PGFplot - Find duplicates within \pgfplotstablecreatecol

Question

Based on this question, I try to find duplicates in my generated hash list. These could be there, because I accidentally used the same X & Y values or because the first three digits of the hash's are equal. In this case, I want to give a compiler error like this \errmessage{Hash \tempHash already used!}.

Everything that is inside the \calcHash function seems to be very fragile and I don't know, how to add functionality without destroying the hash calculation.

In the following MWE I tried to find duplicates via a datatool DataBase. But this is not mandatory, when there is another easy possibility to search for duplicates, I'm absolutely fine with :)

\documentclass[10pt,a4paper]{article}
\usepackage{pgfplotstable}
\usepackage{xstring}
\usepackage{datatool}
\pgfplotsset{compat=newest}
\DTLnewdb{hashDB}
\newcommand{\calcHash}[1]{
    \noexpand\StrLeft{\pdfmdfivesum{#1}}{3}
    \newcommand{\tempHash}{\StrLeft{\pdfmdfivesum{#1}}{3}}
    %\DTLifdbempty{hashDB}
    %{
        %\DTLnewrow{hashDB}
        %\DTLnewdbentry{hashDB}{Hash}{\tempHash}
    %} 
    %\DTLforeach{hashDB}{\hash=hash}
    %{
        %\ifthenelse{\equal{\tempHash}{\hash}}
        %{
        %    \errmessage{Hash \tempHash already used!}
        %}{}
    %}
}
\pgfplotstableread[]{
X Y
1 a
2 b
5 c
}\mydata
\begin{document}
\pgfplotstablecreatecol[
create col/assign/.code={
        \edef\myHash{\noexpand\calcHash{\thisrow{X}\thisrow{Y}}}
        \pgfkeyslet{/pgfplots/table/create col/next content}\myHash
}]{ID}{\mydata}
\pgfplotstablegetrowsof{\mydata}
\pgfmathtruncatemacro\myDataRows{\pgfplotsretval-1}
\pgfplotstabletypeset[string type]{\mydata}
\end{document}

Answer 1

The following uses an L3 sequence and the L3 md5sum function to implement your \calcHash. Note that the \calcHash is used where it is, not stored in some other macro which is then assigned to the next content.

\documentclass[10pt,a4paper]{article}
\usepackage{pgfplotstable}
\pgfplotsset{compat=newest}
\ExplSyntaxOn
\str_new:N \l__pascals_hash_str
\seq_new:N \g__pascals_hashes_seq
\msg_new:nnn { pascals } { duplicate-hash }
  { Hash~ #1~ already~ used! }
\cs_generate_variant:Nn \str_set:Nn { Ne }
\cs_new_protected:Npn __pascals_calc_hash:n #1
  {
    \str_set:Ne \l__pascals_hash_str { \str_mdfive_hash:e {#1} }
    \seq_if_in:NVTF \g__pascals_hashes_seq \l__pascals_hash_str
      { \msg_error:nnV { pascals } { duplicate-hash } \l__pascals_hash_str }
      { \seq_gput_right:NV \g__pascals_hashes_seq \l__pascals_hash_str }
    \pgfkeyslet { /pgfplots/table/create~ col/next~ content } \l__pascals_hash_str
  }
\NewDocumentCommand \clearHashes {} { \seq_gclear:N \g__pascals_hashes_seq }
\NewDocumentCommand \calcHash { m } { __pascals_calc_hash:n {#1} }
\ExplSyntaxOff
\pgfplotstableread[]{
X Y
1 a
2 b
5 c
}\mydata
\begin{document}
\clearHashes
\pgfplotstablecreatecol[
create col/assign/.code={%
  \calcHash{\thisrow{X}\thisrow{Y}}%
}]{ID}{\mydata}
\pgfplotstablegetrowsof{\mydata}
\pgfmathtruncatemacro\myDataRows{\pgfplotsretval-1}
\pgfplotstabletypeset[string type]{\mydata}
\end{document}

