benbrastmckie/nvim/skill-literature

# Parse from skill args: "mode={mode} file={file}" or "mode=search query={query text}"
mode=$(echo "$ARGUMENTS" | grep -oP 'mode=\K\S+' | head -1)
file=$(echo "$ARGUMENTS" | grep -oP 'file=\K\S+' | head -1)
 
# Extract query: everything after "query=" (supports spaces in query text)
query=$(echo "$ARGUMENTS" | sed 's/.*query=//' | sed 's/^[[:space:]]*//')
 
# Default to status mode if not specified
if [ -z "$mode" ]; then
  mode="status"
fi
 
# Resolve file path (may be relative or absolute)
if [ -n "$file" ]; then
  if [[ "$file" != /* ]]; then
    file="specs/literature/$file"
  fi
fi

source .claude/scripts/lib/common.sh
session_id="$(common_session_id)"
# Two-tier fallback: use LITERATURE_DIR if set and exists, otherwise use per-project specs/literature/
if [ -n "${LITERATURE_DIR:-}" ] && [ -d "$LITERATURE_DIR" ]; then
  lit_dir="$LITERATURE_DIR"
else
  lit_dir="specs/literature"
fi
index_file="$lit_dir/index.json"
# Determine sources/ prefix for centralized repo
if [ -n "${LITERATURE_DIR:-}" ] && [ "$lit_dir" = "$LITERATURE_DIR" ]; then
  sources_prefix="sources/"
else
  sources_prefix=""
fi

has_pdftotext=$(which pdftotext 2>/dev/null && echo "yes" || echo "no")
has_pdfinfo=$(which pdfinfo 2>/dev/null && echo "yes" || echo "no")
has_djvutxt=$(which djvutxt 2>/dev/null && echo "yes" || echo "no")

case "$mode" in
  status)   handle_status ;;
  scan)     handle_scan ;;
  convert)  handle_convert ;;
  validate) handle_validate ;;
  index)    handle_index ;;
  search)   handle_search ;;
  ingest)   handle_ingest ;;
  rebuild)  handle_rebuild ;;
  *)
    echo "Error: Unknown mode '$mode'. Available: status, scan, convert, validate, index, search, ingest, rebuild"
    exit 1
    ;;
esac

if [ ! -d "$lit_dir" ]; then
  echo "## Literature Status"
  echo ""
  echo "No specs/literature/ directory found."
  echo "Create it and add PDF/DJVU files to get started."
  echo ""
  echo "**Tool Availability**:"
  echo "- pdftotext: $has_pdftotext"
  echo "- djvutxt: $has_djvutxt ($([ "$has_djvutxt" = "no" ] && echo 'install: nix-env -iA nixpkgs.djvulibre' || echo 'available'))"
  exit 0
fi

# Find all PDF and DJVU source files
pdf_files=$(find "$lit_dir" -name "*.pdf" 2>/dev/null | sort)
djvu_files=$(find "$lit_dir" -name "*.djvu" 2>/dev/null | sort)
all_source_files="$pdf_files $djvu_files"
 
# Find all markdown files (excluding any in subdirectory source_files/)
md_files=$(find "$lit_dir" -name "*.md" -not -path "*/source_files/*" 2>/dev/null | sort)

if [ -f "$index_file" ]; then
  entry_count=$(jq '.entries | length' "$index_file" 2>/dev/null || echo "0")
  indexed_paths=$(jq -r '.entries[].path' "$index_file" 2>/dev/null || echo "")
else
  entry_count=0
  indexed_paths=""
fi

# Count source files
pdf_count=$(echo "$pdf_files" | grep -c "\.pdf$" 2>/dev/null || echo 0)
djvu_count=$(echo "$djvu_files" | grep -c "\.djvu$" 2>/dev/null || echo 0)
md_count=$(echo "$md_files" | grep -c "\.md$" 2>/dev/null || echo 0)
 
# Identify unprocessed source files (PDFs/DJVUs without corresponding .md)
unprocessed=()
for src in $pdf_files $djvu_files; do
  basename_no_ext=$(basename "$src" | sed 's/\.[^.]*$//')
  # Check if any .md file starts with this basename
  if ! find "$lit_dir" -name "${basename_no_ext}*.md" -not -path "*/source_files/*" 2>/dev/null | grep -q .; then
    unprocessed+=("$src")
  fi
done
unprocessed_count=${#unprocessed[@]}
processed_count=$(( pdf_count + djvu_count - unprocessed_count ))

## Literature Status
 
**Directory**: specs/literature/
**Source Files**: {pdf_count} PDFs, {djvu_count} DJVUs
**Converted**: {processed_count} processed, {unprocessed_count} unprocessed
**Markdown Files**: {md_count}
**Index Entries**: {entry_count}
 
**Tool Availability**:
- pdftotext: {has_pdftotext}
- djvutxt: {has_djvutxt} {install hint if no}
 
{if unprocessed_count > 0}
**Unprocessed Files** ({unprocessed_count}):
- {file1}
- {file2}
...
 
