Package org.openrefine.importers.tree

Class XmlImportUtilities

java.lang.Object

org.openrefine.importers.tree.TreeImportUtilities

org.openrefine.importers.tree.XmlImportUtilities

public class XmlImportUtilities
extends TreeImportUtilities

Nested Class Summary

Nested classes/interfaces inherited from class org.openrefine.importers.tree.TreeImportUtilities

TreeImportUtilities.ColumnIndexAllocator

Constructor Summary

Constructors

Constructor	Description
XmlImportUtilities()

Method Summary

Modifier and Type	Method	Description
protected static void	addImportRecordToProject(ImportRecord record, List<Row> project, boolean includeFileSources, String fileSource, boolean includeArchiveName, String archiveName)
protected static String	composeName(String prefix, String localName)
static String[]	detectPathFromTag(TreeReader parser, String tag)
static String[]	detectRecordElement(TreeReader parser)	Seeks for recurring element in a parsed document which are likely candidates for being data records
protected static List<String>	detectRecordElement(TreeReader parser, String tag)	Looks for an element with the given tag name in the Tree data being parsed, returning the path hierarchy to reach it.
protected static org.openrefine.importers.tree.RecordElementCandidate	detectRecordElement(TreeReader parser, String[] path)
protected static void	findRecord(TreeImportUtilities.ColumnIndexAllocator allocator, List<Row> rows, TreeReader parser, String[] recordPath, int pathIndex, ImportColumnGroup rootColumnGroup, int limit, ImportParameters parameters)	Deprecated. Use the version of this method which expands all parameters in the signature of the function
protected static void	findRecord(TreeImportUtilities.ColumnIndexAllocator columnIndexAllocator, List<Row> rows, TreeReader parser, String[] recordPath, int pathIndex, ImportColumnGroup rootColumnGroup, long limit, boolean trimStrings, boolean storeEmptyStrings, boolean guessDataTypes, boolean includeFileSource, String fileSource, boolean includeArchiveName, String archiveFileName)
static void	importTreeData(TreeReader parser, TreeImportUtilities.ColumnIndexAllocator columnIndexAllocator, List<Row> rows, String[] recordPath, ImportColumnGroup rootColumnGroup, int limit, ImportParameters parameters)	Deprecated. 2020-07-23 Use the version of this method which expands all parameters in the signature of the function
static void	importTreeData(TreeReader parser, TreeImportUtilities.ColumnIndexAllocator columnIndexAllocator, List<Row> rows, String[] recordPath, ImportColumnGroup rootColumnGroup, long limit, boolean trimStrings, boolean storeEmptyStrings, boolean guessDataTypes, boolean includeFileSources, String fileSource, boolean includeArchiveName, String archiveFileName)
protected static void	processFieldAsRecord(TreeImportUtilities.ColumnIndexAllocator columnIndexAllocator, List<Row> rows, TreeReader parser, ImportColumnGroup rootColumnGroup, boolean trimStrings, boolean storeEmptyStrings, boolean guessDataType, boolean includeFileSources, String fileSource, boolean includeArchiveName, String archiveFileName)	processFieldAsRecord parses Tree data for a single element and its sub-elements, adding the parsed data as a row to the project
protected static void	processRecord(TreeImportUtilities.ColumnIndexAllocator columnIndexAllocator, List<Row> rows, TreeReader parser, ImportColumnGroup rootColumnGroup, boolean trimStrings, boolean storeEmptyStrings, boolean guessDataTypes, boolean includeFileSources, String fileSource, boolean includeArchiveName, String archiveFileName)	processRecord parses Tree data for a single element and it's sub-elements, adding the parsed data as a row to the project
protected static void	processRecord(TreeImportUtilities.ColumnIndexAllocator allocator, List<Row> rows, TreeReader parser, ImportColumnGroup rootColumnGroup, ImportParameters parameter)	Deprecated. Use the version of this method which expands all parameters in the signature of the function
protected static void	processSubRecord(TreeImportUtilities.ColumnIndexAllocator columnIndexAllocator, List<Row> rows, TreeReader parser, ImportColumnGroup columnGroup, ImportRecord record, int level, boolean trimStrings, boolean storeEmptyStrings, boolean guessDataType)
protected static void	processSubRecord(TreeImportUtilities.ColumnIndexAllocator columnIndexAllocator, List<Row> rows, TreeReader parser, ImportColumnGroup columnGroup, ImportRecord record, int level, ImportParameters parameter)	Deprecated.
protected static void	skip(TreeReader parser)

