%\VignetteIndexEntry{MiniDIFDUP_1}
%\VignettePackage{readJDX}
%\VignetteIndexEntry{readJDX}
%\VignetteKeyword{JCAMP, DX, NMR, IR, Raman}

\documentclass[12 pt]{article}

\usepackage[margin = 1.5 cm, letterpaper]{geometry}

\usepackage{inconsolata}
\renewcommand*\familydefault{\ttdefault}
\usepackage[T1]{fontenc}
\usepackage[parfill]{parskip}
\usepackage[dvipsnames, svgnames, table]{xcolor}

\pagestyle{empty}

%%%%%  Document Contents  %%%%%
% https://tex.stackexchange.com/a/25906/6580 for text boxes

\begin{document}
\fboxrule = 2 pt

\noindent\fcolorbox{red}{white}{ % highlight entire file
\minipage[t]{\dimexpr1.0\linewidth-2\fboxsep-2\fboxrule\relax}


\noindent\fcolorbox{blue}{white}{ % highlight meta data in blue
\minipage[t]{\dimexpr0.95\linewidth-2\fboxsep-2\fboxrule\relax}

\#\#TITLE=Tiny IR Spectrum for Demo\\
\#\#JCAMP-DX=4.24\\
\#\#DATA TYPE=INFRARED SPECTRUM\\
\#\#OWNER= GPL-3 (modified from BRUKER1.JCM (IUPAC) by B. Hanson)\\
\#\#XUNITS=1/CM\\
\#\#YUNITS=TRANSMITTANCE\\
\#\#FIRSTX= 4000.655017\\
\#\#LASTX= 400.1619262\\
\#\#DELTAX= -9.64245605E-1\\
\#\#MAXY= 95.83563804\\
\#\#MINY= -2.87246704E-1\\
\#\#XFACTOR= 4.882812500E-4\\
\#\#YFACTOR= 1.220703125E-2\\
\#\#NPOINTS= 612\\
\#\#FIRSTY= 7493
\endminipage}\hfill
\noindent\fcolorbox{orange}{white}{ % highlight variable list in orange
\minipage[t]{\dimexpr0.95\linewidth-2\fboxsep-2\fboxrule\relax}
\#\#XYDATA=(X++(Y..Y))\\
4861896G493jknkJlkJjJlKjOkNTjNKJNKMlmKqMnKkOjJKJKTNNMNKJMJjKTJTkMlKlKJ\\
4729586G542nNjKmJMJmMjljKmklTlJkNjMLNTMKlKjmkjkTlokmqkqj0oTrj4j3j9k3k8l8\\
4611099G336m7o0q2j07j38j73k10k40k62k53k11j55p2K0J09J76K11K28K20J97J70J45J22J01\\
4563705G025Q6P0O0N1M4L8L2K8K4K1J7J8J1RTQNMTkMTjNLNMJULJKUJjJkTnmkTLTJ0OLRMULJM\\
4453117G637JTLJKTJJLkKLlLjJLKjTMJjLJjKlKLljKJjJKTJljKJTlKTkLTjKJTMJTK\\
4320808G688JKTkLjJOkjJTjTKkKUkjLNkmLjLlJKlOmjKkMJTTkNKkJjkJjLTmKJkKkLJmJL\\
4186523G715jTKLKlJLkjKJjUKUkJKTljKnMJLmNJjUMkLkTUjMKJKjj3J1PnMKLJTKjMkK\\
4050263G750JjKJTKJqNKJlKlKTpNMlKKlJUjTOj9J8kjKklLlKLmMjJNj1j2K0lQj5\\
3929802G753k9L4QmOkMnJMkNJTkJKJlKTmTQkMk4LK3kJlJNLkLJLMnJKjLl8JK7lJ0MjLlj\\
3811316G794JkMkMpKkMmTnPJ5r1J2Q0k2J7kTjqJ6rPqOmn3L1K3Lm8L3K0j4J3pOjrMTkJl
\#\#END=
\endminipage}\hfill

\endminipage}\hfill

Key to the above:
\begin{itemize}
  \item \textcolor{red}{Entire File}. Input for \textit{findVariableLists}, as a vector of character strings.
  \item \textcolor{blue}{Metadata}.  Input for \textit{extractParams}, as a vector of character strings.
  \item \textcolor{orange}{Variable List}. Input for \textit{processVariableList} and \textit{processXYY}, as a vector of character strings.
\end{itemize}

<< setup, echo = FALSE >>=
suppressPackageStartupMessages(library("stringr"))
@

The entire file is the input to \textit{findVariableLists}. Here are two raw lines from the variable list; each is a character vector of length one:

<< getData, echo = FALSE >>=
mdd <- system.file("extdata", "MiniDIFDUP.JDX", package = "readJDX")
lines <- readLines(mdd)
@

<< rawLines, echo = FALSE >>=
print(lines[17:18])
@

The input to \textit{decompLines} and \textit{getComp} is a vector of \emph{named} raw lines:

<< namedRawLines, echo = FALSE >>=
names(lines) <- paste("Line", 1:length(lines), sep = "_")
print(lines[17:18])
@

The input to \textit{unSQZ}, \textit{insertDUPs}, \textit{deDIF} and \textit{yValueCheck} is a \emph{named} list of lines.  Each raw line has been split into the individual pieces and named according to its compression mode:

<< lineList, echo = FALSE >>=
# The following code is from decompLines

lineNames <- names(lines) # save to replace when functions nuke

# Helper Function
nameComp <- function(cvec) { # cvec = character vector
  	names(cvec) <- rep(NA_character_, length(cvec))
  	names(cvec)[grepl("[@A-Ia-i]{1}", cvec)] <- "SQZ"
  	names(cvec)[grepl("[%J-Rj-r]{1}", cvec)] <- "DIF"
  	names(cvec)[grepl("[S-Zs]{1}", cvec)] <- "DUP"
  	names(cvec)[!grepl("[@%A-Za-rs]", cvec)] <- "NUM" # anything else is a NUM/AFFN
  	cvec
}

# Preliminaries
lines <- gsub(",", ".", lines) # replace ',' with '.' -- needed for EU style files
lines <- gsub("\\s+\\${2}.*$", "", lines) # remove any ...xxxx  $$ checkpoint type entries
lines <- gsub("(\\+|-){1}([0-9]+)", " \\1\\2", lines) # put space ahead of +|- signs (PAC)
lines <- str_trim(lines, side = "both") # remove extra white space
lines <- str_replace_all(lines, "([@%A-Za-rs])", " \\1") # break into pieces by compression mode

# Convert to list to process each piece separately
lines <- as.list(lines)
names(lines) <- lineNames # replace the names that were nuked

FUN <- function(x) {unlist(strsplit(x, "\\s+"))}
lines <- lapply(lines, FUN)

# Name each entry by compression mode
lines <- lapply(lines, nameComp) # name each entry by the compression mode

print(lines[17])
@

The input to \textit{unDIF} is a character vector with entries named with ASDF mode:

<< unDIFinput, echo = FALSE >>=
line17 <- unlist(lines[17])
names(line17) <- gsub("Line_[0-9]*\\.", "", names(line17)) # names were whacked during unlisting
print(line17)
@

The input to \textit{repDUPs} is a character vector with length one:

<< repDUPsinput, echo = FALSE >>=
print(line17[21])
@

\end{document}