Icon

01_​SDS phrases extraction

SDS Risk Phrase Extraction
Execute the first wrapped metanode and change the Excel and ZIP file if you want to try with your data. Otherwise, execute the whole workflow.In the last wrapped metanode, download the resulting excel files. Read SDS in PDF format Text Mining Preprocessing PhrasesExtraction Post Processing Deployment ReadonlyPDFRisk Phrasessingle row matrixExtractsentencefrom documentUnpivotingall _Arr[*] columnsFilter outmissing value rowsSplit pathend inject the last part as variableCollect rowsas matrixPrint standardmessage when for any reason the upper partstops its executionConvertColumnValues Typeas StringExtract Risk PhrasesTOP: integer columnsBOTTOM: String columnsOrder columnsAppend Descriptionfor each Risk PhraseTransformcontent indocumentSplitsentence by line separator Tika Parser Try (Data Ports) Catch Errors(Data Ports) Sentence Extractor Unpivoting Row Filter gather filename Loop End If somethinggoes wrong... cast ColumnValuesas String Phrases Chunk Loop Start Input Column Splitter Column Resorter View Phrasesand Download Risk Description Strings To Document Cell Splitter Execute the first wrapped metanode and change the Excel and ZIP file if you want to try with your data. Otherwise, execute the whole workflow.In the last wrapped metanode, download the resulting excel files. Read SDS in PDF format Text Mining Preprocessing PhrasesExtraction Post Processing Deployment ReadonlyPDFRisk Phrasessingle row matrixExtractsentencefrom documentUnpivotingall _Arr[*] columnsFilter outmissing value rowsSplit pathend inject the last part as variableCollect rowsas matrixPrint standardmessage when for any reason the upper partstops its executionConvertColumnValues Typeas StringExtract Risk PhrasesTOP: integer columnsBOTTOM: String columnsOrder columnsAppend Descriptionfor each Risk PhraseTransformcontent indocumentSplitsentence by line separatorTika Parser Try (Data Ports) Catch Errors(Data Ports) Sentence Extractor Unpivoting Row Filter gather filename Loop End If somethinggoes wrong... cast ColumnValuesas String Phrases Chunk Loop Start Input Column Splitter Column Resorter View Phrasesand Download Risk Description Strings To Document Cell Splitter

Nodes

Extensions

Links