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/IRS990ScheduleG/Form990ScheduleGPartI/FundraiserActivityInformation/Activity	1
/Return/ReturnData/IRS990ScheduleG/Form990ScheduleGPartI/FundraiserActivityInformation/AmountRetainedByContractor	2
/Return/ReturnData/IRS990ScheduleG/Form990ScheduleGPartI/FundraiserActivityInformation/FundraiserControlOfFunds	3
/Return/ReturnData/IRS990ScheduleG/Form990ScheduleGPartI/FundraiserActivityInformation/GrossReceipts	4
/Return/ReturnData/IRS990ScheduleG/Form990ScheduleGPartI/FundraiserActivityInformation/NameOfIndividualOrOrganization/BusinessName/BusinessNameLine1	5
/Return/ReturnData/IRS990ScheduleG/Form990ScheduleGPartI/FundraiserActivityInformation/NameOfIndividualOrOrganization/BusinessName/BusinessNameLine2	6
/Return/ReturnData/IRS990ScheduleG/Form990ScheduleGPartI/FundraiserActivityInformation/NameOfIndividualOrOrganization/PersonName	7
/Return/ReturnData/IRS990ScheduleG/Form990ScheduleGPartI/FundraiserActivityInformation/NetToOrganization	8
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInfoGrp/ActivityTxt	9
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInfoGrp/ForeignAddress/AddressLine1	10
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInfoGrp/ForeignAddress/AddressLine1Txt	11
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInfoGrp/ForeignAddress/AddressLine2	12
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInfoGrp/ForeignAddress/AddressLine2Txt	13
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInfoGrp/ForeignAddress/City	14
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInfoGrp/ForeignAddress/CityNm	15
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInfoGrp/ForeignAddress/Country	16
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInfoGrp/ForeignAddress/CountryCd	17
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInfoGrp/ForeignAddress/ForeignPostalCd	18
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInfoGrp/ForeignAddress/PostalCode	19
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInfoGrp/ForeignAddress/ProvinceOrState	20
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInfoGrp/ForeignAddress/ProvinceOrStateNm	21
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInfoGrp/FundraiserControlOfFundsInd	22
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInfoGrp/GrossReceiptsAmt	23
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInfoGrp/NetToOrganizationAmt	24
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInfoGrp/OrganizationBusinessName/BusinessNameLine1	25
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInfoGrp/OrganizationBusinessName/BusinessNameLine1Txt	26
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInfoGrp/OrganizationBusinessName/BusinessNameLine2	27
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInfoGrp/OrganizationBusinessName/BusinessNameLine2Txt	28
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInfoGrp/PersonNm	29
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInfoGrp/RetainedByContractorAmt	30
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInfoGrp/USAddress/AddressLine1	31
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInfoGrp/USAddress/AddressLine1Txt	32
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInfoGrp/USAddress/AddressLine2	33
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInfoGrp/USAddress/AddressLine2Txt	34
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInfoGrp/USAddress/City	35
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInfoGrp/USAddress/CityNm	36
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInfoGrp/USAddress/State	37
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInfoGrp/USAddress/StateAbbreviationCd	38
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInfoGrp/USAddress/ZIPCd	39
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInfoGrp/USAddress/ZIPCode	40
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInformation/Activity	41
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInformation/AddressForeign/AddressLine1	42
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInformation/AddressForeign/AddressLine2	43
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInformation/AddressForeign/City	44
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInformation/AddressForeign/Country	45
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInformation/AddressForeign/PostalCode	46
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInformation/AddressForeign/ProvinceOrState	47
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInformation/AddressUS/AddressLine1	48
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInformation/AddressUS/AddressLine2	49
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInformation/AddressUS/City	50
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInformation/AddressUS/State	51
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInformation/AddressUS/ZIPCode	52
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInformation/AmountRetainedByContractor	53
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInformation/FundraiserControlOfFunds	54
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInformation/GrossReceipts	55
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInformation/NameOfIndividual	56
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInformation/NameOfOrganization/BusinessNameLine1	57
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInformation/NameOfOrganization/BusinessNameLine2	58
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInformation/NetToOrganization	59