---

A variant that only uses the first three tokens from the resulting hash:

\documentclass[10pt,a4paper]{article}
\usepackage{pgfplotstable}
\pgfplotsset{compat=newest}
\ExplSyntaxOn
\str_new:N \l__pascals_hash_str
\seq_new:N \g__pascals_hashes_seq
\msg_new:nnn { pascals } { duplicate-hash }
  { Hash~ #1~ already~ used! }
\cs_generate_variant:Nn \str_set:Nn { Ne }
\cs_generate_variant:Nn \str_range:nnn { e }
\cs_new_protected:Npn __pascals_calc_hash:n #1
  {
    \str_set:Ne \l__pascals_hash_str
      { \str_range:enn { \str_mdfive_hash:e {#1} } { 1 } { 3 } }
    \seq_if_in:NVTF \g__pascals_hashes_seq \l__pascals_hash_str
      { \msg_error:nnV { pascals } { duplicate-hash } \l__pascals_hash_str }
      { \seq_gput_right:NV \g__pascals_hashes_seq \l__pascals_hash_str }
    \pgfkeyslet { /pgfplots/table/create~ col/next~ content } \l__pascals_hash_str
  }
\NewDocumentCommand \clearHashes {} { \seq_gclear:N \g__pascals_hashes_seq }
\NewDocumentCommand \calcHash { m } { __pascals_calc_hash:n {#1} }
\ExplSyntaxOff
\pgfplotstableread[]{
X Y
1 a
2 b
5 c
}\mydata
\begin{document}
\clearHashes
\pgfplotstablecreatecol[
create col/assign/.code={%
  \calcHash{\thisrow{X}\thisrow{Y}}%
}]{ID}{\mydata}
\pgfplotstablegetrowsof{\mydata}
\pgfmathtruncatemacro\myDataRows{\pgfplotsretval-1}
\pgfplotstabletypeset[string type]{\mydata}
\end{document}

---

Yet another variant, this one defaulting to using the full hash, but with an optional argument to only use the first n characters.

\documentclass[10pt,a4paper]{article}
\usepackage{pgfplotstable}
\pgfplotsset{compat=newest}
\ExplSyntaxOn
\str_new:N \l__pascals_hash_str
\seq_new:N \g__pascals_hashes_seq
\msg_new:nnn { pascals } { duplicate-hash }
  { Hash~ #1~ already~ used! }
\cs_generate_variant:Nn \str_set:Nn { Ne }
\cs_generate_variant:Nn \str_range:nnn { e }
\cs_new_protected:Npn __pascals_calc_hash:nn #1#2
  {
    \str_set:Ne \l__pascals_hash_str
      { \str_range:enn { \str_mdfive_hash:e {#1} } { 1 } {#2} }
    \seq_if_in:NVTF \g__pascals_hashes_seq \l__pascals_hash_str
      { \msg_error:nnV { pascals } { duplicate-hash } \l__pascals_hash_str }
      { \seq_gput_right:NV \g__pascals_hashes_seq \l__pascals_hash_str }
    \pgfkeyslet { /pgfplots/table/create~ col/next~ content } \l__pascals_hash_str
  }
\NewDocumentCommand \clearHashes {} { \seq_gclear:N \g__pascals_hashes_seq }
\NewDocumentCommand \calcHash { O{-1} m } { __pascals_calc_hash:nn {#2} {#1} }
\ExplSyntaxOff
\pgfplotstableread[]{
X Y
1 a
2 b
5 c
}\mydata
\begin{document}
\clearHashes
\pgfplotstablecreatecol[
create col/assign/.code={%
  \calcHash[3]{\thisrow{X}\thisrow{Y}}%
}]{ID}{\mydata}
\pgfplotstablegetrowsof{\mydata}
\pgfmathtruncatemacro\myDataRows{\pgfplotsretval-1}
\pgfplotstabletypeset[string type]{\mydata}
\end{document}