Setup
Build the Table
- Write to File
Diagnostics
- Missing or Extra XPATHS
- Failes URLs
XML Table Structure
- Create Network Edgelists
- Visualize Tree Structure
XPATH Summary

Setup

Load Packages

library( irs990efile )  # functions for parsing efile XMLs
library( dplyr )        # data wrangling
library( purrr )        # data wrangling 
library( pander )       # formatting
library( knitr )        # formatting
library( DT )           # table printing
library( httr )         # web requests 
library( xmltools )     # xml utilities
library( xml2 )         # xml utilities
library( XML )          # xml utilities 
library( data.tree )    # network visualization
library( networkD3 )    # network visualization
library( igraph )       # network visualization

source( "R/rdb-functions-v2.R")
source( "R/utils.R")

Data

head( index )

The Concordance File

The concordance is an RDB to XML Crosswalk that maps all xpaths onto a specified set of variables. It is located in the irs990efile package.

The full data dictionary is available on GitHub.

DATA DICTIONARY

concordance %>% 
  filter( rdb_table == table.name )

xpath	id
/Return/ReturnData/IRS990ScheduleN/DispositionOfAssetsDetail/AssetsDistriOrExpnssPaidDesc	1
/Return/ReturnData/IRS990ScheduleN/DispositionOfAssetsDetail/BusinessName/BusinessNameLine1	2
/Return/ReturnData/IRS990ScheduleN/DispositionOfAssetsDetail/BusinessName/BusinessNameLine1Txt	3
/Return/ReturnData/IRS990ScheduleN/DispositionOfAssetsDetail/BusinessName/BusinessNameLine2	4
/Return/ReturnData/IRS990ScheduleN/DispositionOfAssetsDetail/BusinessName/BusinessNameLine2Txt	5
/Return/ReturnData/IRS990ScheduleN/DispositionOfAssetsDetail/DistributionDt	6
/Return/ReturnData/IRS990ScheduleN/DispositionOfAssetsDetail/EIN	7
/Return/ReturnData/IRS990ScheduleN/DispositionOfAssetsDetail/FairMarketValueOfAssetAmt	8
/Return/ReturnData/IRS990ScheduleN/DispositionOfAssetsDetail/ForeignAddress/AddressLine1	9
/Return/ReturnData/IRS990ScheduleN/DispositionOfAssetsDetail/ForeignAddress/AddressLine1Txt	10
/Return/ReturnData/IRS990ScheduleN/DispositionOfAssetsDetail/ForeignAddress/AddressLine2	11
/Return/ReturnData/IRS990ScheduleN/DispositionOfAssetsDetail/ForeignAddress/AddressLine2Txt	12
/Return/ReturnData/IRS990ScheduleN/DispositionOfAssetsDetail/ForeignAddress/City	13
/Return/ReturnData/IRS990ScheduleN/DispositionOfAssetsDetail/ForeignAddress/CityNm	14
/Return/ReturnData/IRS990ScheduleN/DispositionOfAssetsDetail/ForeignAddress/Country	15
/Return/ReturnData/IRS990ScheduleN/DispositionOfAssetsDetail/ForeignAddress/CountryCd	16
/Return/ReturnData/IRS990ScheduleN/DispositionOfAssetsDetail/ForeignAddress/ForeignPostalCd	17
/Return/ReturnData/IRS990ScheduleN/DispositionOfAssetsDetail/ForeignAddress/PostalCode	18
/Return/ReturnData/IRS990ScheduleN/DispositionOfAssetsDetail/ForeignAddress/ProvinceOrState	19
/Return/ReturnData/IRS990ScheduleN/DispositionOfAssetsDetail/ForeignAddress/ProvinceOrStateNm	20
/Return/ReturnData/IRS990ScheduleN/DispositionOfAssetsDetail/IRCSectionTxt	21
/Return/ReturnData/IRS990ScheduleN/DispositionOfAssetsDetail/MethodOfFMVDeterminationTxt	22
/Return/ReturnData/IRS990ScheduleN/DispositionOfAssetsDetail/PersonNm	23
/Return/ReturnData/IRS990ScheduleN/DispositionOfAssetsDetail/USAddress/AddressLine1	24
/Return/ReturnData/IRS990ScheduleN/DispositionOfAssetsDetail/USAddress/AddressLine1Txt	25
/Return/ReturnData/IRS990ScheduleN/DispositionOfAssetsDetail/USAddress/AddressLine2	26
/Return/ReturnData/IRS990ScheduleN/DispositionOfAssetsDetail/USAddress/AddressLine2Txt	27
/Return/ReturnData/IRS990ScheduleN/DispositionOfAssetsDetail/USAddress/City	28
/Return/ReturnData/IRS990ScheduleN/DispositionOfAssetsDetail/USAddress/CityNm	29
/Return/ReturnData/IRS990ScheduleN/DispositionOfAssetsDetail/USAddress/State	30
