ENH: Allow to customize what can be before / inside / after +project and @context (#271)

* ENH: Allow to customize what can be before / inside / after +project and @context

I noticed that todo.sh mistakenly picks up some random stuff as projects and contexts. The todo.txt specification is very lenient in what makes those (allowing any length of non-whitespace characters), but in practice, every user has its own idea of the set of used words. This change allows (expert) users to tweak the pattern (via TODOTXT_SIGIL_VALID_PATTERN), to be able to reduce the amount of "false positives" that listproj and listcon show.
Additionally, there's a (mainly unspecified) extension mechanism in the form of key:value, which often is used to implement custom "markers", like w:something to make a task blocked and waiting for "something". It would be nice to be able to refer to @contexts (and maybe also +projects), but the default syntax (which requires whitespace around those) doesn't allow it, and these context then don't show up in searches, which is unfortunate. The added TODOTXT_SIGIL_BEFORE_PATTERN and TODOTXT_SIGIL_AFTER_PATTERN allow to tweak the syntax to accommodate this.
The implementation just exchanges grep with a corresponding sed pipeline step, which shouldn't negatively affect the performance at all (as sed is one of the main commands used thoughout the script), but which allows for the additional matching flexibility.

* FIX: Compatibility: sed \? multi not supported on MacOS

Use the POSIX \{0,1\} instead.

* FIX: Compatibility: sed \| multi not supported on MacOS

Concatenate both alternatives as optional matches; this is only an approximation but satisfies the test case here. It would probably be better if the entire sed code used extended regular expression syntax (-E) instead of basic ones (-e), but that change would also affect all add-ons. As this is an optional customization feature, uses who really need this either also have to work around, or supply a GNU sed port on MacOS.

* FIX: Compatibility: sed \+ multi not supported on MacOS

Use the POSIX \{1,\} instead.

Co-authored-by: Ali Karbassi <ali@karbassi.com>

tests/t1310-listcon.sh

@@ -65,6 +65,47 @@ test_todo_session 'listcon with project' <<EOF
 @garden
 EOF
 
+cat > todo.txt <<EOF
+(B) +math (@school or @home) integrate @x and @y
+(C) say thanks @GinaTrapani w:@OtherContributors
+stop
+EOF
+test_todo_session 'listcon with default configuration' <<EOF
+>>> todo.sh listcon
+@GinaTrapani
+@home)
+@x
+@y
+EOF
+test_todo_session 'listcon limiting to multi-character sequences' <<EOF
+>>> TODOTXT_SIGIL_VALID_PATTERN='.\{2,\}' todo.sh listcon
+@GinaTrapani
+@home)
+EOF
+test_todo_session 'listcon allowing w: marker before contexts' <<EOF
+>>> TODOTXT_SIGIL_BEFORE_PATTERN='\(w:\)\{0,1\}' todo.sh listcon
+@GinaTrapani
+@OtherContributors
+@home)
+@x
+@y
+EOF
+test_todo_session 'listcon allowing parentheses around contexts' <<EOF
+>>> TODOTXT_SIGIL_BEFORE_PATTERN='(\{0,1\}' TODOTXT_SIGIL_AFTER_PATTERN=')\{0,1\}' todo.sh listcon
+@GinaTrapani
+@home
+@school
+@x
+@y
+EOF
+test_todo_session 'listcon with all customizations combined' <<EOF
+>>> TODOTXT_SIGIL_VALID_PATTERN='.\{2,\}' TODOTXT_SIGIL_BEFORE_PATTERN='\(w:\)\{0,1\}\((\)\{0,1\}' TODOTXT_SIGIL_AFTER_PATTERN=')\{0,1\}' todo.sh listcon
+@GinaTrapani
+@OtherContributors
+@home
+@school
+EOF
+
 cat > todo.txt <<EOF
 @con01 -- Some context 1 task
 EOF

tests/t1320-listproj.sh

@@ -75,6 +75,33 @@ test_todo_session 'listproj with context' <<EOF
 +sunflowers
 EOF
 
