version=&srguid=i0ad6adc60000018b4985c8a0c99bd9dd&lang=spa&src=withinResuts&spos=10&epos=10&mdfilter=mdlegisfilter
Expand All @@ -52,6 +52,30 @@ module.exports = new Parser(function analyseEC(parsedUrl, ec) {
// http://aranzadi.aranzadidigital.es/maf/app/search/run/multi
result.rtype = 'SEARCH';
result.mime = 'HTML';
} else if (/^\/maf\/app\/document$/i.test(path) && (marginal = param.marginal) != undefined && (marginal.split('\\')[0] === 'RJ' || marginal.split('\\')[0] === 'RCL')) {
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

You can group several parsers into a single one by using lot of if or a switch.

} else if (/^\/maf\/app\/document$/i.test(path)) {
    // /maf/app/document?startChunk=1&mdfilter=mdlegisfilter&endChunk=2&stid=marginal_chunk&ds=ARZ_LEGIS_CS&infotype=arz_legis&subResult=i0ad6adc60000018ed0247a839bee5891&docguid=I6b664a40e83811db8079010000000000&marginal=RCL\1999\710&spos=1&epos=1&version=19990406&displayName=&lang=spa
    // /maf/app/document?srguid=i0ad6adc50000018ed0247dc8eb6fe26f&marginal=RJ\2017\1890&docguid=I03fcd8903aa011e79de2010000000000&ds=ARZ_LEGIS_CS&infotype=arz_doc-admin;&spos=1&epos=1&td=0&predefinedRelationshipsType=documentRetrieval&global-result-list=global&fromTemplate=&suggestScreen=&&selectedNodeName=&selec_mod=false&displayName=
    marginal = param.marginal
    
    if (marginal.split('\\')[0] === 'RJ' || marginal.split('\\')[0] === 'RCL') {
      // /maf/app/document?startChunk=1&mdfilter=mdlegisfilter&endChunk=2&stid=marginal_chunk&ds=ARZ_LEGIS_CS&infotype=arz_legis&subResult=i0ad6adc60000018ed0247a839bee5891&docguid=I6b664a40e83811db8079010000000000&marginal=RCL\1999\710&spos=1&epos=1&version=19990406&displayName=&lang=spa
      // /maf/app/document?srguid=i0ad6adc50000018ed0247dc8eb6fe26f&marginal=RJ\2017\1890&docguid=I03fcd8903aa011e79de2010000000000&ds=ARZ_LEGIS_CS&infotype=arz_doc-admin;&spos=1&epos=1&td=0&predefinedRelationshipsType=documentRetrieval&global-result-list=global&fromTemplate=&suggestScreen=&&selectedNodeName=&selec_mod=false&displayName=
      result.rtype    = 'ARTICLE';
      result.mime     = 'HTML';
      result.unitid   = marginal;
    }

    if (marginal.split('\\')[0] === 'BIB') {
      // /maf/app/document?srguid=i0ad6adc50000018ed0247a19ba6a7861&marginal=BIB\2021\1098&docguid=I2e8fecd0a23611ebaf9ae70e1612b1e3&ds=ARZ_LEGIS_CS&infotype=arz_biblos;&spos=1&epos=1&td=0&predefinedRelationshipsType=documentRetrieval&fromTemplate=&suggestScreen=&&selectedNodeName=&selec_mod=false&displayName=
      // /maf/app/document?srguid=i0ad6adc50000018ed0247a19ba6a7861&marginal=BIB\2015\322&docguid=Idbdd5360a82c11e4b065010000000000&ds=ARZ_LEGIS_CS&infotype=arz_biblos;&spos=5&epos=5&td=0&predefinedRelationshipsType=documentRetrieval&fromTemplate=&suggestScreen=&&selectedNodeName=&selec_mod=false&displayName=
      result.rtype    = 'BOOK';
      result.mime     = 'HTML';
      result.unitid   = marginal;
    }

    if (marginal.split('\\')[0] === 'FOR') {
      // /maf/app/document?srguid=i0ad6adc50000018ed0247c23d3a4bb99&marginal=FOR\2012\839&docguid=I0eb20050b1e111e1847d010000000000&ds=ARZ_LEGIS_CS&infotype=arz_formularios;&spos=1&epos=1&td=0&predefinedRelationshipsType=documentRetrieval&fromTemplate=&suggestScreen=&&selectedNodeName=&selec_mod=false&displayName=
      // /maf/app/document?srguid=i0ad6adc50000018ed0247c23d3a4bb99&marginal=FOR\2011\924&docguid=I55351570de7f11e0a788010000000000&ds=ARZ_LEGIS_CS&infotype=arz_formularios;&spos=8&epos=8&td=0&predefinedRelationshipsType=documentRetrieval&fromTemplate=&suggestScreen=&&selectedNodeName=&selec_mod=false&displayName=
      result.rtype    = 'FORMULES';
      result.mime     = 'HTML';
      result.unitid   = marginal;
    }

