diff options
Diffstat (limited to 'reproduce/analysis/make/format.mk')
-rw-r--r-- | reproduce/analysis/make/format.mk | 44 |
1 files changed, 22 insertions, 22 deletions
diff --git a/reproduce/analysis/make/format.mk b/reproduce/analysis/make/format.mk index fd4060a..979475f 100644 --- a/reproduce/analysis/make/format.mk +++ b/reproduce/analysis/make/format.mk @@ -6,7 +6,7 @@ # because it provides interesting statistics about tools and methods used # in scientific papers. # -# Copyright (C) 2020-2021 Mohammad Akhlaghi <mohammad@akhlaghi.org> +# Copyright (C) 2020-2022 Mohammad Akhlaghi <mohammad@akhlaghi.org> # # This Makefile is free software: you can redistribute it and/or modify it # under the terms of the GNU General Public License as published by the @@ -28,13 +28,13 @@ mk20tab3 = $(a1dir)/table-3.txt $(a1dir):; mkdir $@ $(mk20tab3): $(indir)/menke20.xlsx | $(a1dir) - # Set a base-name for the table-3 data. +# Set a base-name for the table-3 data. base=$(basename $(notdir $<))-table-3 - # Unfortunately XLSX I/O only works when the input and output are - # in the directory it is running. So first, we need to switch to - # the input directory, run it, then put our desired output where we - # want and delete the extra files. +# Unfortunately XLSX I/O only works when the input and output are in +# the directory it is running. So first, we need to switch to the +# input directory, run it, then put our desired output where we want +# and delete the extra files. topdir=$$(pwd) cd $(indir) xlsxio_xlsx2csv $(notdir $<) @@ -42,12 +42,12 @@ $(mk20tab3): $(indir)/menke20.xlsx | $(a1dir) rm $(notdir $<).*.csv cd $$topdir - # Read the necessary information. Note that we are dealing with a - # CSV (comma-separated value) file. But when there are commas in a - # string, quotation signs are put around it. The `FPAT' values is - # fully described in the GNU AWK manual. In short, it ensures that - # if there is a comma in the middle of double-quotes, it doesn't - # count as a delimter. +# Read the necessary information. Note that we are dealing with a CSV +# (comma-separated value) file. But when there are commas in a +# string, quotation signs are put around it. The `FPAT' values is +# fully described in the GNU AWK manual. In short, it ensures that if +# there is a comma in the middle of double-quotes, it doesn't count +# as a delimter. echo "# Column 1: YEAR [counter, i16] Year of journal's publication." > $@.tmp echo "# Column 2: NUM_PAPERS [counter, i16] Number of studied papers in that journal." >> $@.tmp echo "# Column 3: NUM_PAPERS_WITH_TOOLS [counter, i16] Number of papers with an identified tool." >> $@.tmp @@ -56,9 +56,9 @@ $(mk20tab3): $(indir)/menke20.xlsx | $(a1dir) awk 'NR>1{printf("%-10d%-10d%-10d%-10d %s\n", $$2, $$3, $$3*$$NF, $$(NF-1), $$1)}' \ FPAT='([^,]+)|("[^"]+")' $(indir)/$$base.csv >> $@.tmp - # Set the temporary file as the final target. This was done so if - # there is any possible crash in the steps above, this rule is - # re-run (its final target isn't rebuilt). +# Set the temporary file as the final target. This was done so if +# there is any possible crash in the steps above, this rule is re-run +# (its final target isn't rebuilt). mv $@.tmp $@ @@ -68,19 +68,19 @@ $(mk20tab3): $(indir)/menke20.xlsx | $(a1dir) # Main LaTeX macro file $(mtexdir)/format.tex: $(mk20tab3) - # Count the total number of papers in their study. +# Count the total number of papers in their study. v=$$(awk '!/^#/{c+=$$2} END{print c}' $(mk20tab3)) echo "\newcommand{\menkenumpapers}{$$v}" > $@ - # Count how many unique journals there were in the study. Note that - # the `31' comes because we put 10 characters for each numeric - # column and separated the last numeric column from the string - # column with a space. If the number of numeric columns change in - # the future, the `31' also has to change. +# Count how many unique journals there were in the study. Note that +# the `31' comes because we put 10 characters for each numeric column +# and separated the last numeric column from the string column with a +# space. If the number of numeric columns change in the future, the +# `31' also has to change. v=$$(awk 'BEGIN{FIELDWIDTHS="41 10000"} !/^#/{print $$2}' \ $(mk20tab3) | uniq | wc -l) echo "\newcommand{\menkenumjournals}{$$v}" >> $@ - # Count how many rows the original catalog has. +# Count how many rows the original catalog has. v=$$(awk '!/^#/{c++} END{print c}' $(mk20tab3)) echo "\newcommand{\menkenumorigrows}{$$v}" >> $@ |