X-Git-Url: https://feistymeow.org/gitweb/?a=blobdiff_plain;f=scripts%2Fnotes%2Finfo_overload_report.sh;h=3809113815856a698ff6ea55441d83543c6907b2;hb=244e0eeaf916718d7bcd7beba44f9c0de29c504d;hp=6ba059749ad2b97ea94baaa661c9dc32a19c99eb;hpb=4e8a35eb97d5595f7c6d8122e50211c66b32cff8;p=feisty_meow.git

diff --git a/scripts/notes/info_overload_report.sh b/scripts/notes/info_overload_report.sh
index 6ba05974..38091138 100644
--- a/scripts/notes/info_overload_report.sh
+++ b/scripts/notes/info_overload_report.sh
@@ -1,56 +1,147 @@
 
 # these metrics are how bogged down we are in to-do type items.
 
-REPORT_FILE="$HOME/quartz/history_info_overload.txt"
+REPORT_FILE="$HOME/cloud/fred_stats/overload_history.txt"
 
-# given a path, this will find how many items are under it, ignoring svn and git files.
-function calculate_depth()
+# given a path, this will find how many items are under it, ignoring svn and git files, plus
+# other patterns we happen to notice are not useful.
+function calculate_count()
 {
   local dir="$1"; shift
-  find "$dir" -type f -exec echo \"{}\" ';' | grep -v "\.svn" | grep -v "\.git" | wc -l | tr -d ' '
+  local count=$(find "$dir" -type f -exec echo \"{}\" ';' 2>/dev/null |  grep -v "\.svn" | grep -v "\.git"| grep -v "\.basket" | grep -v "\.version" | grep -v "\.keep" | wc -l | tr -d ' ')
+  if [ -z "$count" ]; then echo 0; else echo "$count"; fi
+}
+
+# calculates the size in kilobytes of all the note files in a hierarchy.
+# this is just a raw statistic for how much content all those notes make up.  since
+# we have not separated out all the to-dos in some files (most notably the metaverse
+# backlogs and to-do lists), it's good to also know what kind of girth the notes have.
+function calculate_weight()
+{
+  local dir="$1"; shift
+  local weight=$(find "$dir" -type f -exec echo \"{}\" ';' 2>/dev/null | grep -v "\.svn" | grep -v "\.git"| grep -v "\.basket" | grep -v "\.version" | grep -v "\.keep" | xargs ls -al | awk '{ print $5 }' | paste -sd+ | bc 2>/dev/null)
+  if [ -z "$weight" ]; then echo 0; else echo "$weight"; fi
+}
+
+# calculate_complexity gets a very simple metric of how many directory components are
+# present at the target location and below.
+function calculate_complexity()
+{
+  local dir="$1"; shift
+  local complexity=$(find "$dir" -type d | wc -l)
+  if [ -z "$complexity" ]; then echo 0; else echo "$complexity"; fi
+}
+
+# produces a report line in our format.
+function format_report_line()
+{
+  local count="$1"; shift
+  local weight="$1"; shift
+  weight=$((weight / 1024))
+  local complexity="$1"; shift
+  echo "$count\t${complexity}\t\t${weight}\t\t$*\n"
+}
+
+# two parameters are needed: the directory to sum up and the label to use for it in the report.
+# this will calculate the count and weight for a hierarchy of notes, and then produce a
+# line of reporting for those.
+function analyze_hierarchy_and_report()
+{
+  local dir="$1"; shift
+  local label="$1"; shift
+  local count=$(calculate_count "$dir")
+  total_overload=$(($count + $total_overload))
+  local weight=$(calculate_weight "$dir")
+  total_weight=$(($total_weight + $weight))
+  local complexity=$(calculate_complexity "$dir")
+  total_complexity=$(($total_complexity + $complexity))
+  full_report+=$(format_report_line "$count" "$weight" "$complexity" "$label")
+}
+
+# scans through items in the notes folder that begin with a pattern.
+# each of those is treated as an aggregable portion of the report.
+# first parameter is the title in the report, second and so on are
+# a list of directory patterns to scan and aggregate.
+function analyze_by_dir_patterns()
+{
+  local title="$1"; shift
+  local hier_count=0
+  local hier_weight=0
+  local hier_complexity=0
+  for folder in $@; do
+    temp_count=$(calculate_count $folder)
+    hier_count=$(($hier_count + $temp_count))
+    temp_weight=$(calculate_weight $folder)
+    hier_weight=$(($hier_weight + $temp_weight))
+    temp_complexity=$(calculate_complexity $folder)
+    hier_complexity=$(($hier_complexity + $temp_complexity))
+  done
+  total_overload=$(($hier_count + $total_overload))
+  total_weight=$(($total_weight + $hier_weight))
+  total_complexity=$(($total_complexity + $hier_complexity))
+  full_report+=$(format_report_line "$hier_count" "$hier_weight" "$hier_complexity" "$title")
 }
 