+cat > todo.txt <<EOF
+(B) give a +1 to this project
+(C) notice the sunflowers +sunflowers [+gardening] [+landscape]
+stop
+EOF
+test_todo_session 'listproj with default configuration' <<EOF
+>>> todo.sh listproj
++1
++sunflowers
+EOF
+test_todo_session 'listproj limiting to alphabetic characters' <<EOF
+>>> TODOTXT_SIGIL_VALID_PATTERN='[a-zA-Z]\{1,\}' todo.sh listproj
++sunflowers
+EOF
+test_todo_session 'listproj allowing brackets around projects' <<EOF
+>>> TODOTXT_SIGIL_BEFORE_PATTERN='\[\{0,1\}' TODOTXT_SIGIL_AFTER_PATTERN='\]\{0,1\}' todo.sh listproj
++1
++gardening
++landscape
++sunflowers
+EOF
+
+cat > todo.txt <<EOF
+(B) smell the uppercase Roses +roses @outside +shared
+(C) notice the sunflowers +sunflowers @garden +shared +landscape
+stop
+EOF
 TEST_TODO_CUSTOM=todo-custom.cfg
 cat todo.cfg > "$TEST_TODO_CUSTOM"
 cat >> "$TEST_TODO_CUSTOM" <<'EOF'

todo.sh

@@ -149,6 +149,9 @@ help()
 		    TODOTXT_SORT_COMMAND="sort ..." customize list output
 		    TODOTXT_FINAL_FILTER="sed ..."  customize list after color, P@+ hiding
 		    TODOTXT_SOURCEVAR=\$DONE_FILE   use another source for listcon, listproj
+		    TODOTXT_SIGIL_BEFORE_PATTERN="" optionally allow chars preceding +p / @c
+		    TODOTXT_SIGIL_VALID_PATTERN=.*  tweak the allowed chars for +p and @c
+		    TODOTXT_SIGIL_AFTER_PATTERN=""  optionally allow chars after +p / @c
 
 
 	EndVerboseHelp
@@ -620,6 +623,9 @@ TODOTXT_SORT_COMMAND=${TODOTXT_SORT_COMMAND:-env LC_COLLATE=C sort -f -k2}
 TODOTXT_DISABLE_FILTER=${TODOTXT_DISABLE_FILTER:-}
 TODOTXT_FINAL_FILTER=${TODOTXT_FINAL_FILTER:-cat}
 TODOTXT_GLOBAL_CFG_FILE=${TODOTXT_GLOBAL_CFG_FILE:-/etc/todo/config}
+TODOTXT_SIGIL_BEFORE_PATTERN=${TODOTXT_SIGIL_BEFORE_PATTERN:-}	# Allow any other non-whitespace entity before +project and @context; should be an optional match; example: \(w:\)\{0,1\} to allow w:@context.
+TODOTXT_SIGIL_VALID_PATTERN=${TODOTXT_SIGIL_VALID_PATTERN:-.*}	# Limit the valid characters (from the default any non-whitespace sequence) for +project and @context; example: [a-zA-Z]\{3,\} to only allow alphabetic ones that are at least three characters long.
+TODOTXT_SIGIL_AFTER_PATTERN=${TODOTXT_SIGIL_AFTER_PATTERN:-}	# Allow any other non-whitespace entity after +project and @context; should be an optional match; example: )\{0,1\} to allow (with the corresponding TODOTXT_SIGIL_BEFORE_PATTERN) enclosing in parentheses.
 
 # Export all TODOTXT_* variables
 export "${!TODOTXT_@}"
@@ -1037,7 +1043,13 @@ listWordsWithSigil()
 
     FILE=$TODO_FILE
     [ "$TODOTXT_SOURCEVAR" ] && eval "FILE=$TODOTXT_SOURCEVAR"
-    eval "$(filtercommand 'cat "${FILE[@]}"' '' "$@")" | grep -o "[^ ]*${sigil}[^ ]\\+" | grep "^$sigil" | sort -u
+	eval "$(filtercommand 'cat "${FILE[@]}"' '' "$@")" \
+		| grep -o "[^ ]*${sigil}[^ ]\\+" \
+		| sed -n \
+			-e "s#^${TODOTXT_SIGIL_BEFORE_PATTERN//#/\\#}##" \
+			-e "s#${TODOTXT_SIGIL_AFTER_PATTERN//#/\\#}\$##" \
+			-e "/^${sigil}${TODOTXT_SIGIL_VALID_PATTERN//\//\\/}$/p" \
+		| sort -u
 }
 
 export -f cleaninput getPrefix getTodo getNewtodo shellquote filtercommand _list listWordsWithSigil getPadding _format die