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

##                                             levelName
## 1  Return                                            
## 2   °--ReturnData                                    
## 3       °--IRS990ScheduleG                           
## 4           ¦--Form990ScheduleGPartI                 
## 5           ¦   °--FundraiserActivityInformation     
## 6           ¦       ¦--Activity                      
## 7           ¦       ¦--AmountRetainedByContractor    
## 8           ¦       ¦--FundraiserControlOfFunds      
## 9           ¦       ¦--GrossReceipts                 
## 10          ¦       ¦--NameOfIndividualOrOrganization
## 11          ¦       ¦   ¦--BusinessName              
## 12          ¦       ¦   ¦   ¦--BusinessNameLine1     
## 13          ¦       ¦   ¦   °--BusinessNameLine2     
## 14          ¦       ¦   °--PersonName                
## 15          ¦       ¦--NetToOrganization             
## 16          ¦       ¦--AddressForeign                
## 17          ¦       ¦   ¦--AddressLine1              
## 18          ¦       ¦   ¦--AddressLine2              
## 19          ¦       ¦   ¦--City                      
## 20          ¦       ¦   ¦--Country                   
## 21          ¦       ¦   ¦--PostalCode                
## 22          ¦       ¦   °--ProvinceOrState           
## 23          ¦       ¦--AddressUS                     
## 24          ¦       ¦   ¦--AddressLine1              
## 25          ¦       ¦   ¦--AddressLine2              
## 26          ¦       ¦   ¦--City                      
## 27          ¦       ¦   ¦--State                     
## 28          ¦       ¦   °--ZIPCode                   
## 29          ¦       ¦--NameOfIndividual              
## 30          ¦       °--NameOfOrganization            
## 31          ¦           ¦--BusinessNameLine1         
## 32          ¦           °--BusinessNameLine2         
## 33          ¦--FundraiserActivityInfoGrp             
## 34          ¦   ¦--ActivityTxt                       
## 35          ¦   ¦--ForeignAddress                    
## 36          ¦   ¦   ¦--AddressLine1                  
## 37          ¦   ¦   ¦--AddressLine1Txt               
## 38          ¦   ¦   ¦--AddressLine2                  
## 39          ¦   ¦   ¦--AddressLine2Txt               
## 40          ¦   ¦   ¦--City                          
## 41          ¦   ¦   ¦--CityNm                        
## 42          ¦   ¦   ¦--Country                       
## 43          ¦   ¦   ¦--CountryCd                     
## 44          ¦   ¦   ¦--ForeignPostalCd               
## 45          ¦   ¦   ¦--PostalCode                    
## 46          ¦   ¦   ¦--ProvinceOrState               
## 47          ¦   ¦   °--ProvinceOrStateNm             
## 48          ¦   ¦--FundraiserControlOfFundsInd       
## 49          ¦   ¦--GrossReceiptsAmt                  
## 50          ¦   ¦--NetToOrganizationAmt              
## 51          ¦   ¦--OrganizationBusinessName          
## 52          ¦   ¦   ¦--BusinessNameLine1             
## 53          ¦   ¦   ¦--BusinessNameLine1Txt          
## 54          ¦   ¦   ¦--BusinessNameLine2             
## 55          ¦   ¦   °--BusinessNameLine2Txt          
## 56          ¦   ¦--PersonNm                          
## 57          ¦   ¦--RetainedByContractorAmt           
## 58          ¦   °--USAddress                         
## 59          ¦       ¦--AddressLine1                  
## 60          ¦       ¦--AddressLine1Txt               
## 61          ¦       ¦--AddressLine2                  
## 62          ¦       ¦--AddressLine2Txt               
## 63          ¦       ¦--City                          
## 64          ¦       ¦--CityNm                        
## 65          ¦       ¦--State                         
## 66          ¦       ¦--StateAbbreviationCd           
## 67          ¦       ¦--ZIPCd                         
## 68          ¦       °--ZIPCode                       
## 69          °--FundraiserActivityInformation         
## 70              ¦--Activity                          
## 71              ¦--AmountRetainedByContractor        
## 72              ¦--FundraiserControlOfFunds          
## 73              ¦--GrossReceipts                     
## 74              ¦--NameOfIndividualOrOrganization    
## 75              ¦   ¦--BusinessName                  
## 76              ¦   ¦   ¦--BusinessNameLine1         
## 77              ¦   ¦   °--BusinessNameLine2         
## 78              ¦   °--PersonName                    
## 79              ¦--NetToOrganization                 
## 80              ¦--AddressForeign                    
## 81              ¦   ¦--AddressLine1                  
## 82              ¦   ¦--AddressLine2                  
## 83              ¦   ¦--City                          
## 84              ¦   ¦--Country                       
## 85              ¦   ¦--PostalCode                    
## 86              ¦   °--ProvinceOrState               
## 87              ¦--AddressUS                         
## 88              ¦   ¦--AddressLine1                  
## 89              ¦   ¦--AddressLine2                  
## 90              ¦   ¦--City                          
## 91              ¦   ¦--State                         
## 92              ¦   °--ZIPCode                       
## 93              ¦--NameOfIndividual                  
## 94              °--NameOfOrganization                
## 95                  ¦--BusinessNameLine1             
## 96                  °--BusinessNameLine2

