@cesarandreslopez/occ 0.1.0 → 0.1.2

package/README.md

@@ -77,24 +77,24 @@ occ --ci docs/
 ## Example Output
 
 ```
--- Documents -----------------------------------------------------------
-Format        Files    Words    Pages    Extra          Size
---------------------------------------------------------------------
-Word             12   34,210      137    1,203 paras    1.2 MB
-PDF               8   22,540       64                   4.5 MB
-Excel             3                      12 sheets      890 KB
---------------------------------------------------------------------
-Total            23   56,750      201    1,203 paras    6.5 MB
---------------------------------------------------------------------
-
--- Code (via scc) ------------------------------------------------------
-Language         Files    Lines   Blanks  Comments     Code
---------------------------------------------------------------------
-JavaScript          15     2340      180       320     1840
-Python               8     1200       90       150      960
---------------------------------------------------------------------
-Total               23     3540      270       470     2800
---------------------------------------------------------------------
+-- Documents ---------------------------------------------------------------
+  Format    Files    Words    Pages                  Details      Size
+----------------------------------------------------------------------------
+  Word         12   34,210      137              1,203 paras    1.2 MB
+  PDF           8   22,540       64                             4.5 MB
+  Excel         3                                12 sheets      890 KB
+----------------------------------------------------------------------------
+  Total        23   56,750      201              1,203 paras    6.5 MB
+
+-- Code (via scc) ----------------------------------------------------------
+  Language    Files    Lines   Blanks  Comments     Code
+----------------------------------------------------------------------------
+  JavaScript     15     2340      180       320     1840
+  Python          8     1200       90       150      960
+----------------------------------------------------------------------------
+  Total          23     3540      270       470     2800
+
+Scanned 23 documents (56,750 words, 201 pages) in 120ms
 ```
 
 ## Supported Formats
@@ -156,7 +156,7 @@ Tools like `scc`, `cloc`, and `tokei` give you instant visibility into codebases
 
 ## How It Works
 
-OCC uses [fast-glob](https://github.com/mrmlnc/fast-glob) for file discovery, dispatches to format-specific parsers (mammoth for DOCX, pdf-parse for PDF, ExcelJS for XLSX, JSZip + officeparser for PPTX/ODF), aggregates metrics, and renders output via cli-table3. For code metrics, it shells out to a vendored [scc](https://github.com/boyter/scc) binary (auto-downloaded during `npm install`, with PATH fallback).
+OCC uses [fast-glob](https://github.com/mrmlnc/fast-glob) for file discovery, dispatches to format-specific parsers (mammoth for DOCX, pdf-parse for PDF, SheetJS for XLSX, JSZip + officeparser for PPTX/ODF), aggregates metrics, and renders output via cli-table3. For code metrics, it shells out to a vendored [scc](https://github.com/boyter/scc) binary (auto-downloaded during `npm install`, with PATH fallback).
 
 ## Contributing
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@cesarandreslopez/occ",
-  "version": "0.1.0",
+  "version": "0.1.2",
   "description": "Office Cloc and Count — scc-style summary tables for office documents",
   "type": "module",
   "bin": {
@@ -20,8 +20,17 @@
     "url": "https://github.com/cesarandreslopez/occ/issues"
   },
   "keywords": [
-    "office", "documents", "cloc", "count", "metrics",
-    "docx", "xlsx", "pptx", "pdf", "scc", "cli"
+    "office",
+    "documents",
+    "cloc",
+    "count",
+    "metrics",
+    "docx",
+    "xlsx",
+    "pptx",
+    "pdf",
+    "scc",
+    "cli"
   ],
   "files": [
     "bin/",
@@ -39,12 +48,12 @@
     "chalk": "^5.3.0",
     "cli-table3": "^0.6.5",
     "commander": "^12.1.0",
-    "exceljs": "^4.4.0",
     "fast-glob": "^3.3.2",
     "jszip": "^3.10.1",
     "mammoth": "^1.8.0",
     "officeparser": "^6.0.1",
-    "pdf-parse": "^1.1.1"
+    "pdf-parse": "^1.1.1",
+    "xlsx": "^0.18.5"
   },
   "devDependencies": {
     "docx": "^9.6.0"

package/scripts/postinstall.js

@@ -3,7 +3,8 @@
 // Downloads the scc binary for the current platform during npm install.
 // Falls back gracefully — if download fails, occ will look for scc on PATH.
 