/Return/ReturnData/IRS990ScheduleN/DispositionOfAssetsDetail/USAddress/StateAbbreviationCd	31
/Return/ReturnData/IRS990ScheduleN/DispositionOfAssetsDetail/USAddress/ZIPCd	32
/Return/ReturnData/IRS990ScheduleN/DispositionOfAssetsDetail/USAddress/ZIPCode	33
/Return/ReturnData/IRS990ScheduleN/DispositionTable/AddressForeign/AddressLine1	34
/Return/ReturnData/IRS990ScheduleN/DispositionTable/AddressForeign/AddressLine2	35
/Return/ReturnData/IRS990ScheduleN/DispositionTable/AddressForeign/City	36
/Return/ReturnData/IRS990ScheduleN/DispositionTable/AddressForeign/Country	37
/Return/ReturnData/IRS990ScheduleN/DispositionTable/AddressForeign/PostalCode	38
/Return/ReturnData/IRS990ScheduleN/DispositionTable/AddressForeign/ProvinceOrState	39
/Return/ReturnData/IRS990ScheduleN/DispositionTable/AddressUS/AddressLine1	40
/Return/ReturnData/IRS990ScheduleN/DispositionTable/AddressUS/AddressLine2	41
/Return/ReturnData/IRS990ScheduleN/DispositionTable/AddressUS/City	42
/Return/ReturnData/IRS990ScheduleN/DispositionTable/AddressUS/State	43
/Return/ReturnData/IRS990ScheduleN/DispositionTable/AddressUS/ZIPCode	44
/Return/ReturnData/IRS990ScheduleN/DispositionTable/DateOfDistribution	45
/Return/ReturnData/IRS990ScheduleN/DispositionTable/DescriptionOfAsset	46
/Return/ReturnData/IRS990ScheduleN/DispositionTable/EIN	47
/Return/ReturnData/IRS990ScheduleN/DispositionTable/FMVOfAsset	48
/Return/ReturnData/IRS990ScheduleN/DispositionTable/IRCSection	49
/Return/ReturnData/IRS990ScheduleN/DispositionTable/MethodOfFMVDetermination	50
/Return/ReturnData/IRS990ScheduleN/DispositionTable/NameBusiness/BusinessNameLine1	51
/Return/ReturnData/IRS990ScheduleN/DispositionTable/NameBusiness/BusinessNameLine2	52
/Return/ReturnData/IRS990ScheduleN/DispositionTable/NamePerson	53
/Return/ReturnData/IRS990ScheduleN/Form990ScheduleNPartII/DispositionTable/AddressForeign/AddressLine1	54
/Return/ReturnData/IRS990ScheduleN/Form990ScheduleNPartII/DispositionTable/AddressForeign/AddressLine2	55
/Return/ReturnData/IRS990ScheduleN/Form990ScheduleNPartII/DispositionTable/AddressForeign/City	56
/Return/ReturnData/IRS990ScheduleN/Form990ScheduleNPartII/DispositionTable/AddressForeign/Country	57
/Return/ReturnData/IRS990ScheduleN/Form990ScheduleNPartII/DispositionTable/AddressForeign/PostalCode	58
/Return/ReturnData/IRS990ScheduleN/Form990ScheduleNPartII/DispositionTable/AddressForeign/ProvinceOrState	59
/Return/ReturnData/IRS990ScheduleN/Form990ScheduleNPartII/DispositionTable/AddressUS/AddressLine1	60
/Return/ReturnData/IRS990ScheduleN/Form990ScheduleNPartII/DispositionTable/AddressUS/AddressLine2	61
/Return/ReturnData/IRS990ScheduleN/Form990ScheduleNPartII/DispositionTable/AddressUS/City	62
/Return/ReturnData/IRS990ScheduleN/Form990ScheduleNPartII/DispositionTable/AddressUS/State	63
/Return/ReturnData/IRS990ScheduleN/Form990ScheduleNPartII/DispositionTable/AddressUS/ZIPCode	64
/Return/ReturnData/IRS990ScheduleN/Form990ScheduleNPartII/DispositionTable/DateOfDistribution	65
/Return/ReturnData/IRS990ScheduleN/Form990ScheduleNPartII/DispositionTable/DescriptionOfAsset	66
/Return/ReturnData/IRS990ScheduleN/Form990ScheduleNPartII/DispositionTable/EIN	67
/Return/ReturnData/IRS990ScheduleN/Form990ScheduleNPartII/DispositionTable/FMVOfAsset	68
/Return/ReturnData/IRS990ScheduleN/Form990ScheduleNPartII/DispositionTable/IRCSection	69
/Return/ReturnData/IRS990ScheduleN/Form990ScheduleNPartII/DispositionTable/MethodOfFMVDetermination	70
/Return/ReturnData/IRS990ScheduleN/Form990ScheduleNPartII/DispositionTable/NameBusiness/BusinessNameLine1	71
/Return/ReturnData/IRS990ScheduleN/Form990ScheduleNPartII/DispositionTable/NameBusiness/BusinessNameLine2	72
/Return/ReturnData/IRS990ScheduleN/Form990ScheduleNPartII/DispositionTable/NamePerson	73