    if (marginal.split('\\')[0] === 'MIX') {
      // /maf/app/document?srguid=i0ad6adc50000018ed0247b3d15b13605&marginal=MIX\2023\211717&docguid=Id421ff501ef611eeba5fb46f48ac422d&ds=ARZ_LEGIS_CS&infotype=arz_cuadros;&spos=1&epos=1&td=0&predefinedRelationshipsType=documentRetrieval&fromTemplate=&suggestScreen=&&selectedNodeName=&selec_mod=false&displayName=
      // /maf/app/document?srguid=i0ad6adc50000018ed0247b3d15b13605&marginal=MIX\2004\583&docguid=I4aa5994075a211dba338010000000000&ds=ARZ_LEGIS_CS&infotype=arz_cuadros;&spos=2&epos=2&td=0&predefinedRelationshipsType=documentRetrieval&fromTemplate=&suggestScreen=&&selectedNodeName=&selec_mod=false&displayName=#
      result.rtype    = 'IMAGE';
      result.mime     = 'PDF';
      result.unitid   = marginal;
    }
  }

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Hi,
I have modified the code. Please check.
Thanks!

// https://insignis.aranzadidigital.es/maf/app/document?startChunk=1&mdfilter=mdlegisfilter&endChunk=2&stid=marginal_chunk&ds=ARZ_LEGIS_CS&infotype=arz_legis&subResult=i0ad6adc60000018ed0247a839bee5891&docguid=I6b664a40e83811db8079010000000000&marginal=RCL\1999\710&spos=1&epos=1&version=19990406&displayName=&lang=spa
// https://insignis.aranzadidigital.es/maf/app/document?srguid=i0ad6adc50000018ed0247dc8eb6fe26f&marginal=RJ\2017\1890&docguid=I03fcd8903aa011e79de2010000000000&ds=ARZ_LEGIS_CS&infotype=arz_doc-admin;&spos=1&epos=1&td=0&predefinedRelationshipsType=documentRetrieval&global-result-list=global&fromTemplate=&suggestScreen=&&selectedNodeName=&selec_mod=false&displayName=
result.rtype = 'ARTICLE';
result.mime = 'HTML';
result.unitid = marginal;
} else if (/^\/maf\/app\/document$/i.test(path) && (marginal = param.marginal) != undefined && marginal.split('\\')[0] == 'BIB') {
// https://insignis.aranzadidigital.es/maf/app/document?srguid=i0ad6adc50000018ed0247a19ba6a7861&marginal=BIB\2021\1098&docguid=I2e8fecd0a23611ebaf9ae70e1612b1e3&ds=ARZ_LEGIS_CS&infotype=arz_biblos;&spos=1&epos=1&td=0&predefinedRelationshipsType=documentRetrieval&fromTemplate=&suggestScreen=&&selectedNodeName=&selec_mod=false&displayName=
// https://insignis.aranzadidigital.es/maf/app/document?srguid=i0ad6adc50000018ed0247a19ba6a7861&marginal=BIB\2015\322&docguid=Idbdd5360a82c11e4b065010000000000&ds=ARZ_LEGIS_CS&infotype=arz_biblos;&spos=5&epos=5&td=0&predefinedRelationshipsType=documentRetrieval&fromTemplate=&suggestScreen=&&selectedNodeName=&selec_mod=false&displayName=
result.rtype = 'BOOK';
result.mime = 'HTML';
result.unitid = marginal;
} else if (/^\/maf\/app\/document$/i.test(path) && (marginal = param.marginal) != undefined && marginal.split('\\')[0] == 'FOR') {
// https://insignis.aranzadidigital.es/maf/app/document?srguid=i0ad6adc50000018ed0247c23d3a4bb99&marginal=FOR\2012\839&docguid=I0eb20050b1e111e1847d010000000000&ds=ARZ_LEGIS_CS&infotype=arz_formularios;&spos=1&epos=1&td=0&predefinedRelationshipsType=documentRetrieval&fromTemplate=&suggestScreen=&&selectedNodeName=&selec_mod=false&displayName=
// https://insignis.aranzadidigital.es/maf/app/document?srguid=i0ad6adc50000018ed0247c23d3a4bb99&marginal=FOR\2011\924&docguid=I55351570de7f11e0a788010000000000&ds=ARZ_LEGIS_CS&infotype=arz_formularios;&spos=8&epos=8&td=0&predefinedRelationshipsType=documentRetrieval&fromTemplate=&suggestScreen=&&selectedNodeName=&selec_mod=false&displayName=
result.rtype = 'FORMULES';
result.mime = 'HTML';
result.unitid = marginal;
} else if (/^\/maf\/app\/document$/i.test(path) && (marginal = param.marginal) != undefined && marginal.split('\\')[0] == 'MIX') {
// https://insignis.aranzadidigital.es/maf/app/document?srguid=i0ad6adc50000018ed0247b3d15b13605&marginal=MIX\2023\211717&docguid=Id421ff501ef611eeba5fb46f48ac422d&ds=ARZ_LEGIS_CS&infotype=arz_cuadros;&spos=1&epos=1&td=0&predefinedRelationshipsType=documentRetrieval&fromTemplate=&suggestScreen=&&selectedNodeName=&selec_mod=false&displayName=
// https://insignis.aranzadidigital.es/maf/app/document?srguid=i0ad6adc50000018ed0247b3d15b13605&marginal=MIX\2004\583&docguid=I4aa5994075a211dba338010000000000&ds=ARZ_LEGIS_CS&infotype=arz_cuadros;&spos=2&epos=2&td=0&predefinedRelationshipsType=documentRetrieval&fromTemplate=&suggestScreen=&&selectedNodeName=&selec_mod=false&displayName=#
result.rtype = 'IMAGE';
result.mime = 'PDF';
result.unitid = marginal;
}