-import { createWriteStream, existsSync, mkdirSync, chmodSync, unlinkSync } from 'node:fs';
+import { createWriteStream, readFileSync, existsSync, mkdirSync, chmodSync, unlinkSync } from 'node:fs';
+import { createHash } from 'node:crypto';
 import { pipeline } from 'node:stream/promises';
 import { execFile } from 'node:child_process';
 import { promisify } from 'node:util';
@@ -27,6 +28,18 @@ const ARCH_MAP = {
   ia32: 'i386',
 };
 
+// SHA-256 checksums from the official scc v3.7.0 release
+const CHECKSUMS = {
+  'scc_Darwin_arm64.tar.gz':  '376cbae670be59ee64f398de20e0694ec434bf8a9b842642952b0ab0be5f3961',
+  'scc_Darwin_x86_64.tar.gz': 'c3f7457856b9169ccb3c1dd14198e67f730bee065f24d9051bf52cdc2a719ecc',
+  'scc_Linux_arm64.tar.gz':   'dcb05c6e993bb2d8d2da4765ff018f2e752325dd205a41698929c55e4123575d',
+  'scc_Linux_i386.tar.gz':    '1de91dae8a927ac2063a99b520d9a474644db6827fe6f85e3d8f87a1def3b14d',
+  'scc_Linux_x86_64.tar.gz':  '3d9d65b00ca874c2b29151abe7e1480736f5229edc3ce8e4b2791460cdfabf5a',
+  'scc_Windows_arm64.zip':    'fd114614c10382c9ed2e32d5455cc4b51960a9f71691c5c1ca42b31adea5b84d',
+  'scc_Windows_i386.zip':     '7b887022c37dc79e79ae51897030a6ff2515ab7b124e7b2aabcb0fba15412b05',
+  'scc_Windows_x86_64.zip':   '97abf9d55d4b79d3310536d576ccbdf5017aeb425780e850336120b6e67622e1',
+};
+
 function getAssetName() {
   const platform = PLATFORM_MAP[process.platform];
   const arch = ARCH_MAP[process.arch];
@@ -53,6 +66,19 @@ async function download(url, dest) {
   await pipeline(res.body, createWriteStream(dest));
 }
 
+function verifyChecksum(filePath, assetName) {
+  const expected = CHECKSUMS[assetName];
+  if (!expected) {
+    console.warn(`occ: No checksum available for ${assetName}, skipping verification`);
+    return;
+  }
+  const data = readFileSync(filePath);
+  const actual = createHash('sha256').update(data).digest('hex');
+  if (actual !== expected) {
+    throw new Error(`Checksum mismatch for ${assetName}\n  Expected: ${expected}\n  Got:      ${actual}`);
+  }
+}
+
 async function extract(archive, destDir) {
   if (archive.endsWith('.tar.gz')) {
     await execFileAsync('tar', ['xzf', archive, '-C', destDir]);
@@ -92,6 +118,7 @@ async function main() {
   try {
     console.log(`Downloading scc v${SCC_VERSION} for ${process.platform}-${process.arch}...`);
     await download(url, archivePath);
+    verifyChecksum(archivePath, assetName);
 
     console.log('Extracting...');
     await extract(archivePath, vendorDir);

package/src/cli.js

@@ -1,20 +1,22 @@
-import { Command } from 'commander';
-import { writeFile } from 'node:fs/promises';
+import { Command, Option } from 'commander';
+import { readFile, writeFile } from 'node:fs/promises';
 import { findFiles } from './walker.js';
 import { parseFiles } from './parsers/index.js';
 import { aggregate } from './stats.js';
-import { formatDocumentTable, formatSccTable } from './output/tabular.js';
+import { formatDocumentTable, formatSccTable, formatSummaryLine } from './output/tabular.js';
 import { formatJson } from './output/json.js';
 import { checkScc, runScc } from './scc.js';
 import { createProgress } from './progress.js';
 