 ##############
 
+# reset these before we add anything...
+total_overload=0
+total_weight=0
+
+# start out the report with a header.
+full_report="\
+\n\
+current information overload consists of:\n\
+\n\
+"
+full_report+="count\tcomplexity\tweight (kb)\tcategory\n\
+================================================================\n\
+"
+
+analyze_hierarchy_and_report ~/cloud/urgent "high priority"
+
 # notes are individual files of tasks, usually, although some are combined.
-note_depth=$(calculate_depth ~/cloud/grunty_notes)
+analyze_hierarchy_and_report ~/cloud/grunty_notes "grunty notes (external facing things?)"
+
+# feisty notes are about feisty meow(r) concerns ltd codebase development.
+analyze_hierarchy_and_report ~/cloud/feisty_notes "feisty meow notes (code related)"
 
+# home notes are a new top-level category; used to be under the grunty.
+analyze_hierarchy_and_report ~/cloud/branch_road "hearth and home notes (branch road, yo!)"
+
+# games and fun stuff.  not sure why these count as backlog, but whatever.
+analyze_hierarchy_and_report ~/cloud/games_yo "games, yo!"
+
+# some source code that needs to be sucked into other places, other codebases.  they are not
+# supposed to pile up here.  but they have, so we track them.
+analyze_hierarchy_and_report ~/cloud/scavenging_source "source scavenging"
+
+# and then count up the things that we think will be cleaned soon, but one thing we have learned
 # unsorted files haven't been categorized yet.
-unsorted_depth=$(calculate_depth ~/cloud/unsorted)
+analyze_hierarchy_and_report ~/cloud/disordered "unsorted files"
 
-# source examples need to be sucked into other places, other codebases.  they are not
-# supposed to pile up here.
-source_example_depth=$(calculate_depth ~/cloud/example_source)
+# we now consider the backlog of things to read to be a relevant fact.  this is going to hose
+# up our weight accounting considerably.
+analyze_hierarchy_and_report ~/cloud/reading "reading list"
 
-# the list files are web documents with to-do lists.  individual items are marked with <li>.
-item_depth=$(find ~/cloud/grunty_notes/ -type f -iname "*.html" -exec grep "<li" "{}" ';' | wc -l | tr -d ' ')
+# scan all the items declared as active projects.
+analyze_by_dir_patterns "active items" ~/cloud/active*
 
-# scan across all appropriately named folders in our folders that live in the "cloud".
-cloud_depth=0
-for i in ~/cloud/*project* ~/cloud/*research*; do
-  temp_depth=$(calculate_depth $i)
-  cloud_depth=$(($cloud_depth + $temp_depth))
-done
+# scan across all appropriately named project or research folders that live in the "cloud".
+analyze_by_dir_patterns "project files" ~/cloud/project* ~/cloud/research*
 
-##############
+# snag any work related items for that category.
+analyze_by_dir_patterns "job and work tasks" ~/cloud/job* 
 
-total_overload=$(($note_depth + $item_depth + $unsorted_depth + $source_example_depth + $cloud_depth))
+# scan all the trivial project folders.
+analyze_by_dir_patterns "trivial items" ~/cloud/trivia*
 
-report="\
-\n\
-Current information overload consists of:\n\
-\n\
-  $note_depth\tnote files\n\
-  $item_depth\tto-do list items\n\
-  $unsorted_depth\tunsorted files\n\
-  $source_example_depth\tsource examples\n\
-  $cloud_depth\tcloud notes\n\
-  -------\n\
-  $total_overload\ttotal items\n\
-\n\
-Gathered On: $(date)\n\
-\n\
+full_report+="================================================================\n\
+"
+full_report+="$(format_report_line "$total_overload" "$total_weight" "$total_complexity" "total overload")"
+full_report+="\n\
+[gathered on $(date)]\n\n\
 ##############"
 
-echo -e "$report" | tee -a "$REPORT_FILE"
+echo -e "$full_report" | tee -a "$REPORT_FILE"