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/IRS990ScheduleR/Form990ScheduleRPartVI/AddressForeign/AddressLine1	1
/Return/ReturnData/IRS990ScheduleR/Form990ScheduleRPartVI/AddressForeign/AddressLine2	2
/Return/ReturnData/IRS990ScheduleR/Form990ScheduleRPartVI/AddressForeign/City	3
/Return/ReturnData/IRS990ScheduleR/Form990ScheduleRPartVI/AddressForeign/Country	4
/Return/ReturnData/IRS990ScheduleR/Form990ScheduleRPartVI/AddressForeign/PostalCode	5
/Return/ReturnData/IRS990ScheduleR/Form990ScheduleRPartVI/AddressForeign/ProvinceOrState	6
/Return/ReturnData/IRS990ScheduleR/Form990ScheduleRPartVI/AddressUS/AddressLine1	7
/Return/ReturnData/IRS990ScheduleR/Form990ScheduleRPartVI/AddressUS/AddressLine2	8
/Return/ReturnData/IRS990ScheduleR/Form990ScheduleRPartVI/AddressUS/City	9
/Return/ReturnData/IRS990ScheduleR/Form990ScheduleRPartVI/AddressUS/State	10
/Return/ReturnData/IRS990ScheduleR/Form990ScheduleRPartVI/AddressUS/ZIPCode	11
/Return/ReturnData/IRS990ScheduleR/Form990ScheduleRPartVI/AllPartnersC3S	12
/Return/ReturnData/IRS990ScheduleR/Form990ScheduleRPartVI/CodeVAmount	13
/Return/ReturnData/IRS990ScheduleR/Form990ScheduleRPartVI/DisproportionateAllocations	14
/Return/ReturnData/IRS990ScheduleR/Form990ScheduleRPartVI/EIN	15
/Return/ReturnData/IRS990ScheduleR/Form990ScheduleRPartVI/GeneralOrManagingPartner	16
/Return/ReturnData/IRS990ScheduleR/Form990ScheduleRPartVI/LegalDomicile/ForeignCountry	17
/Return/ReturnData/IRS990ScheduleR/Form990ScheduleRPartVI/LegalDomicile/State	18
/Return/ReturnData/IRS990ScheduleR/Form990ScheduleRPartVI/LegalDomicileForeignCountry	19
/Return/ReturnData/IRS990ScheduleR/Form990ScheduleRPartVI/LegalDomicileState	20
/Return/ReturnData/IRS990ScheduleR/Form990ScheduleRPartVI/NameOfBusiness/BusinessNameLine1	21
/Return/ReturnData/IRS990ScheduleR/Form990ScheduleRPartVI/NameOfBusiness/BusinessNameLine2	22
/Return/ReturnData/IRS990ScheduleR/Form990ScheduleRPartVI/PercentageOwnership	23
/Return/ReturnData/IRS990ScheduleR/Form990ScheduleRPartVI/PredominateIncomeDesc	24
/Return/ReturnData/IRS990ScheduleR/Form990ScheduleRPartVI/PrimaryActivity	25
/Return/ReturnData/IRS990ScheduleR/Form990ScheduleRPartVI/ShareOfEOYAssets	26
/Return/ReturnData/IRS990ScheduleR/Form990ScheduleRPartVI/ShareOfTotalIncome	27
/Return/ReturnData/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp/AllPartnersC3SInd	28
/Return/ReturnData/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp/BusinessName/BusinessNameLine1	29
/Return/ReturnData/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp/BusinessName/BusinessNameLine1Txt	30
/Return/ReturnData/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp/BusinessName/BusinessNameLine2	31
/Return/ReturnData/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp/BusinessName/BusinessNameLine2Txt	32
/Return/ReturnData/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp/DisproportionateAllocationsInd	33
/Return/ReturnData/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp/EIN	34
/Return/ReturnData/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp/ForeignAddress/AddressLine1	35
/Return/ReturnData/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp/ForeignAddress/AddressLine1Txt	36
/Return/ReturnData/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp/ForeignAddress/AddressLine2	37
/Return/ReturnData/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp/ForeignAddress/AddressLine2Txt	38
/Return/ReturnData/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp/ForeignAddress/City	39
/Return/ReturnData/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp/ForeignAddress/CityNm	40
/Return/ReturnData/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp/ForeignAddress/Country	41
/Return/ReturnData/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp/ForeignAddress/CountryCd	42
/Return/ReturnData/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp/ForeignAddress/ForeignPostalCd	43
/Return/ReturnData/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp/ForeignAddress/PostalCode	44
/Return/ReturnData/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp/ForeignAddress/ProvinceOrState	45
/Return/ReturnData/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp/ForeignAddress/ProvinceOrStateNm	46
/Return/ReturnData/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp/GeneralOrManagingPartnerInd	47
/Return/ReturnData/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp/LegalDomicileForeignCountryCd	48
/Return/ReturnData/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp/LegalDomicileStateCd	49
/Return/ReturnData/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp/OwnershipPct	50
/Return/ReturnData/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp/PredominateIncomeDesc	51
/Return/ReturnData/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp/PrimaryActivitiesTxt	52
/Return/ReturnData/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp/ShareOfEOYAssetsAmt	53
/Return/ReturnData/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp/ShareOfTotalIncomeAmt	54
/Return/ReturnData/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp/UBICodeVAmt	55
/Return/ReturnData/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp/USAddress/AddressLine1	56
/Return/ReturnData/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp/USAddress/AddressLine1Txt	57
/Return/ReturnData/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp/USAddress/AddressLine2	58
/Return/ReturnData/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp/USAddress/AddressLine2Txt	59
/Return/ReturnData/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp/USAddress/City	60
/Return/ReturnData/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp/USAddress/CityNm	61
/Return/ReturnData/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp/USAddress/State	62
/Return/ReturnData/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp/USAddress/StateAbbreviationCd	63
/Return/ReturnData/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp/USAddress/ZIPCd	64
/Return/ReturnData/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp/USAddress/ZIPCode	65