Methods inherited from class org.openrefine.importers.tree.TreeImportUtilities

addCell, addCell, addCell, createColumn, createColumnGroup, createColumnsFromImport, getColumn, getColumnGroup, sortRecordElementCandidates

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

XmlImportUtilities

public XmlImportUtilities()

Method Detail

detectPathFromTag

public static String[] detectPathFromTag(TreeReader parser,
                                         String tag)
                                  throws TreeReaderException

Throws:

TreeReaderException

detectRecordElement

protected static List<String> detectRecordElement(TreeReader parser,
                                                  String tag)
                                           throws TreeReaderException

Looks for an element with the given tag name in the Tree data being parsed, returning the path hierarchy to reach it.

Parameters:

parser -

tag - The element name (can be qualified) to search for

Returns:

If the tag is found, an array of strings is returned. If the tag is at the top level, the tag will be the only item in the array. If the tag is nested beneath the top level, the array is filled with the hierarchy with the tag name at the last index null if the the tag is not found.

Throws:

TreeReaderException

composeName

protected static String composeName(String prefix,
                                    String localName)

detectRecordElement

public static String[] detectRecordElement(TreeReader parser)

Seeks for recurring element in a parsed document which are likely candidates for being data records

Parameters:

parser - The parser loaded with tree data

Returns:

The path to the most numerous of the possible candidates. null if no candidates were found (less than 6 recurrences)

detectRecordElement

protected static org.openrefine.importers.tree.RecordElementCandidate detectRecordElement(TreeReader parser,
                                                                                          String[] path)

importTreeData

@Deprecated
public static void importTreeData(TreeReader parser,
                                  TreeImportUtilities.ColumnIndexAllocator columnIndexAllocator,
                                  List<Row> rows,
                                  String[] recordPath,
                                  ImportColumnGroup rootColumnGroup,
                                  int limit,
                                  ImportParameters parameters)
                           throws TreeReaderException

Deprecated.

2020-07-23 Use the version of this method which expands all parameters in the signature of the function

Parameters:

parser -

columnIndexAllocator -

rows -

recordPath -

rootColumnGroup -

limit -

parameters -

Throws:

TreeReaderException

importTreeData

public static void importTreeData(TreeReader parser,
                                  TreeImportUtilities.ColumnIndexAllocator columnIndexAllocator,
                                  List<Row> rows,
                                  String[] recordPath,
                                  ImportColumnGroup rootColumnGroup,
                                  long limit,
                                  boolean trimStrings,
                                  boolean storeEmptyStrings,
                                  boolean guessDataTypes,
                                  boolean includeFileSources,
                                  String fileSource,
                                  boolean includeArchiveName,
                                  String archiveFileName)
                           throws TreeReaderException

Throws:

TreeReaderException

findRecord

@Deprecated
protected static void findRecord(TreeImportUtilities.ColumnIndexAllocator allocator,
                                 List<Row> rows,
                                 TreeReader parser,
                                 String[] recordPath,
                                 int pathIndex,
                                 ImportColumnGroup rootColumnGroup,
                                 int limit,
                                 ImportParameters parameters)
                          throws TreeReaderException

Deprecated.