xpaths <- as.character( t.xpaths$xpath )
el <- create_edgelist_v1( xpaths )
nd <- FromDataFrameNetwork( network=el )
print( nd )

##                                       levelName
## 1  Return                                      
## 2   °--ReturnData                              
## 3       °--IRS990ScheduleN                     
## 4           ¦--DispositionOfAssetsDetail       
## 5           ¦   ¦--AssetsDistriOrExpnssPaidDesc
## 6           ¦   ¦--BusinessName                
## 7           ¦   ¦   ¦--BusinessNameLine1       
## 8           ¦   ¦   ¦--BusinessNameLine1Txt    
## 9           ¦   ¦   ¦--BusinessNameLine2       
## 10          ¦   ¦   °--BusinessNameLine2Txt    
## 11          ¦   ¦--DistributionDt              
## 12          ¦   ¦--EIN                         
## 13          ¦   ¦--FairMarketValueOfAssetAmt   
## 14          ¦   ¦--ForeignAddress              
## 15          ¦   ¦   ¦--AddressLine1            
## 16          ¦   ¦   ¦--AddressLine1Txt         
## 17          ¦   ¦   ¦--AddressLine2            
## 18          ¦   ¦   ¦--AddressLine2Txt         
## 19          ¦   ¦   ¦--City                    
## 20          ¦   ¦   ¦--CityNm                  
## 21          ¦   ¦   ¦--Country                 
## 22          ¦   ¦   ¦--CountryCd               
## 23          ¦   ¦   ¦--ForeignPostalCd         
## 24          ¦   ¦   ¦--PostalCode              
## 25          ¦   ¦   ¦--ProvinceOrState         
## 26          ¦   ¦   °--ProvinceOrStateNm       
## 27          ¦   ¦--IRCSectionTxt               
## 28          ¦   ¦--MethodOfFMVDeterminationTxt 
## 29          ¦   ¦--PersonNm                    
## 30          ¦   °--USAddress                   
## 31          ¦       ¦--AddressLine1            
## 32          ¦       ¦--AddressLine1Txt         
## 33          ¦       ¦--AddressLine2            
## 34          ¦       ¦--AddressLine2Txt         
## 35          ¦       ¦--City                    
## 36          ¦       ¦--CityNm                  
## 37          ¦       ¦--State                   
## 38          ¦       ¦--StateAbbreviationCd     
## 39          ¦       ¦--ZIPCd                   
## 40          ¦       °--ZIPCode                 
## 41          ¦--DispositionTable                
## 42          ¦   ¦--AddressForeign              
## 43          ¦   ¦   ¦--AddressLine1            
## 44          ¦   ¦   ¦--AddressLine2            
## 45          ¦   ¦   ¦--City                    
## 46          ¦   ¦   ¦--Country                 
## 47          ¦   ¦   ¦--PostalCode              
## 48          ¦   ¦   °--ProvinceOrState         
## 49          ¦   ¦--AddressUS                   
## 50          ¦   ¦   ¦--AddressLine1            
## 51          ¦   ¦   ¦--AddressLine2            
## 52          ¦   ¦   ¦--City                    
## 53          ¦   ¦   ¦--State                   
## 54          ¦   ¦   °--ZIPCode                 
## 55          ¦   ¦--DateOfDistribution          
## 56          ¦   ¦--DescriptionOfAsset          
## 57          ¦   ¦--EIN                         
## 58          ¦   ¦--FMVOfAsset                  
## 59          ¦   ¦--IRCSection                  
## 60          ¦   ¦--MethodOfFMVDetermination    
## 61          ¦   ¦--NameBusiness                
## 62          ¦   ¦   ¦--BusinessNameLine1       
## 63          ¦   ¦   °--BusinessNameLine2       
## 64          ¦   °--NamePerson                  
## 65          °--Form990ScheduleNPartII          
## 66              °--DispositionTable            
## 67                  ¦--AddressForeign          
## 68                  ¦   ¦--AddressLine1        
## 69                  ¦   ¦--AddressLine2        
## 70                  ¦   ¦--City                
## 71                  ¦   ¦--Country             
## 72                  ¦   ¦--PostalCode          
## 73                  ¦   °--ProvinceOrState     
## 74                  ¦--AddressUS               
## 75                  ¦   ¦--AddressLine1        
## 76                  ¦   ¦--AddressLine2        
## 77                  ¦   ¦--City                
## 78                  ¦   ¦--State               
## 79                  ¦   °--ZIPCode             
## 80                  ¦--DateOfDistribution      
## 81                  ¦--DescriptionOfAsset      
## 82                  ¦--EIN                     
## 83                  ¦--FMVOfAsset              
## 84                  ¦--IRCSection              
## 85                  ¦--MethodOfFMVDetermination
## 86                  ¦--NameBusiness            
## 87                  ¦   ¦--BusinessNameLine1   
## 88                  ¦   °--BusinessNameLine2   
## 89                  °--NamePerson