return result;
Expand Down
16 changes: 16 additions & 0 deletions az/test/AZ.2024-04-19.csv
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,16 @@
out-db_id;out-unitid;out-rtype;out-mime;in-url
;MIX\2004\583;IMAGE;PDF;"https://insignis.aranzadidigital.es/maf/app/document?srguid=i0ad6adc50000018ed0247b3d15b13605&marginal=MIX\2004\583&docguid=I4aa5994075a211dba338010000000000&ds=ARZ_LEGIS_CS&infotype=arz_cuadros;&spos=2&epos=2&td=0&predefinedRelationshipsType=documentRetrieval&fromTemplate=&suggestScreen=&&selectedNodeName=&selec_mod=false&displayName=#"
;MIX\2023\211717;IMAGE;PDF;"https://insignis.aranzadidigital.es/maf/app/document?srguid=i0ad6adc50000018ed0247b3d15b13605&marginal=MIX\2023\211717&docguid=Id421ff501ef611eeba5fb46f48ac422d&ds=ARZ_LEGIS_CS&infotype=arz_cuadros;&spos=1&epos=1&td=0&predefinedRelationshipsType=documentRetrieval&fromTemplate=&suggestScreen=&&selectedNodeName=&selec_mod=false&displayName="
;FOR\2011\924;FORMULES;HTML;"https://insignis.aranzadidigital.es/maf/app/document?srguid=i0ad6adc50000018ed0247c23d3a4bb99&marginal=FOR\2011\924&docguid=I55351570de7f11e0a788010000000000&ds=ARZ_LEGIS_CS&infotype=arz_formularios;&spos=8&epos=8&td=0&predefinedRelationshipsType=documentRetrieval&fromTemplate=&suggestScreen=&&selectedNodeName=&selec_mod=false&displayName="
;FOR\2012\839;FORMULES;HTML;"https://insignis.aranzadidigital.es/maf/app/document?srguid=i0ad6adc50000018ed0247c23d3a4bb99&marginal=FOR\2012\839&docguid=I0eb20050b1e111e1847d010000000000&ds=ARZ_LEGIS_CS&infotype=arz_formularios;&spos=1&epos=1&td=0&predefinedRelationshipsType=documentRetrieval&fromTemplate=&suggestScreen=&&selectedNodeName=&selec_mod=false&displayName="
;BIB\2015\322;BOOK;HTML;"https://insignis.aranzadidigital.es/maf/app/document?srguid=i0ad6adc50000018ed0247a19ba6a7861&marginal=BIB\2015\322&docguid=Idbdd5360a82c11e4b065010000000000&ds=ARZ_LEGIS_CS&infotype=arz_biblos;&spos=5&epos=5&td=0&predefinedRelationshipsType=documentRetrieval&fromTemplate=&suggestScreen=&&selectedNodeName=&selec_mod=false&displayName="
;BIB\2021\1098;BOOK;HTML;"https://insignis.aranzadidigital.es/maf/app/document?srguid=i0ad6adc50000018ed0247a19ba6a7861&marginal=BIB\2021\1098&docguid=I2e8fecd0a23611ebaf9ae70e1612b1e3&ds=ARZ_LEGIS_CS&infotype=arz_biblos;&spos=1&epos=1&td=0&predefinedRelationshipsType=documentRetrieval&fromTemplate=&suggestScreen=&&selectedNodeName=&selec_mod=false&displayName="