Use the version of this method which expands all parameters in the signature of the function

Parameters:

allocator -

rows -

parser -

recordPath -

pathIndex -

rootColumnGroup -

limit -

parameters -

Throws:

TreeReaderException

findRecord

protected static void findRecord(TreeImportUtilities.ColumnIndexAllocator columnIndexAllocator,
                                 List<Row> rows,
                                 TreeReader parser,
                                 String[] recordPath,
                                 int pathIndex,
                                 ImportColumnGroup rootColumnGroup,
                                 long limit,
                                 boolean trimStrings,
                                 boolean storeEmptyStrings,
                                 boolean guessDataTypes,
                                 boolean includeFileSource,
                                 String fileSource,
                                 boolean includeArchiveName,
                                 String archiveFileName)
                          throws TreeReaderException

Parameters:

columnIndexAllocator -

rows -

parser -

recordPath -

pathIndex -

rootColumnGroup -

limit -

trimStrings - trim whitespace from strings if true

storeEmptyStrings - store empty strings if true

guessDataTypes - guess whether strings represent numbers and convert

archiveFileName -

includeArchiveName -

Throws:

TreeReaderException

skip

protected static void skip(TreeReader parser)
                    throws TreeReaderException

Throws:

TreeReaderException

processRecord

@Deprecated
protected static void processRecord(TreeImportUtilities.ColumnIndexAllocator allocator,
                                    List<Row> rows,
                                    TreeReader parser,
                                    ImportColumnGroup rootColumnGroup,
                                    ImportParameters parameter)
                             throws TreeReaderException

Deprecated.

Use the version of this method which expands all parameters in the signature of the function

Parameters:

allocator -

rows -

parser -

rootColumnGroup -

parameter -

Throws:

TreeReaderException

processRecord

protected static void processRecord(TreeImportUtilities.ColumnIndexAllocator columnIndexAllocator,
                                    List<Row> rows,
                                    TreeReader parser,
                                    ImportColumnGroup rootColumnGroup,
                                    boolean trimStrings,
                                    boolean storeEmptyStrings,
                                    boolean guessDataTypes,
                                    boolean includeFileSources,
                                    String fileSource,
                                    boolean includeArchiveName,
                                    String archiveFileName)
                             throws TreeReaderException

processRecord parses Tree data for a single element and it's sub-elements, adding the parsed data as a row to the project

Parameters:

columnIndexAllocator -

rows -

parser -

rootColumnGroup -

archiveFileName -

includeArchiveName -

Throws:

TreeReaderException

processFieldAsRecord

protected static void processFieldAsRecord(TreeImportUtilities.ColumnIndexAllocator columnIndexAllocator,
                                           List<Row> rows,
                                           TreeReader parser,
                                           ImportColumnGroup rootColumnGroup,
                                           boolean trimStrings,
                                           boolean storeEmptyStrings,
                                           boolean guessDataType,
                                           boolean includeFileSources,
                                           String fileSource,
                                           boolean includeArchiveName,
                                           String archiveFileName)
                                    throws TreeReaderException

processFieldAsRecord parses Tree data for a single element and its sub-elements, adding the parsed data as a row to the project

Parameters:

columnIndexAllocator -

parser -

rootColumnGroup -

Throws:

TreeReaderException

addImportRecordToProject

protected static void addImportRecordToProject(ImportRecord record,
                                               List<Row> project,
                                               boolean includeFileSources,
                                               String fileSource,
                                               boolean includeArchiveName,
                                               String archiveName)

processSubRecord

@Deprecated
protected static void processSubRecord(TreeImportUtilities.ColumnIndexAllocator columnIndexAllocator,
                                       List<Row> rows,
                                       TreeReader parser,
                                       ImportColumnGroup columnGroup,
                                       ImportRecord record,
                                       int level,
                                       ImportParameters parameter)
                                throws TreeReaderException

Deprecated.

Throws:

TreeReaderException

processSubRecord

protected static void processSubRecord(TreeImportUtilities.ColumnIndexAllocator columnIndexAllocator,
                                       List<Row> rows,
                                       TreeReader parser,
                                       ImportColumnGroup columnGroup,
                                       ImportRecord record,
                                       int level,
                                       boolean trimStrings,
                                       boolean storeEmptyStrings,
                                       boolean guessDataType)
                                throws TreeReaderException

Parameters:

columnIndexAllocator -

rows -

parser -

columnGroup -

record -

Throws:

TreeReaderException