SEC embedded XML document parser in R

script.r

# Load XML library
# If not already installed, install with
# sudo Rscript -e 'install.packages("XML", repos = "http://cran.us.r-project.org")'
library(XML)

# Select input file
FILENAME <- "./0001086364-17-000005.txt"

# Read raw file into memory
book <- readLines(FILENAME)

# Store each XML document in this list
chapters <- list()

# Loop through lines in raw file searching for embedded XML documents
isInChapter <- FALSE
currentChapter <- 0
currentIndex <- 1
for (currentLine in 1:length(book)) {
    if (!isInChapter && book[currentLine] == "<XML>") {
        # This is the start of a new embedded docoument
        # Set the state accordingly and reset the chapter line counter
        isInChapter <- TRUE
        currentIndex <- 0
        currentChapter <- currentChapter + 1
        chapters[[currentChapter]] <- list()
    }
    else if (isInChapter && book[currentLine] == "</XML>") {
        # This is the start of a new embedded docoument
        # Set the state accordingly
        isInChapter <- FALSE
    }
    else if (isInChapter) {
        # We're still in a chapter
        # Append the current line to the end of the active chapter
        currentIndex <- currentIndex + 1
        chapters[[currentChapter]][[currentIndex]] <- book[currentLine]
    }
}

# Loop through each document searching for the target document
data <- list()
for (currentChapter in 1:length(chapters)) {
    document <- xmlParse(chapters[[currentChapter]])
    root <- xmlRoot(document)
    if (xmlName(root) == "informationTable") {
        rows = xmlChildren(root)
        for (currentIndex in 1:length(rows)) {
            row = rows[[currentIndex]]
            name <- xmlValue(xmlChildren(row)[[1]])
            value <- xmlValue(xmlChildren(row)[[4]])
            data[[currentIndex]] <- list(name, value)
        }
    }
}

cat("Total Rows: ", length(data), "\n")
print("Example Data:")
for (row in 1:10) {
    cat(data[[row]][[2]], "\t", data[[row]][[1]], "\n")
}