SetGraphStyle( nd, rankdir = "LR")
SetEdgeStyle( nd, arrowhead = "vee", color = "grey20", penwidth = 2 )
SetNodeStyle( nd, 
              style = "filled,rounded", 
              shape = "box", 
              fillcolor = "LightBlue", 
              fontname = "helvetica", 
              fontcolor="black",
              tooltip = GetDefaultTooltip )

# SetNodeStyle(acme$IT, fillcolor = "LightBlue", penwidth = "5px")
plot( nd )

# old version
find_group_names( table.name )

## [1] "//DispositionOfAssetsDetail" "//DispositionTable"         
## [3] "//Form990ScheduleNPartII"

# new version
find_table_headers( table.name )

##  [1] "//DispositionOfAssetsDetail/AssetsDistriOrExpnssPaidDesc"
##  [2] "//DispositionOfAssetsDetail/DistributionDt"              
##  [3] "//DispositionOfAssetsDetail/FairMarketValueOfAssetAmt"   
##  [4] "//DispositionOfAssetsDetail/MethodOfFMVDeterminationTxt" 
##  [5] "//DispositionOfAssetsDetail/EIN"                         
##  [6] "//DispositionOfAssetsDetail/ForeignAddress"              
##  [7] "//DispositionOfAssetsDetail/USAddress"                   
##  [8] "//DispositionOfAssetsDetail/BusinessName"                
##  [9] "//DispositionOfAssetsDetail/PersonNm"                    
## [10] "//DispositionOfAssetsDetail/IRCSectionTxt"               
## [11] "//DispositionTable/DispositionTable"                     
## [12] "//DispositionTable/Form990ScheduleNPartII"               
## [13] "//Form990ScheduleNPartII/DispositionTable"               
## [14] "//Form990ScheduleNPartII/DirectorOfSuccessor"            
## [15] "//Form990ScheduleNPartII/EmployeeOfSuccessor"            
## [16] "//Form990ScheduleNPartII/OwnerOfSuccessor"               
## [17] "//Form990ScheduleNPartII/ReceiveCompensation"

# manual
if( ! is.null(table.headers) )
{table.headers}

Build the Table

# create new folder
dir.create( folder.name )
setwd( folder.name )

# create sample
set.seed( 1234 )
sample.index <- sample_n( index, sample.size )
write.csv( index, "sample-index.csv", row.names=F )
sample.urls <- sample.index$URL

# erase existing log files
file.create("XPATH-LOG.txt") 
file.create("FAIL-LOG.txt")


start.build.time <- Sys.time()    # --------------------

results.list <- list()
xpath.list <- list()


for( i in 1:length( sample.urls ) )
{
  
  url <- sample.urls[i]
  
  results.list[[i]] <- 
    build_rdb_table_v2( url, 
                        table.name, 
                        table.headers=table.headers )
  
  xpath.list[[i]]   <- 
    get_table_xpaths( url, 
                      table.name, 
                      table.headers=table.headers )
  
  if( i %% 100 == 0 ){ print(i) }
  
}


end.build.time <- Sys.time()      # --------------------


df <- dplyr::bind_rows( results.list )


fail.log <- readLines( "FAIL-LOG.txt" )
all.xpaths <- xpath.list %>% unlist() %>% unique() %>% sort()
cat( all.xpaths, sep="\n", file="XPATH-LOG.txt" )

TABLE: SN-P02-T01-DISPOSITION-OF-ASSETS

## [1] "NUMBER OF RETURNS PROCESSED:   1000"
## [1] "TOTAL NUMBER OF TABLE ROWS:   475"

TOTAL RUN TIME:

## Time difference of 21.05689 mins
## Time difference of -0.3509482 hours

Write to File

write.csv( df, paste0( folder.name, "/", table.name, ".csv" ), row.names=F )
head(df)