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

##                                         levelName
## 1  Return                                        
## 2   °--ReturnData                                
## 3       °--IRS990ScheduleR                       
## 4           ¦--Form990ScheduleRPartVI            
## 5           ¦   ¦--AddressForeign                
## 6           ¦   ¦   ¦--AddressLine1              
## 7           ¦   ¦   ¦--AddressLine2              
## 8           ¦   ¦   ¦--City                      
## 9           ¦   ¦   ¦--Country                   
## 10          ¦   ¦   ¦--PostalCode                
## 11          ¦   ¦   °--ProvinceOrState           
## 12          ¦   ¦--AddressUS                     
## 13          ¦   ¦   ¦--AddressLine1              
## 14          ¦   ¦   ¦--AddressLine2              
## 15          ¦   ¦   ¦--City                      
## 16          ¦   ¦   ¦--State                     
## 17          ¦   ¦   °--ZIPCode                   
## 18          ¦   ¦--AllPartnersC3S                
## 19          ¦   ¦--CodeVAmount                   
## 20          ¦   ¦--DisproportionateAllocations   
## 21          ¦   ¦--EIN                           
## 22          ¦   ¦--GeneralOrManagingPartner      
## 23          ¦   ¦--LegalDomicile                 
## 24          ¦   ¦   ¦--ForeignCountry            
## 25          ¦   ¦   °--State                     
## 26          ¦   ¦--LegalDomicileForeignCountry   
## 27          ¦   ¦--LegalDomicileState            
## 28          ¦   ¦--NameOfBusiness                
## 29          ¦   ¦   ¦--BusinessNameLine1         
## 30          ¦   ¦   °--BusinessNameLine2         
## 31          ¦   ¦--PercentageOwnership           
## 32          ¦   ¦--PredominateIncomeDesc         
## 33          ¦   ¦--PrimaryActivity               
## 34          ¦   ¦--ShareOfEOYAssets              
## 35          ¦   °--ShareOfTotalIncome            
## 36          °--UnrelatedOrgTxblPartnershipGrp    
## 37              ¦--AllPartnersC3SInd             
## 38              ¦--BusinessName                  
## 39              ¦   ¦--BusinessNameLine1         
## 40              ¦   ¦--BusinessNameLine1Txt      
## 41              ¦   ¦--BusinessNameLine2         
## 42              ¦   °--BusinessNameLine2Txt      
## 43              ¦--DisproportionateAllocationsInd
## 44              ¦--EIN                           
## 45              ¦--ForeignAddress                
## 46              ¦   ¦--AddressLine1              
## 47              ¦   ¦--AddressLine1Txt           
## 48              ¦   ¦--AddressLine2              
## 49              ¦   ¦--AddressLine2Txt           
## 50              ¦   ¦--City                      
## 51              ¦   ¦--CityNm                    
## 52              ¦   ¦--Country                   
## 53              ¦   ¦--CountryCd                 
## 54              ¦   ¦--ForeignPostalCd           
## 55              ¦   ¦--PostalCode                
## 56              ¦   ¦--ProvinceOrState           
## 57              ¦   °--ProvinceOrStateNm         
## 58              ¦--GeneralOrManagingPartnerInd   
## 59              ¦--LegalDomicileForeignCountryCd 
## 60              ¦--LegalDomicileStateCd          
## 61              ¦--OwnershipPct                  
## 62              ¦--PredominateIncomeDesc         
## 63              ¦--PrimaryActivitiesTxt          
## 64              ¦--ShareOfEOYAssetsAmt           
## 65              ¦--ShareOfTotalIncomeAmt         
## 66              ¦--UBICodeVAmt                   
## 67              °--USAddress                     
## 68                  ¦--AddressLine1              
## 69                  ¦--AddressLine1Txt           
## 70                  ¦--AddressLine2              
## 71                  ¦--AddressLine2Txt           
## 72                  ¦--City                      
## 73                  ¦--CityNm                    
## 74                  ¦--State                     
## 75                  ¦--StateAbbreviationCd       
## 76                  ¦--ZIPCd                     
## 77                  °--ZIPCode