Run `/literature --convert` to convert all, or `/literature --scan` to see details.
{end if}
 
{if entry_count > 0 and md_count != entry_count}
**Index Health**: {entry_count} indexed entries, {md_count} markdown files — run `/literature --validate` to check consistency.
{end if}

unprocessed=()
for src in $(find "$lit_dir" -name "*.pdf" -o -name "*.djvu" 2>/dev/null | sort); do
  basename_no_ext=$(basename "$src" | sed 's/\.[^.]*$//')
  if ! find "$lit_dir" -name "${basename_no_ext}*.md" -not -path "*/source_files/*" 2>/dev/null | grep -q .; then
    unprocessed+=("$src")
  fi
done

for src in "${unprocessed[@]}"; do
  ext="${src##*.}"
  if [ "$ext" = "pdf" ]; then
    if [ "$has_pdfinfo" = "yes" ]; then
      pages=$(pdfinfo "$src" 2>/dev/null | grep "^Pages:" | awk '{print $2}')
    else
      pages="unknown"
    fi
  elif [ "$ext" = "djvu" ]; then
    if [ "$has_djvutxt" = "yes" ]; then
      # djvused can get page count: djvused -e n file.djvu
      pages=$(djvused -e n "$src" 2>/dev/null || echo "unknown")
    else
      pages="unknown (djvutxt not installed)"
    fi
  fi
  echo "- $src ($pages pages)"
done

## Literature Scan Results
 
**Unprocessed Files** ({count}):
- {file1} ({N} pages)
- {file2} ({N} pages)
...
 
**Tool Status**:
- pdftotext: {status}
- djvutxt: {status} {install hint if unavailable}
 
**Next Steps**:
- Convert all: `/literature --convert`
- Convert one: `/literature --convert path/to/file.pdf`

## Literature Scan Results
 
All source files have been converted. No unprocessed PDFs or DJVUs found.
 
**Files**: {N} PDFs, {M} DJVUs — all converted
**Index**: {entry_count} entries in index.json
 
Run `/literature --validate` to check index.json consistency.

project_name=$(basename "$(pwd)")
today=$(date +%Y-%m-%d)
 
if [ -f "specs/literature-index.json" ]; then
  echo "Sub-index already exists at specs/literature-index.json"
  echo "Current entries: $(jq '.entries | length' specs/literature-index.json) entries"
else
  jq -n \
    --arg project "$project_name" \
    --arg today "$today" \
    '{
      "project": $project,
      "literature_dir": null,
      "created": $today,
      "entries": []
    }' > specs/literature-index.json
  echo "Created specs/literature-index.json for project: $project_name"
fi

# Usage: doc_id="blackburn_2002" relevance="Core reference for modal logic"
global_index="${LITERATURE_DIR:-$HOME/Projects/Literature}/index.json"
today=$(date +%Y-%m-%d)
 
# Validate doc_id exists in global index
if ! jq -e --arg id "$doc_id" '.entries[] | select(.id == $id)' "$global_index" >/dev/null 2>&1; then
  echo "Error: doc_id '$doc_id' not found in global index ($global_index)" >&2
  exit 1
fi
 
# Check if already present in sub-index
if jq -e --arg id "$doc_id" '.entries[] | select(.doc_id == $id)' specs/literature-index.json >/dev/null 2>&1; then
  echo "Warning: doc_id '$doc_id' already in sub-index — skipping" >&2
  exit 0
fi
 
# Append entry
tmp=$(mktemp)
jq --arg id "$doc_id" \
   --arg rel "${relevance:-}" \
   --arg today "$today" \
   '.entries += [{
     "doc_id": $id,
     "relevance": (if $rel == "" then null else $rel end),
     "added": $today,
     "source": "manual"
   }]' specs/literature-index.json > "$tmp" && mv "$tmp" specs/literature-index.json
echo "Added doc_id '$doc_id' to specs/literature-index.json"

# Usage: doc_id="blackburn_2002"
tmp=$(mktemp)
before=$(jq '.entries | length' specs/literature-index.json)
jq --arg id "$doc_id" '
  .entries = [.entries[] | select(.doc_id == $id | not)]
' specs/literature-index.json > "$tmp" && mv "$tmp" specs/literature-index.json
after=$(jq '.entries | length' specs/literature-index.json)
 
if [ "$before" -eq "$after" ]; then
  echo "Warning: doc_id '$doc_id' not found in sub-index — no change"
else
  echo "Removed doc_id '$doc_id' from specs/literature-index.json"
fi

global_index="${LITERATURE_DIR:-$HOME/Projects/Literature}/index.json"
 
entry_count=$(jq '.entries | length' specs/literature-index.json)
if [ "$entry_count" -eq 0 ]; then
  echo "Sub-index is empty. Run: /literature --subindex add <doc_id>"
  exit 0
fi
 
echo "## Sub-Index Entries ($entry_count)"
echo ""