Are all names standardized?

names(df)

##  [1] "OBJECT_ID"                       "EIN"                            
##  [3] "NAME"                            "TAXYR"                          
##  [5] "FORMTYPE"                        "URL"                            
##  [7] "SN_02_DOA_ASSET_DIST_DESC"       "SN_02_DOA_ASSET_DIST_DATE"      
##  [9] "SN_02_DOA_ASSET_DIST_FMV"        "SN_02_DOA_ASSET_DIST_FMV_METHOD"
## [11] "SN_02_DOA_RECIP_EIN"             "SN_02_DOA_RECIP_IRC_SECTION"    
## [13] "SN_02_DOA_RECIP_NAME_ORG_L1"     "SN_02_DOA_RECIP_ADDR_L1"        
## [15] "SN_02_DOA_RECIP_ADDR_CITY."      "SN_02_DOA_RECIP_ADDR_STATE"     
## [17] "SN_02_DOA_RECIP_ADDR_ZIP"        "SN_02_DOA_RECIP_NAME_PERS"      
## [19] "SN_02_DOA_RECIP_ADDR_L2"         "SN_02_DOA_RECIP_ADDR_CNTR"      
## [21] "SN_02_DOA_RECIP_NAME_ORG_L2"

Diagnostics

Missing or Extra XPATHS

Check for xpaths that were used in the tables but do not exist in the Concordance file.

c.table <- dplyr::filter( concordance, rdb_table == table.name ) 
xpath.concordance <- c.table$xpath
setdiff( all.xpaths, xpath.concordance )

## [1] ""                                                                           
## [2] "/Return/ReturnData/IRS990ScheduleN/DispositionOfAssetsDetail/BusinessName"  
## [3] "/Return/ReturnData/IRS990ScheduleN/DispositionOfAssetsDetail/ForeignAddress"
## [4] "/Return/ReturnData/IRS990ScheduleN/DispositionOfAssetsDetail/USAddress"

Capture to update the Concordance file.

these <- setdiff( all.xpaths, xpath.concordance )
cat( these, sep="\n", file=paste0( folder.name, "/MISSING-XPATHS.txt" ) )

Failes URLs

Check the status of failed URLs.

if( length(fail.log) > 0 )
{ 
  sapply( fail.log, get_message ) %>% 
  table() %>% 
  pander() 
} else {
  print("ALL URLs ARE VALID")
}

## [1] "ALL URLs ARE VALID"

XML Table Structure

Create Network Edgelists

The create_edgelist() functions v1 and v2 are in R/utils.R.

V1 retains the root nodes Return and ReturnData.

V2 drops the root nodes and uses form versions “990” and “990EZ” as the root to visualize the sets of tables separately.

# KEEP ROOT NOTES Return & ReturnData
el <- create_edgelist_v1( all.xpaths )

Edgelist format:

V1	V2
Return	ReturnData
ReturnData	IRS990
IRS990	Form990PartVIISectionAGrp
Form990PartVIISectionAGrp	PersonNm
Form990PartVIISectionAGrp	TitleTxt
Form990PartVIISectionAGrp	AverageHoursPerWeekRt
Form990PartVIISectionAGrp	IndividualTrusteeOrDirectorInd
Form990PartVIISectionAGrp	OfficerInd
Form990PartVIISectionAGrp	ReportableCompFromOrgAmt
Form990PartVIISectionAGrp	ReportableCompFromRltdOrgAmt

Visualize Tree Structure

# library( data.tree )
nd <- FromDataFrameNetwork( network=el )
print( nd )

##                                       levelName
## 1  Return                                      
## 2   °--ReturnData                              
## 3       °--IRS990ScheduleN                     
## 4           °--DispositionOfAssetsDetail       
## 5               ¦--AssetsDistriOrExpnssPaidDesc
## 6               ¦--BusinessName                
## 7               ¦   ¦--BusinessNameLine1Txt    
## 8               ¦   °--BusinessNameLine2Txt    
## 9               ¦--DistributionDt              
## 10              ¦--EIN                         
## 11              ¦--FairMarketValueOfAssetAmt   
## 12              ¦--ForeignAddress              
## 13              ¦   ¦--AddressLine1Txt         
## 14              ¦   ¦--AddressLine2Txt         
## 15              ¦   ¦--CityNm                  
## 16              ¦   ¦--CountryCd               
## 17              ¦   ¦--ForeignPostalCd         
## 18              ¦   °--ProvinceOrStateNm       
## 19              ¦--IRCSectionTxt               
## 20              ¦--MethodOfFMVDeterminationTxt 
## 21              ¦--PersonNm                    
## 22              °--USAddress                   
## 23                  ¦--AddressLine1Txt         
## 24                  ¦--AddressLine2Txt         
## 25                  ¦--CityNm                  
## 26                  ¦--StateAbbreviationCd     
## 27                  °--ZIPCd