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] "//Form990ScheduleRPartVI"         "//UnrelatedOrgTxblPartnershipGrp"

# new version
find_table_headers( table.name )

##  [1] "//Form990ScheduleRPartVI/AddressForeign"                        
##  [2] "//Form990ScheduleRPartVI/AddressUS"                             
##  [3] "//Form990ScheduleRPartVI/EIN"                                   
##  [4] "//Form990ScheduleRPartVI/NameOfBusiness"                        
##  [5] "//Form990ScheduleRPartVI/PrimaryActivity"                       
##  [6] "//Form990ScheduleRPartVI/LegalDomicile"                         
##  [7] "//Form990ScheduleRPartVI/LegalDomicileForeignCountry"           
##  [8] "//Form990ScheduleRPartVI/LegalDomicileState"                    
##  [9] "//Form990ScheduleRPartVI/PredominateIncomeDesc"                 
## [10] "//Form990ScheduleRPartVI/AllPartnersC3S"                        
## [11] "//Form990ScheduleRPartVI/ShareOfTotalIncome"                    
## [12] "//Form990ScheduleRPartVI/ShareOfEOYAssets"                      
## [13] "//Form990ScheduleRPartVI/DisproportionateAllocations"           
## [14] "//Form990ScheduleRPartVI/CodeVAmount"                           
## [15] "//Form990ScheduleRPartVI/GeneralOrManagingPartner"              
## [16] "//Form990ScheduleRPartVI/PercentageOwnership"                   
## [17] "//UnrelatedOrgTxblPartnershipGrp/ForeignAddress"                
## [18] "//UnrelatedOrgTxblPartnershipGrp/USAddress"                     
## [19] "//UnrelatedOrgTxblPartnershipGrp/EIN"                           
## [20] "//UnrelatedOrgTxblPartnershipGrp/BusinessName"                  
## [21] "//UnrelatedOrgTxblPartnershipGrp/PrimaryActivitiesTxt"          
## [22] "//UnrelatedOrgTxblPartnershipGrp/LegalDomicileForeignCountryCd" 
## [23] "//UnrelatedOrgTxblPartnershipGrp/LegalDomicileStateCd"          
## [24] "//UnrelatedOrgTxblPartnershipGrp/PredominateIncomeDesc"         
## [25] "//UnrelatedOrgTxblPartnershipGrp/AllPartnersC3SInd"             
## [26] "//UnrelatedOrgTxblPartnershipGrp/ShareOfTotalIncomeAmt"         
## [27] "//UnrelatedOrgTxblPartnershipGrp/ShareOfEOYAssetsAmt"           
## [28] "//UnrelatedOrgTxblPartnershipGrp/DisproportionateAllocationsInd"
## [29] "//UnrelatedOrgTxblPartnershipGrp/UBICodeVAmt"                   
## [30] "//UnrelatedOrgTxblPartnershipGrp/GeneralOrManagingPartnerInd"   
## [31] "//UnrelatedOrgTxblPartnershipGrp/OwnershipPct"

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

## [1] "//IRS990ScheduleR/Form990ScheduleRPartVI"        
## [2] "//IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp"

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: SR-P06-T01-UNRLTD-ORGS-TAXABLE-PARTNERSHIP

## [1] "NUMBER OF RETURNS PROCESSED:   1000"
## [1] "TOTAL NUMBER OF TABLE ROWS:   13"

TOTAL RUN TIME:

## Time difference of 13.12158 mins
## Time difference of -0.2186931 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] "SR_06_UNRLTD_ORG_PTR_EIN"         "SR_06_UNRLTD_ORG_PTR_PRIMARY_ACT"
##  [9] "SR_06_UNRLTD_ORG_PTR_DMCL_STATE"  "SR_06_UNRLTD_ORG_PTR_PREDMNT"    
## [11] "SR_06_UNRLTD_ORG_PTR_501C3_X"     "SR_06_UNRLTD_ORG_PTR_ALLOC_X"    
## [13] "SR_06_UNRLTD_ORG_PTR_GENERAL_X"   "SR_06_UNRLTD_ORG_PTR_PCT_OWN"    
## [15] "SR_06_UNRLTD_ORG_PTR_NAME_L1"     "SR_06_UNRLTD_ORG_PTR_ADDR_L1"    
## [17] "SR_06_UNRLTD_ORG_PTR_ADDR_CITY"   "SR_06_UNRLTD_ORG_PTR_ADDR_STATE" 
## [19] "SR_06_UNRLTD_ORG_PTR_ADDR_ZIP"    "SR_06_UNRLTD_ORG_PTR_TOT_INCOME" 
## [21] "SR_06_UNRLTD_ORG_PTR_EOY_ASSETS"  "SR_06_UNRLTD_ORG_PTR_CODE_V_AMT"

