Stats

NOTES_DIR="{vocabulary.notes}"

# Note count (excluding MOCs)
TOTAL_FILES=$(ls -1 "$NOTES_DIR"/*.md 2>/dev/null | wc -l | tr -d ' ')
MOC_COUNT=$(grep -rl '^type: moc' "$NOTES_DIR"/*.md 2>/dev/null | wc -l | tr -d ' ')
NOTE_COUNT=$((TOTAL_FILES - MOC_COUNT))

# Connection count (all wiki links across notes/)
LINK_COUNT=$(grep -ohP '\[\[[^\]]+\]\]' "$NOTES_DIR"/*.md 2>/dev/null | wc -l | tr -d ' ')

# Average connections per note
if [[ "$NOTE_COUNT" -gt 0 ]]; then
  AVG_LINKS=$(echo "scale=1; $LINK_COUNT / $NOTE_COUNT" | bc)
else
  AVG_LINKS="0"
fi

# Topic count (unique values in topics: fields)
TOPIC_COUNT=$(grep -ohP '^\s*-\s*"\[\[([^\]]+)\]\]"' "$NOTES_DIR"/*.md 2>/dev/null | sort -u | wc -l | tr -d ' ')

# Link density
if [[ "$NOTE_COUNT" -gt 1 ]]; then
  POSSIBLE=$((NOTE_COUNT * (NOTE_COUNT - 1)))
  DENSITY=$(echo "scale=4; $LINK_COUNT / $POSSIBLE" | bc)
else
  DENSITY="N/A"
fi

# Orphan count (notes with zero incoming links)
ORPHAN_COUNT=0
for f in "$NOTES_DIR"/*.md; do
  NAME=$(basename "$f" .md)
  grep -q '^type: moc' "$f" 2>/dev/null && continue
  INCOMING=$(grep -rl "\[\[$NAME\]\]" "$NOTES_DIR"/ 2>/dev/null | grep -v "$f" | wc -l | tr -d ' ')
  [[ "$INCOMING" -eq 0 ]] && ORPHAN_COUNT=$((ORPHAN_COUNT + 1))
done

# Dangling link count
DANGLING_COUNT=$(grep -ohP '\[\[([^\]]+)\]\]' "$NOTES_DIR"/*.md 2>/dev/null | sort -u | while read -r link; do
  NAME=$(echo "$link" | sed 's/\[\[//;s/\]\]//')
  [[ ! -f "$NOTES_DIR/$NAME.md" ]] && echo "$NAME"
done | wc -l | tr -d ' ')

# Schema compliance (% of notes with required fields: description, topics)
MISSING_DESC=$(grep -rL '^description:' "$NOTES_DIR"/*.md 2>/dev/null | wc -l | tr -d ' ')
MISSING_TOPICS=$(grep -rL '^topics:' "$NOTES_DIR"/*.md 2>/dev/null | wc -l | tr -d ' ')
SCHEMA_ISSUES=$((MISSING_DESC + MISSING_TOPICS))
if [[ "$TOTAL_FILES" -gt 0 ]]; then
  # Notes with BOTH required fields
  COMPLIANT=$((TOTAL_FILES - MISSING_DESC))
  COMPLIANCE=$(echo "scale=0; $COMPLIANT * 100 / $TOTAL_FILES" | bc)
else
  COMPLIANCE="N/A"
fi

# MOC coverage
COVERED=0
for f in "$NOTES_DIR"/*.md; do
  NAME=$(basename "$f" .md)
  grep -q '^type: moc' "$f" 2>/dev/null && continue
  if grep -rl '^type: moc' "$NOTES_DIR"/*.md 2>/dev/null | xargs grep -l "\[\[$NAME\]\]" >/dev/null 2>&1; then
    COVERED=$((COVERED + 1))
  fi
done
if [[ "$NOTE_COUNT" -gt 0 ]]; then
  COVERAGE=$(echo "scale=0; $COVERED * 100 / $NOTE_COUNT" | bc)
else
  COVERAGE="N/A"
fi

# Inbox items
INBOX_COUNT=$(find {vocabulary.inbox}/ -name "*.md" 2>/dev/null | wc -l | tr -d ' ')

# Queue pending (check both YAML and JSON formats)
QUEUE_FILE=""
if [[ -f "ops/queue/queue.yaml" ]]; then
  QUEUE_FILE="ops/queue/queue.yaml"
  QUEUE_PENDING=$(grep -c 'status: pending' "$QUEUE_FILE" 2>/dev/null || echo 0)
  QUEUE_DONE=$(grep -c 'status: done' "$QUEUE_FILE" 2>/dev/null || echo 0)
elif [[ -f "ops/queue/queue.json" ]]; then
  QUEUE_FILE="ops/queue/queue.json"
  QUEUE_PENDING=$(grep -c '"status": "pending"' "$QUEUE_FILE" 2>/dev/null || echo 0)
  QUEUE_DONE=$(grep -c '"status": "done"' "$QUEUE_FILE" 2>/dev/null || echo 0)
else
  QUEUE_PENDING=0
  QUEUE_DONE=0
fi