;RJ\2017\1890;ARTICLE;HTML;"https://insignis.aranzadidigital.es/maf/app/document?srguid=i0ad6adc50000018ed0247dc8eb6fe26f&marginal=RJ\2017\1890&docguid=I03fcd8903aa011e79de2010000000000&ds=ARZ_LEGIS_CS&infotype=arz_doc-admin;&spos=1&epos=1&td=0&predefinedRelationshipsType=documentRetrieval&global-result-list=global&fromTemplate=&suggestScreen=&&selectedNodeName=&selec_mod=false&displayName="
;RCL\1999\710;ARTICLE;HTML;https://insignis.aranzadidigital.es/maf/app/document?startChunk=1&mdfilter=mdlegisfilter&endChunk=2&stid=marginal_chunk&ds=ARZ_LEGIS_CS&infotype=arz_legis&subResult=i0ad6adc60000018ed0247a839bee5891&docguid=I6b664a40e83811db8079010000000000&marginal=RCL\1999\710&spos=1&epos=1&version=19990406&displayName=&lang=spa
;;SEARCH;HTML;https://insignis.aranzadidigital.es/maf/app/search/run/multi
;I0661f5f02b8a11e1936b010000000000;FORMULES;HTML;http://aranzadi.aranzadidigital.es/maf/app/document?docguid=I0661f5f02b8a11e1936b010000000000&srguid=i0ad6adc60000018b49ab472c81fff954&src=withinResuts&spos=4&epos=4
;I0aabd1b05e2a11e8a041010000000000;FORMULES;HTML;http://aranzadi.aranzadidigital.es/maf/app/document?docguid=I0aabd1b05e2a11e8a041010000000000&srguid=i0ad6adc60000018b49ab472c81fff954&src=withinResuts&spos=1&epos=1
1697747395452;I3407bf608eb111ea98abc16d771da8bc;ARTICLE;PDF;http://aranzadi.aranzadidigital.es/maf/app/delivery/document?_=1697747395452&deliveryTarget=save&deliveryType=document&infoType=arz_legis&typeTitle=Legislaci%C3%B3n&magazines=&srguid=i0ad6adc60000018b49a00a26fc754444&td=0&docTitle=Desarrolla+el+Estatuto+del+Trabajo+Aut%C3%B3nomo++(RCL+2007%5C1354)+en+materia+de+contrato+del+trabajador+aut%C3%B3n...&label=Real+Decreto+n%C3%BAm.+197%2F2009%2C+de+23+febrero&docguid=I3407bf608eb111ea98abc16d771da8bc
;RCL\1979\2289;ARTICLE;HTML;http://aranzadi.aranzadidigital.es/maf/app/document?startChunk=1&endChunk=2&stid=marginal_chunk&ds=ARZ_LEGIS_CS&infotype=arz_legis&marginal=RCL\1979\2289&version=&srguid=i0ad6adc60000018b4985c8a0c99bd9dd&lang=spa&src=withinResuts&spos=10&epos=10&mdfilter=mdlegisfilter
;RCL\2004\1466;ARTICLE;HTML;http://aranzadi.aranzadidigital.es/maf/app/document?startChunk=1&endChunk=2&stid=marginal_chunk&ds=ARZ_LEGIS_CS&infotype=arz_legis&marginal=RCL\2004\1466&version=&srguid=i0ad6adc60000018b4985c8a0c99bd9dd&lang=spa&src=withinResuts&spos=1&epos=1&mdfilter=mdlegisfilter
;;SEARCH;HTML;http://aranzadi.aranzadidigital.es/maf/app/search/run/multi
9 changes: 0 additions & 9 deletions az/test/az.2023-11-01.csv
View file
Open in desktop

This file was deleted.

Loading