SetGraphStyle( nd, rankdir = "LR")
SetEdgeStyle( nd, arrowhead = "vee", color = "grey20", penwidth = 2 )
SetNodeStyle( nd, 
              style = "filled,rounded", 
              shape = "box", 
              fillcolor = "LightBlue", 
              fontname = "helvetica", 
              fontcolor="black",
              tooltip = GetDefaultTooltip )

# SetNodeStyle(acme$IT, fillcolor = "LightBlue", penwidth = "5px")
plot( nd )

# library( networkD3 )
# net <- ToDataFrameNetwork( nd, "name" )
# simpleNetwork( net, fontSize = 12 )
simpleNetwork( el, fontSize = 12 )

#plot with networkD3
radnet <- ToListExplicit( nd, unname = TRUE )
radialNetwork( radnet, fontSize = 12 )

XPATH Summary

Unique Xpaths for this RDB Table

t.xpaths <- 
  concordance %>%
  filter( rdb_table == table.name ) %>% 
  select( xpath ) %>% 
  unique() %>% 
  arrange( xpath ) %>% 
  mutate( id=row_number() ) 

t.xpaths %>% 
  kable( align="l" )

xpath	id
/Return/ReturnData/IRS990ScheduleN/DispositionOfAssetsDetail/AssetsDistriOrExpnssPaidDesc	1
/Return/ReturnData/IRS990ScheduleN/DispositionOfAssetsDetail/BusinessName/BusinessNameLine1	2
/Return/ReturnData/IRS990ScheduleN/DispositionOfAssetsDetail/BusinessName/BusinessNameLine1Txt	3
/Return/ReturnData/IRS990ScheduleN/DispositionOfAssetsDetail/BusinessName/BusinessNameLine2	4
/Return/ReturnData/IRS990ScheduleN/DispositionOfAssetsDetail/BusinessName/BusinessNameLine2Txt	5
/Return/ReturnData/IRS990ScheduleN/DispositionOfAssetsDetail/DistributionDt	6
/Return/ReturnData/IRS990ScheduleN/DispositionOfAssetsDetail/EIN	7
/Return/ReturnData/IRS990ScheduleN/DispositionOfAssetsDetail/FairMarketValueOfAssetAmt	8
/Return/ReturnData/IRS990ScheduleN/DispositionOfAssetsDetail/ForeignAddress/AddressLine1	9
/Return/ReturnData/IRS990ScheduleN/DispositionOfAssetsDetail/ForeignAddress/AddressLine1Txt	10
/Return/ReturnData/IRS990ScheduleN/DispositionOfAssetsDetail/ForeignAddress/AddressLine2	11
/Return/ReturnData/IRS990ScheduleN/DispositionOfAssetsDetail/ForeignAddress/AddressLine2Txt	12
/Return/ReturnData/IRS990ScheduleN/DispositionOfAssetsDetail/ForeignAddress/City	13
/Return/ReturnData/IRS990ScheduleN/DispositionOfAssetsDetail/ForeignAddress/CityNm	14
/Return/ReturnData/IRS990ScheduleN/DispositionOfAssetsDetail/ForeignAddress/Country	15
/Return/ReturnData/IRS990ScheduleN/DispositionOfAssetsDetail/ForeignAddress/CountryCd	16
/Return/ReturnData/IRS990ScheduleN/DispositionOfAssetsDetail/ForeignAddress/ForeignPostalCd	17
/Return/ReturnData/IRS990ScheduleN/DispositionOfAssetsDetail/ForeignAddress/PostalCode	18
/Return/ReturnData/IRS990ScheduleN/DispositionOfAssetsDetail/ForeignAddress/ProvinceOrState	19
/Return/ReturnData/IRS990ScheduleN/DispositionOfAssetsDetail/ForeignAddress/ProvinceOrStateNm	20
/Return/ReturnData/IRS990ScheduleN/DispositionOfAssetsDetail/IRCSectionTxt	21
/Return/ReturnData/IRS990ScheduleN/DispositionOfAssetsDetail/MethodOfFMVDeterminationTxt	22
/Return/ReturnData/IRS990ScheduleN/DispositionOfAssetsDetail/PersonNm	23
/Return/ReturnData/IRS990ScheduleN/DispositionOfAssetsDetail/USAddress/AddressLine1	24
/Return/ReturnData/IRS990ScheduleN/DispositionOfAssetsDetail/USAddress/AddressLine1Txt	25
/Return/ReturnData/IRS990ScheduleN/DispositionOfAssetsDetail/USAddress/AddressLine2	26
/Return/ReturnData/IRS990ScheduleN/DispositionOfAssetsDetail/USAddress/AddressLine2Txt	27
/Return/ReturnData/IRS990ScheduleN/DispositionOfAssetsDetail/USAddress/City	28
/Return/ReturnData/IRS990ScheduleN/DispositionOfAssetsDetail/USAddress/CityNm	29
/Return/ReturnData/IRS990ScheduleN/DispositionOfAssetsDetail/USAddress/State	30
/Return/ReturnData/IRS990ScheduleN/DispositionOfAssetsDetail/USAddress/StateAbbreviationCd	31