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] "//FundraiserActivityInformation" "//FundraiserActivityInfoGrp"    
## [3] "//Form990ScheduleGPartI"

# new version
find_table_headers( table.name )

##  [1] "//FundraiserActivityInformation/FundraiserActivityInformation"
##  [2] "//FundraiserActivityInformation/Form990ScheduleGPartI"        
##  [3] "//FundraiserActivityInfoGrp/ForeignAddress"                   
##  [4] "//FundraiserActivityInfoGrp/USAddress"                        
##  [5] "//FundraiserActivityInfoGrp/PersonNm"                         
##  [6] "//FundraiserActivityInfoGrp/OrganizationBusinessName"         
##  [7] "//FundraiserActivityInfoGrp/ActivityTxt"                      
##  [8] "//FundraiserActivityInfoGrp/FundraiserControlOfFundsInd"      
##  [9] "//FundraiserActivityInfoGrp/GrossReceiptsAmt"                 
## [10] "//FundraiserActivityInfoGrp/RetainedByContractorAmt"          
## [11] "//FundraiserActivityInfoGrp/NetToOrganizationAmt"             
## [12] "//Form990ScheduleGPartI/MailSolicitations"                    
## [13] "//Form990ScheduleGPartI/EmailSolicitations"                   
## [14] "//Form990ScheduleGPartI/PhoneSolicitations"                   
## [15] "//Form990ScheduleGPartI/InPersonSolicitations"                
## [16] "//Form990ScheduleGPartI/SolicitationOfNonGovtGrants"          
## [17] "//Form990ScheduleGPartI/SolicitationOfGovtGrants"             
## [18] "//Form990ScheduleGPartI/SpecialFundraisingEvents"             
## [19] "//Form990ScheduleGPartI/AgreementRefFundraising"              
## [20] "//Form990ScheduleGPartI/FundraiserActivityInformation"        
## [21] "//Form990ScheduleGPartI/TotalGrossReceipts"                   
## [22] "//Form990ScheduleGPartI/TotalNetToOrganization"               
## [23] "//Form990ScheduleGPartI/TotalRetainedByContractors"           
## [24] "//Form990ScheduleGPartI/LicensedStates"

# 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: SG-P01-T01-FUNDRAISERS-INFO

## [1] "NUMBER OF RETURNS PROCESSED:   1000"
## [1] "TOTAL NUMBER OF TABLE ROWS:   106"

TOTAL RUN TIME:

## Time difference of 14.60528 mins
## Time difference of -0.2434214 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] "SG_01_FUNDRAISER_ACT"         "SG_01_FUNDRAISER_CTRL_FUND_X"
##  [9] "SG_01_FUNDRAISER_ACT_GRORCPT" "SG_01_FUNDRAISER_AMT_PAID"   
## [11] "SG_01_FUNDRAISER_AMT_ORG"     "SG_01_FUNDRAISER_NAME_ORG_L1"
## [13] "SG_01_FUNDRAISER_ADDR_L1"     "SG_01_FUNDRAISER_ADDR_CITY"  
## [15] "SG_01_FUNDRAISER_ADDR_STATE"  "SG_01_FUNDRAISER_ADDR_ZIP"   
## [17] "SG_01_FUNDRAISER_NAME_INDIV"  "SG_01_FUNDRAISER_ADDR_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/IRS990ScheduleG/FundraiserActivityInfoGrp/OrganizationBusinessName"
## [3] "/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInfoGrp/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       °--IRS990ScheduleG                    
## 4           °--FundraiserActivityInfoGrp      
## 5               ¦--ActivityTxt                
## 6               ¦--FundraiserControlOfFundsInd
## 7               ¦--GrossReceiptsAmt           
## 8               ¦--NetToOrganizationAmt       
## 9               ¦--OrganizationBusinessName   
## 10              ¦   °--BusinessNameLine1Txt   
## 11              ¦--PersonNm                   
## 12              ¦--RetainedByContractorAmt    
## 13              °--USAddress                  
## 14                  ¦--AddressLine1Txt        
## 15                  ¦--AddressLine2Txt        
## 16                  ¦--CityNm                 
## 17                  ¦--StateAbbreviationCd    
## 18                  °--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/IRS990ScheduleG/Form990ScheduleGPartI/FundraiserActivityInformation/Activity	1
/Return/ReturnData/IRS990ScheduleG/Form990ScheduleGPartI/FundraiserActivityInformation/AmountRetainedByContractor	2
/Return/ReturnData/IRS990ScheduleG/Form990ScheduleGPartI/FundraiserActivityInformation/FundraiserControlOfFunds	3
/Return/ReturnData/IRS990ScheduleG/Form990ScheduleGPartI/FundraiserActivityInformation/GrossReceipts	4
/Return/ReturnData/IRS990ScheduleG/Form990ScheduleGPartI/FundraiserActivityInformation/NameOfIndividualOrOrganization/BusinessName/BusinessNameLine1	5
/Return/ReturnData/IRS990ScheduleG/Form990ScheduleGPartI/FundraiserActivityInformation/NameOfIndividualOrOrganization/BusinessName/BusinessNameLine2	6
/Return/ReturnData/IRS990ScheduleG/Form990ScheduleGPartI/FundraiserActivityInformation/NameOfIndividualOrOrganization/PersonName	7
/Return/ReturnData/IRS990ScheduleG/Form990ScheduleGPartI/FundraiserActivityInformation/NetToOrganization	8
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInfoGrp/ActivityTxt	9
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInfoGrp/ForeignAddress/AddressLine1	10
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInfoGrp/ForeignAddress/AddressLine1Txt	11
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInfoGrp/ForeignAddress/AddressLine2	12
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInfoGrp/ForeignAddress/AddressLine2Txt	13
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInfoGrp/ForeignAddress/City	14
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInfoGrp/ForeignAddress/CityNm	15
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInfoGrp/ForeignAddress/Country	16
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInfoGrp/ForeignAddress/CountryCd	17
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInfoGrp/ForeignAddress/ForeignPostalCd	18
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInfoGrp/ForeignAddress/PostalCode	19
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInfoGrp/ForeignAddress/ProvinceOrState	20
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInfoGrp/ForeignAddress/ProvinceOrStateNm	21
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInfoGrp/FundraiserControlOfFundsInd	22
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInfoGrp/GrossReceiptsAmt	23
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInfoGrp/NetToOrganizationAmt	24
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInfoGrp/OrganizationBusinessName/BusinessNameLine1	25
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInfoGrp/OrganizationBusinessName/BusinessNameLine1Txt	26
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInfoGrp/OrganizationBusinessName/BusinessNameLine2	27
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInfoGrp/OrganizationBusinessName/BusinessNameLine2Txt	28
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInfoGrp/PersonNm	29
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInfoGrp/RetainedByContractorAmt	30
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInfoGrp/USAddress/AddressLine1	31
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInfoGrp/USAddress/AddressLine1Txt	32
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInfoGrp/USAddress/AddressLine2	33
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInfoGrp/USAddress/AddressLine2Txt	34
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInfoGrp/USAddress/City	35
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInfoGrp/USAddress/CityNm	36
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInfoGrp/USAddress/State	37
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInfoGrp/USAddress/StateAbbreviationCd	38
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInfoGrp/USAddress/ZIPCd	39
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInfoGrp/USAddress/ZIPCode	40
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInformation/Activity	41
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInformation/AddressForeign/AddressLine1	42
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInformation/AddressForeign/AddressLine2	43
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInformation/AddressForeign/City	44
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInformation/AddressForeign/Country	45
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInformation/AddressForeign/PostalCode	46
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInformation/AddressForeign/ProvinceOrState	47
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInformation/AddressUS/AddressLine1	48
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInformation/AddressUS/AddressLine2	49
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInformation/AddressUS/City	50
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInformation/AddressUS/State	51
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInformation/AddressUS/ZIPCode	52
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInformation/AmountRetainedByContractor	53
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInformation/FundraiserControlOfFunds	54
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInformation/GrossReceipts	55
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInformation/NameOfIndividual	56
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInformation/NameOfOrganization/BusinessNameLine1	57
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInformation/NameOfOrganization/BusinessNameLine2	58
/Return/ReturnData/IRS990ScheduleG/FundraiserActivityInformation/NetToOrganization	59