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/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp"             
## [3] "/Return/ReturnData/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp/BusinessName"
## [4] "/Return/ReturnData/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp/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       °--IRS990ScheduleR                       
## 4           °--UnrelatedOrgTxblPartnershipGrp    
## 5               ¦--AllPartnersC3SInd             
## 6               ¦--BusinessName                  
## 7               ¦   °--BusinessNameLine1Txt      
## 8               ¦--DisproportionateAllocationsInd
## 9               ¦--EIN                           
## 10              ¦--GeneralOrManagingPartnerInd   
## 11              ¦--LegalDomicileStateCd          
## 12              ¦--OwnershipPct                  
## 13              ¦--PredominateIncomeDesc         
## 14              ¦--PrimaryActivitiesTxt          
## 15              ¦--ShareOfEOYAssetsAmt           
## 16              ¦--ShareOfTotalIncomeAmt         
## 17              ¦--UBICodeVAmt                   
## 18              °--USAddress                     
## 19                  ¦--AddressLine1Txt           
## 20                  ¦--CityNm                    
## 21                  ¦--StateAbbreviationCd       
## 22                  °--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/IRS990ScheduleR/Form990ScheduleRPartVI/AddressForeign/AddressLine1	1
/Return/ReturnData/IRS990ScheduleR/Form990ScheduleRPartVI/AddressForeign/AddressLine2	2
/Return/ReturnData/IRS990ScheduleR/Form990ScheduleRPartVI/AddressForeign/City	3
/Return/ReturnData/IRS990ScheduleR/Form990ScheduleRPartVI/AddressForeign/Country	4
/Return/ReturnData/IRS990ScheduleR/Form990ScheduleRPartVI/AddressForeign/PostalCode	5
/Return/ReturnData/IRS990ScheduleR/Form990ScheduleRPartVI/AddressForeign/ProvinceOrState	6
/Return/ReturnData/IRS990ScheduleR/Form990ScheduleRPartVI/AddressUS/AddressLine1	7
/Return/ReturnData/IRS990ScheduleR/Form990ScheduleRPartVI/AddressUS/AddressLine2	8
/Return/ReturnData/IRS990ScheduleR/Form990ScheduleRPartVI/AddressUS/City	9
/Return/ReturnData/IRS990ScheduleR/Form990ScheduleRPartVI/AddressUS/State	10
/Return/ReturnData/IRS990ScheduleR/Form990ScheduleRPartVI/AddressUS/ZIPCode	11
/Return/ReturnData/IRS990ScheduleR/Form990ScheduleRPartVI/AllPartnersC3S	12
/Return/ReturnData/IRS990ScheduleR/Form990ScheduleRPartVI/CodeVAmount	13
/Return/ReturnData/IRS990ScheduleR/Form990ScheduleRPartVI/DisproportionateAllocations	14
/Return/ReturnData/IRS990ScheduleR/Form990ScheduleRPartVI/EIN	15
/Return/ReturnData/IRS990ScheduleR/Form990ScheduleRPartVI/GeneralOrManagingPartner	16
/Return/ReturnData/IRS990ScheduleR/Form990ScheduleRPartVI/LegalDomicile/ForeignCountry	17
/Return/ReturnData/IRS990ScheduleR/Form990ScheduleRPartVI/LegalDomicile/State	18
/Return/ReturnData/IRS990ScheduleR/Form990ScheduleRPartVI/LegalDomicileForeignCountry	19
/Return/ReturnData/IRS990ScheduleR/Form990ScheduleRPartVI/LegalDomicileState	20
/Return/ReturnData/IRS990ScheduleR/Form990ScheduleRPartVI/NameOfBusiness/BusinessNameLine1	21
/Return/ReturnData/IRS990ScheduleR/Form990ScheduleRPartVI/NameOfBusiness/BusinessNameLine2	22
/Return/ReturnData/IRS990ScheduleR/Form990ScheduleRPartVI/PercentageOwnership	23
/Return/ReturnData/IRS990ScheduleR/Form990ScheduleRPartVI/PredominateIncomeDesc	24
/Return/ReturnData/IRS990ScheduleR/Form990ScheduleRPartVI/PrimaryActivity	25
/Return/ReturnData/IRS990ScheduleR/Form990ScheduleRPartVI/ShareOfEOYAssets	26
/Return/ReturnData/IRS990ScheduleR/Form990ScheduleRPartVI/ShareOfTotalIncome	27
/Return/ReturnData/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp/AllPartnersC3SInd	28
/Return/ReturnData/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp/BusinessName/BusinessNameLine1	29
/Return/ReturnData/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp/BusinessName/BusinessNameLine1Txt	30
/Return/ReturnData/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp/BusinessName/BusinessNameLine2	31
/Return/ReturnData/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp/BusinessName/BusinessNameLine2Txt	32
/Return/ReturnData/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp/DisproportionateAllocationsInd	33
/Return/ReturnData/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp/EIN	34
/Return/ReturnData/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp/ForeignAddress/AddressLine1	35
/Return/ReturnData/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp/ForeignAddress/AddressLine1Txt	36
/Return/ReturnData/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp/ForeignAddress/AddressLine2	37
/Return/ReturnData/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp/ForeignAddress/AddressLine2Txt	38
/Return/ReturnData/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp/ForeignAddress/City	39
/Return/ReturnData/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp/ForeignAddress/CityNm	40
/Return/ReturnData/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp/ForeignAddress/Country	41
/Return/ReturnData/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp/ForeignAddress/CountryCd	42
/Return/ReturnData/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp/ForeignAddress/ForeignPostalCd	43
/Return/ReturnData/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp/ForeignAddress/PostalCode	44
/Return/ReturnData/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp/ForeignAddress/ProvinceOrState	45
/Return/ReturnData/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp/ForeignAddress/ProvinceOrStateNm	46
/Return/ReturnData/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp/GeneralOrManagingPartnerInd	47
/Return/ReturnData/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp/LegalDomicileForeignCountryCd	48
/Return/ReturnData/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp/LegalDomicileStateCd	49
/Return/ReturnData/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp/OwnershipPct	50
/Return/ReturnData/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp/PredominateIncomeDesc	51
/Return/ReturnData/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp/PrimaryActivitiesTxt	52
/Return/ReturnData/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp/ShareOfEOYAssetsAmt	53
/Return/ReturnData/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp/ShareOfTotalIncomeAmt	54
/Return/ReturnData/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp/UBICodeVAmt	55
/Return/ReturnData/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp/USAddress/AddressLine1	56
/Return/ReturnData/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp/USAddress/AddressLine1Txt	57
/Return/ReturnData/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp/USAddress/AddressLine2	58
/Return/ReturnData/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp/USAddress/AddressLine2Txt	59
/Return/ReturnData/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp/USAddress/City	60
/Return/ReturnData/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp/USAddress/CityNm	61
/Return/ReturnData/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp/USAddress/State	62
/Return/ReturnData/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp/USAddress/StateAbbreviationCd	63
/Return/ReturnData/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp/USAddress/ZIPCd	64
/Return/ReturnData/IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp/USAddress/ZIPCode	65

Grouping Variables

Identify all unique groups used in xpaths.

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

## [1] "//IRS990ScheduleR/Form990ScheduleRPartVI"        
## [2] "//IRS990ScheduleR/UnrelatedOrgTxblPartnershipGrp"

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: SR-P06-T01-UNRLTD-ORGS-TAXABLE-PARTNERSHIP

Last compiled on 05 April, 2023