/Return/ReturnData/IRS990ScheduleN/DispositionOfAssetsDetail/USAddress/ZIPCd	32
/Return/ReturnData/IRS990ScheduleN/DispositionOfAssetsDetail/USAddress/ZIPCode	33
/Return/ReturnData/IRS990ScheduleN/DispositionTable/AddressForeign/AddressLine1	34
/Return/ReturnData/IRS990ScheduleN/DispositionTable/AddressForeign/AddressLine2	35
/Return/ReturnData/IRS990ScheduleN/DispositionTable/AddressForeign/City	36
/Return/ReturnData/IRS990ScheduleN/DispositionTable/AddressForeign/Country	37
/Return/ReturnData/IRS990ScheduleN/DispositionTable/AddressForeign/PostalCode	38
/Return/ReturnData/IRS990ScheduleN/DispositionTable/AddressForeign/ProvinceOrState	39
/Return/ReturnData/IRS990ScheduleN/DispositionTable/AddressUS/AddressLine1	40
/Return/ReturnData/IRS990ScheduleN/DispositionTable/AddressUS/AddressLine2	41
/Return/ReturnData/IRS990ScheduleN/DispositionTable/AddressUS/City	42
/Return/ReturnData/IRS990ScheduleN/DispositionTable/AddressUS/State	43
/Return/ReturnData/IRS990ScheduleN/DispositionTable/AddressUS/ZIPCode	44
/Return/ReturnData/IRS990ScheduleN/DispositionTable/DateOfDistribution	45
/Return/ReturnData/IRS990ScheduleN/DispositionTable/DescriptionOfAsset	46
/Return/ReturnData/IRS990ScheduleN/DispositionTable/EIN	47
/Return/ReturnData/IRS990ScheduleN/DispositionTable/FMVOfAsset	48
/Return/ReturnData/IRS990ScheduleN/DispositionTable/IRCSection	49
/Return/ReturnData/IRS990ScheduleN/DispositionTable/MethodOfFMVDetermination	50
/Return/ReturnData/IRS990ScheduleN/DispositionTable/NameBusiness/BusinessNameLine1	51
/Return/ReturnData/IRS990ScheduleN/DispositionTable/NameBusiness/BusinessNameLine2	52
/Return/ReturnData/IRS990ScheduleN/DispositionTable/NamePerson	53
/Return/ReturnData/IRS990ScheduleN/Form990ScheduleNPartII/DispositionTable/AddressForeign/AddressLine1	54
/Return/ReturnData/IRS990ScheduleN/Form990ScheduleNPartII/DispositionTable/AddressForeign/AddressLine2	55
/Return/ReturnData/IRS990ScheduleN/Form990ScheduleNPartII/DispositionTable/AddressForeign/City	56
/Return/ReturnData/IRS990ScheduleN/Form990ScheduleNPartII/DispositionTable/AddressForeign/Country	57
/Return/ReturnData/IRS990ScheduleN/Form990ScheduleNPartII/DispositionTable/AddressForeign/PostalCode	58
/Return/ReturnData/IRS990ScheduleN/Form990ScheduleNPartII/DispositionTable/AddressForeign/ProvinceOrState	59
/Return/ReturnData/IRS990ScheduleN/Form990ScheduleNPartII/DispositionTable/AddressUS/AddressLine1	60
/Return/ReturnData/IRS990ScheduleN/Form990ScheduleNPartII/DispositionTable/AddressUS/AddressLine2	61
/Return/ReturnData/IRS990ScheduleN/Form990ScheduleNPartII/DispositionTable/AddressUS/City	62
/Return/ReturnData/IRS990ScheduleN/Form990ScheduleNPartII/DispositionTable/AddressUS/State	63
/Return/ReturnData/IRS990ScheduleN/Form990ScheduleNPartII/DispositionTable/AddressUS/ZIPCode	64
/Return/ReturnData/IRS990ScheduleN/Form990ScheduleNPartII/DispositionTable/DateOfDistribution	65
/Return/ReturnData/IRS990ScheduleN/Form990ScheduleNPartII/DispositionTable/DescriptionOfAsset	66
/Return/ReturnData/IRS990ScheduleN/Form990ScheduleNPartII/DispositionTable/EIN	67
/Return/ReturnData/IRS990ScheduleN/Form990ScheduleNPartII/DispositionTable/FMVOfAsset	68
/Return/ReturnData/IRS990ScheduleN/Form990ScheduleNPartII/DispositionTable/IRCSection	69
/Return/ReturnData/IRS990ScheduleN/Form990ScheduleNPartII/DispositionTable/MethodOfFMVDetermination	70
/Return/ReturnData/IRS990ScheduleN/Form990ScheduleNPartII/DispositionTable/NameBusiness/BusinessNameLine1	71
/Return/ReturnData/IRS990ScheduleN/Form990ScheduleNPartII/DispositionTable/NameBusiness/BusinessNameLine2	72
/Return/ReturnData/IRS990ScheduleN/Form990ScheduleNPartII/DispositionTable/NamePerson	73