Grouping Variables

Identify all unique groups used in xpaths.

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

##  [1] "//FundraiserActivityInformation/FundraiserActivityInformation"
##  [2] "//FundraiserActivityInformation/Form990ScheduleGPartI"        
##  [3] "//FundraiserActivityInfoGrp/ForeignAddress"                   
##  [4] "//FundraiserActivityInfoGrp/USAddress"                        
##  [5] "//FundraiserActivityInfoGrp/PersonNm"                         
##  [6] "//FundraiserActivityInfoGrp/OrganizationBusinessName"         
##  [7] "//FundraiserActivityInfoGrp/ActivityTxt"                      
##  [8] "//FundraiserActivityInfoGrp/FundraiserControlOfFundsInd"      
##  [9] "//FundraiserActivityInfoGrp/GrossReceiptsAmt"                 
## [10] "//FundraiserActivityInfoGrp/RetainedByContractorAmt"          
## [11] "//FundraiserActivityInfoGrp/NetToOrganizationAmt"             
## [12] "//Form990ScheduleGPartI/MailSolicitations"                    
## [13] "//Form990ScheduleGPartI/EmailSolicitations"                   
## [14] "//Form990ScheduleGPartI/PhoneSolicitations"                   
## [15] "//Form990ScheduleGPartI/InPersonSolicitations"                
## [16] "//Form990ScheduleGPartI/SolicitationOfNonGovtGrants"          
## [17] "//Form990ScheduleGPartI/SolicitationOfGovtGrants"             
## [18] "//Form990ScheduleGPartI/SpecialFundraisingEvents"             
## [19] "//Form990ScheduleGPartI/AgreementRefFundraising"              
## [20] "//Form990ScheduleGPartI/FundraiserActivityInformation"        
## [21] "//Form990ScheduleGPartI/TotalGrossReceipts"                   
## [22] "//Form990ScheduleGPartI/TotalNetToOrganization"               
## [23] "//Form990ScheduleGPartI/TotalRetainedByContractors"           
## [24] "//Form990ScheduleGPartI/LicensedStates"

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: SG-P01-T01-FUNDRAISERS-INFO

Last compiled on 04 April, 2023