# Processed ratio (notes vs inbox)
TOTAL_CONTENT=$((NOTE_COUNT + INBOX_COUNT))
if [[ "$TOTAL_CONTENT" -gt 0 ]]; then
  PROCESSED_PCT=$(echo "scale=0; $NOTE_COUNT * 100 / $TOTAL_CONTENT" | bc)
else
  PROCESSED_PCT="N/A"
fi

# This week's growth (notes with created: date within last 7 days)
WEEK_AGO=$(date -v-7d +%Y-%m-%d 2>/dev/null || date -d '7 days ago' +%Y-%m-%d 2>/dev/null)
if [[ -n "$WEEK_AGO" ]]; then
  THIS_WEEK_NOTES=$(grep -rl "^created: " "$NOTES_DIR"/*.md 2>/dev/null | while read -r f; do
    CREATED=$(grep '^created:' "$f" | head -1 | awk '{print $2}')
    [[ "$CREATED" > "$WEEK_AGO" || "$CREATED" == "$WEEK_AGO" ]] && echo "$f"
  done | wc -l | tr -d ' ')
else
  THIS_WEEK_NOTES="?"
fi

# This week's connections (approximate — count links in recently created notes)
if [[ "$THIS_WEEK_NOTES" -gt 0 && -n "$WEEK_AGO" ]]; then
  THIS_WEEK_LINKS=$(grep -rl "^created: " "$NOTES_DIR"/*.md 2>/dev/null | while read -r f; do
    CREATED=$(grep '^created:' "$f" | head -1 | awk '{print $2}')
    [[ "$CREATED" > "$WEEK_AGO" || "$CREATED" == "$WEEK_AGO" ]] && grep -oP '\[\[[^\]]+\]\]' "$f" 2>/dev/null
  done | wc -l | tr -d ' ')
else
  THIS_WEEK_LINKS="?"
fi

# Self space
if [[ -d "self/" ]]; then
  SELF_FILES=$(find self/ -name "*.md" 2>/dev/null | wc -l | tr -d ' ')
  SELF_STATUS="enabled ($SELF_FILES files)"
else
  SELF_STATUS="disabled"
fi

# Methodology notes
METHODOLOGY_COUNT=$(ls -1 ops/methodology/*.md 2>/dev/null | wc -l | tr -d ' ')

# Observations pending
OBS_PENDING=$(grep -rl '^status: pending' ops/observations/ 2>/dev/null | wc -l | tr -d ' ')

# Tensions pending
TENSION_PENDING=$(grep -rl '^status: open\|^status: pending' ops/tensions/ 2>/dev/null | wc -l | tr -d ' ')

# Sessions captured
SESSION_COUNT=$(ls -1 ops/sessions/*.md 2>/dev/null | wc -l | tr -d ' ')

Progress bar calculation:
  filled = PROCESSED_PCT / 5 (number of = characters out of 20)
  empty = 20 - filled
  bar = [===...   ] PCT%

--=={ stats }==--

  Knowledge Graph
  ===============
  {vocabulary.note_plural}:  [NOTE_COUNT]
  Connections:               [LINK_COUNT] (avg [AVG_LINKS] per {vocabulary.note})
  {vocabulary.topic_map_plural}:   [MOC_COUNT] (covering [COVERAGE]% of {vocabulary.note_plural})
  Topics:                    [TOPIC_COUNT]

  Health
  ======
  Orphans:      [ORPHAN_COUNT]
  Dangling:     [DANGLING_COUNT]
  Schema:       [COMPLIANCE]% compliant

  Pipeline
  ========
  Processed:    [==============      ] [PROCESSED_PCT]%
  Inbox:        [INBOX_COUNT] items
  Queue:        [QUEUE_PENDING] pending tasks

  Growth
  ======
  This week:    +[THIS_WEEK_NOTES] {vocabulary.note_plural}, +[THIS_WEEK_LINKS] connections
  Graph density: [DENSITY]

  System
  ======
  Self space:      [SELF_STATUS]
  Methodology:     [METHODOLOGY_COUNT] learned patterns
  Observations:    [OBS_PENDING] pending
  Tensions:        [TENSION_PENDING] open
  Sessions:        [SESSION_COUNT] captured

  Generated by Ars Contexta v1.6