diff --git a/doc.zih.tu-dresden.de/util/grep-forbidden-words.sh b/doc.zih.tu-dresden.de/util/grep-forbidden-patterns.sh
similarity index 57%
rename from doc.zih.tu-dresden.de/util/grep-forbidden-words.sh
rename to doc.zih.tu-dresden.de/util/grep-forbidden-patterns.sh
index cfb2b91b57457b701c5b80e76c6346d460cf4602..7d7b90cec5b88f1fb7468c2ca99e1dda48a17549 100755
--- a/doc.zih.tu-dresden.de/util/grep-forbidden-words.sh
+++ b/doc.zih.tu-dresden.de/util/grep-forbidden-patterns.sh
@@ -12,17 +12,29 @@ basedir=`dirname "$basedir"`
#Further fields represent patterns with exceptions.
#For example, the first rule says:
# The pattern \<io\> should not be present in any file (case-insensitive match), except when it appears as ".io".
-ruleset="i \<io\> \.io
+ruleset="The word \"IO\" should not be used, use \"I/O\" instead.
+i \<io\> \.io
+\"SLURM\" (only capital letters) should not be used, use \"Slurm\" instead.
s \<SLURM\>
+\"File system\" should be written as filesystem, except when used as part of a proper name.
i file \+system HDFS
-i \<taurus\> taurus\.hrsk /taurus /TAURUS
+Use \"ZIH systems\" or \"ZIH system\" instead of \"Taurus\". \"taurus\" is only allowed when used in ssh commands and other very specific situations.
+i \<taurus\> taurus\.hrsk /taurus /TAURUS ssh
+\"HRSKII\" should be avoided, use \"ZIH system\" instead.
i \<hrskii\>
+The term \"HPC-DA\" should be avoided. Depending on the situation, use \"data analytics\" or similar.
i hpc[ -]\+da\>
+\"ATTACHURL\" was a keyword in the old wiki, don't use it.
i attachurl
+Replace \"todo\" with real content.
i \<todo\> <!--.*todo.*-->
+Avoid spaces at end of lines.
i [[:space:]]$
+When referencing partitions, put keyword \"partition\" in front of partition name, e. g. \"partition ml\", not \"ml partition\".
i \(alpha\|ml\|haswell\|romeo\|gpu\|smp\|julia\|hpdlf\|scs5\)-\?\(interactive\)\?[^a-z]*partition
+Give hints in the link text. Words such as \"here\" or \"this link\" are meaningless.
i \[\s\?\(documentation\|here\|this \(link\|page\|subsection\)\|slides\?\|manpage\)\s\?\]
+Use \"workspace\" instead of \"work space\".
i work[ -]\+space"
# Whitelisted files will be ignored
@@ -39,6 +51,32 @@ function grepExceptions () {
fi
}
+function checkFile(){
+ f=$1
+ echo "Check wording in file $f"
+ while read message; do
+ IFS=$'\t' read -r flags pattern exceptionPatterns
+ while IFS=$'\t' read -r -a exceptionPatternsArray; do
+ if [ $silent = false ]; then
+ echo " Pattern: $pattern"
+ fi
+ grepflag=
+ case "$flags" in
+ "i")
+ grepflag=-i
+ ;;
+ esac
+ if grep -n $grepflag $color "$pattern" "$f" | grepExceptions "${exceptionPatternsArray[@]}" ; then
+ number_of_matches=`grep -n $grepflag $color "$pattern" "$f" | grepExceptions "${exceptionPatternsArray[@]}" | wc -l`
+ ((cnt=cnt+$number_of_matches))
+ if [ $silent = false ]; then
+ echo " $message"
+ fi
+ fi
+ done <<< $exceptionPatterns
+ done <<< $ruleset
+}
+
function usage () {
echo "$0 [options]"
echo "Search forbidden patterns in markdown files."
@@ -95,31 +133,19 @@ fi
echo "... $files ..."