Grouping Variables

Identify all unique groups used in xpaths.

if( is.null(table.headers) )
{ find_table_headers( table.name ) } else
table.headers

##  [1] "//DispositionOfAssetsDetail/AssetsDistriOrExpnssPaidDesc"
##  [2] "//DispositionOfAssetsDetail/DistributionDt"              
##  [3] "//DispositionOfAssetsDetail/FairMarketValueOfAssetAmt"   
##  [4] "//DispositionOfAssetsDetail/MethodOfFMVDeterminationTxt" 
##  [5] "//DispositionOfAssetsDetail/EIN"                         
##  [6] "//DispositionOfAssetsDetail/ForeignAddress"              
##  [7] "//DispositionOfAssetsDetail/USAddress"                   
##  [8] "//DispositionOfAssetsDetail/BusinessName"                
##  [9] "//DispositionOfAssetsDetail/PersonNm"                    
## [10] "//DispositionOfAssetsDetail/IRCSectionTxt"               
## [11] "//DispositionTable/DispositionTable"                     
## [12] "//DispositionTable/Form990ScheduleNPartII"               
## [13] "//Form990ScheduleNPartII/DispositionTable"               
## [14] "//Form990ScheduleNPartII/DirectorOfSuccessor"            
## [15] "//Form990ScheduleNPartII/EmployeeOfSuccessor"            
## [16] "//Form990ScheduleNPartII/OwnerOfSuccessor"               
## [17] "//Form990ScheduleNPartII/ReceiveCompensation"

Groups can then be used to extract the 1:M RDB tables:

if( is.null(table.headers) )
{ table.headers <- find_table_headers( table.name ) }
demo.url <- "https://nccs-efile.s3.us-east-1.amazonaws.com/xml/201913079349300206_public.xml"
doc <- xml2::read_xml( demo.url )
xml2::xml_ns_strip( doc )
df.demo <- get_table_v2( doc, table.name, table.headers )
df.demo

## NULL

Standardize Variable Names

Mapping of xml variable names to concordance variable names:

get_var_map( table.name=table.name )

A table with proper names:

v.map <- get_var_map( table.name=table.name )

if( ! is.null(df.demo) )
{re_name( df.demo, v.map ) %>% as.data.frame()}

Print Table Structure

Demo of functions - demo data only.

[[1]]
<Form990PartVIISectionAGrp>
  <PersonNm>
    {text}
  <TitleTxt>
    {text}
  <AverageHoursPerWeekRt>
    {text}
  <IndividualTrusteeOrDirectorInd>
    {text}
  <OfficerInd>
    {text}
  <ReportableCompFromOrgAmt>
    {text}
  <ReportableCompFromRltdOrgAmt>
    {text}
  <OtherCompensationAmt>
    {text}

node.list[[1]] %>% xml_parent() %>% xmltools::xml_view_trees()

 (1) ------------

 +-- Form990PartVIISectionAGrp
  +-- PersonNm
  +-- TitleTxt
  +-- AverageHoursPerWeekRt
  +-- IndividualTrusteeOrDirectorInd
  +-- OfficerInd
  +-- ReportableCompFromOrgAmt
  +-- ReportableCompFromRltdOrgAmt
  ++-- OtherCompensationAmt


 (2) ------------

 +-- Form990PartVIISectionAGrp
  +-- PersonNm
  +-- TitleTxt
  +-- AverageHoursPerWeekRt
  +-- IndividualTrusteeOrDirectorInd
  +-- OfficerInd
  +-- ReportableCompFromOrgAmt
  +-- ReportableCompFromRltdOrgAmt
  ++-- OtherCompensationAmt

TABLE NAME: SN-P02-T01-DISPOSITION-OF-ASSETS

Last compiled on 05 April, 2023