cnt=0
-for f in $files; do
- if [ "${f: -3}" == ".md" -a -f "$f" ]; then
- if (printf '%s\n' "${whitelist[@]}" | grep -xq $f); then
- echo "Skip whitelisted file $f"
- continue
+if [[ ! -z $file ]]; then
+ checkFile $file
+else
+ for f in $files; do
+ if [ "${f: -3}" == ".md" -a -f "$f" ]; then
+ if (printf '%s\n' "${whitelist[@]}" | grep -xq $f); then
+ echo "Skip whitelisted file $f"
+ continue
+ fi
+ checkFile $f
fi
- echo "Check wording in file $f"
- while IFS=$'\t' read -r flags pattern exceptionPatterns; do
- while IFS=$'\t' read -r -a exceptionPatternsArray; do
- if [ $silent = false ]; then
- echo " Pattern: $pattern"
- fi
- grepflag=
- case "$flags" in
- "i")
- grepflag=-i
- ;;
- esac
- if grep -n $grepflag $color "$pattern" "$f" | grepExceptions "${exceptionPatternsArray[@]}" ; then
- ((cnt=cnt+1))
- fi
- done <<< $exceptionPatterns
- done <<< $ruleset
- fi
-done
+ done
+fi
echo ""
case $cnt in
diff --git a/doc.zih.tu-dresden.de/util/grep-forbidden-patterns.testdoc b/doc.zih.tu-dresden.de/util/grep-forbidden-patterns.testdoc
new file mode 100644
index 0000000000000000000000000000000000000000..2b674702cd81304662b439a61d2fe15246ef8215
--- /dev/null
+++ b/doc.zih.tu-dresden.de/util/grep-forbidden-patterns.testdoc
@@ -0,0 +1,46 @@
+# Diese Datei versucht alles falsch zu machen, worauf grep-forbidden-words.sh checkt.
+
+`i \[\s\?\(documentation\|here\|this \(link\|page\|subsection\)\|slides\?\|manpage\)\s\?\]`
+
+Man kann Workspace schreiben oder aber auch
+work-Space, beides sollte auffallen.
+
+Die ML-Partition,
+die Alpha-Partition,
+die Haswell-Partition,
+die Romeo-Partition,
+die GPU-Partition,
+die SMP-Partition,
+die Julia-Partition,
+die HPDLF-Partition,
+die scs5-Partition (was ist das überhaupt?),
+alle gibt es auch in interaktiv:
+Die ML-interactive partition,
+die Alpha-interactive partition,
+die Haswell-interactive Partition,
+die Romeo-interactive partition,
+die GPU-interactive partition,
+die SMP-interactive partition,
+die Julia-interactive partition,
+die HPDLF-interactive partition,
+die scs5-interactive partition (was ist das überhaupt?),
+alle diese Partitionen existieren, aber man darf sie nicht benennen.
+```
+Denn sonst kommt das Leerzeichenmonster und packt Leerzeichen ans Ende der Zeile.
+```
+
+TODO: io sollte mit SLURM laufen.
+
+Das HDFS ist ein sehr gutes
+file system auf taurus.
+
+Taurus ist erreichbar per
+taurus.hrsk oder per
+/taurus oder per
+/TAURUS
+
+Was ist hrskii? Keine Ahnung!
+
+Was ist HPC-DA? Ist es ein attachurl? See (this page).
+Or (here).
+Or (manpage).
diff --git a/doc.zih.tu-dresden.de/util/pre-commit b/doc.zih.tu-dresden.de/util/pre-commit
index b86b75d9a07870a68118aa500ee80781e216c56b..eb63bbea24052eb1dff4ec16a17b8b5aba275e18 100755
--- a/doc.zih.tu-dresden.de/util/pre-commit
+++ b/doc.zih.tu-dresden.de/util/pre-commit
@@ -69,7 +69,7 @@ then
fi
echo "Forbidden words checking..."
-docker run --name=hpc-compendium --rm -w /docs --mount src="$(pwd)",target=/docs,type=bind hpc-compendium ./doc.zih.tu-dresden.de/util/grep-forbidden-words.sh
+docker run --name=hpc-compendium --rm -w /docs --mount src="$(pwd)",target=/docs,type=bind hpc-compendium ./doc.zih.tu-dresden.de/util/grep-forbidden-patterns.sh
if [ $? -ne 0 ]
then
exit_ok=no
diff --git a/doc.zih.tu-dresden.de/util/test-grep-forbidden-patterns.sh b/doc.zih.tu-dresden.de/util/test-grep-forbidden-patterns.sh
new file mode 100755
index 0000000000000000000000000000000000000000..d5d13ffc4ffc2f1f63332ca628f1449525ee1690
--- /dev/null
+++ b/doc.zih.tu-dresden.de/util/test-grep-forbidden-patterns.sh
@@ -0,0 +1,13 @@
+#!/bin/bash
+
+expected_match_count=32
+
+number_of_matches=$(bash ./doc.zih.tu-dresden.de/util/grep-forbidden-words.sh -f doc.zih.tu-dresden.de/util/grep-forbidden-patterns.testdoc -c -c | grep "Forbidden Patterns:" | sed -e 's/.*: //' | sed -e 's/ matches.*//')
+
+if [ $number_of_matches -eq $expected_match_count ]; then
+ echo "Test OK"
+ exit 0
+else
+ echo "Test failed: $expected_match_count matches expected, but only $number_of_matches found"
+ exit 1
+fi