+const pkg = JSON.parse(await readFile(new URL('../package.json', import.meta.url), 'utf8'));
+
 export async function run(argv) {
   const program = new Command();
 
   program
     .name('occ')
     .description('Office Cloc and Count — scc-style summary tables for office documents')
-    .version('0.1.0')
+    .version(pkg.version)
     .argument('[directories...]', 'directories to scan', [])
     .option('-f, --by-file', 'show a row per file instead of grouped by type')
     .option('--format <type>', 'output format: tabular or json', 'tabular')
@@ -22,7 +24,7 @@ export async function run(argv) {
     .option('--exclude-ext <exts>', 'comma-separated extensions to exclude')
     .option('--exclude-dir <dirs>', 'directories to skip (comma-separated)', 'node_modules,.git')
     .option('--no-gitignore', 'disable .gitignore respect')
-    .option('--sort <col>', 'sort by: files, name, words, size', 'files')
+    .addOption(new Option('--sort <col>', 'sort by: files, name, words, size').choices(['files', 'name', 'words', 'size']).default('files'))
     .option('-o, --output <file>', 'write output to file')
     .option('--ci', 'ASCII-only output, no colors')
     .option('--large-file-limit <mb>', 'skip files over this size in MB', '50')
@@ -39,14 +41,25 @@ export async function run(argv) {
   await program.parseAsync(argv);
 }
 
+function validateLargeFileLimit(value) {
+  const n = parseFloat(value);
+  if (Number.isNaN(n) || n <= 0) {
+    throw new Error(`Invalid --large-file-limit value: "${value}" (must be a positive number)`);
+  }
+  return n;
+}
+
 async function execute(directories, opts) {
+  const startTime = Date.now();
   const excludeDirs = opts.excludeDir
     ? opts.excludeDir.split(',').map(d => d.trim())
     : ['node_modules', '.git'];
 
-  // Check scc availability (unless --no-code)
-  if (opts.code !== false) {
-    await checkScc();
+  const includeCode = opts.code !== false;
+
+  let sccBinary = null;
+  if (includeCode) {
+    sccBinary = await checkScc();
   }
 
   // Find and parse office documents
@@ -55,7 +68,7 @@ async function execute(directories, opts) {
     excludeExt: opts.excludeExt,
     excludeDir: excludeDirs,
     noGitignore: !opts.gitignore,
-    largeFileLimit: parseFloat(opts.largeFileLimit),
+    largeFileLimit: validateLargeFileLimit(opts.largeFileLimit),
   });
 
   const showProgress = opts.format !== 'json' && process.stderr.isTTY;
@@ -71,11 +84,10 @@ async function execute(directories, opts) {
     sort: opts.sort,
   });
 
-  // Run scc for code files
   let sccData = null;
-  if (opts.code !== false) {
+  if (includeCode) {
     if (showProgress) process.stderr.write('\rAnalyzing code with scc...');
-    sccData = await runScc(directories, {
+    sccData = await runScc(sccBinary, directories, {
       byFile: opts.byFile,
       excludeDir: excludeDirs,
       sort: opts.sort,
@@ -106,9 +118,9 @@ async function execute(directories, opts) {
         parts.push(formatSccTable(sccData, { ci: opts.ci, byFile: opts.byFile }));
       }
 
-      if (files.length === 0) {
-        parts.unshift('\nNo office documents found.');
-      }
+      const elapsed = Date.now() - startTime;
+      const summary = formatSummaryLine(stats, sccData, elapsed, { ci: opts.ci });
+      if (summary) parts.push(summary);
     }
 
     if (skipped.length > 0) {

package/src/output/json.js

@@ -1,31 +1,35 @@
+import { METRIC_FIELDS, hasKey } from '../utils.js';
+
 export function formatJson(stats, sccData = null) {
+  const { columns } = stats;
+
+  const mapRow = (r) => {
+    const entry = {
+      type: r.fileType,
+      ...(r.fileName ? { name: r.fileName } : {}),
+      ...(r.filePath ? { path: r.filePath } : {}),
+      count: r.files,
+    };
+    for (const f of METRIC_FIELDS) {
+      if (r[hasKey(f)]) entry[f] = r[f] || 0;
+    }
+    entry.size = r.size;
+    return entry;
+  };
+
+  const mapTotals = (t) => {
+    const entry = { files: t.files };
+    for (const f of METRIC_FIELDS) {
+      if (columns[hasKey(f)]) entry[f] = t[f];
+    }
+    entry.size = t.size;
+    return entry;
+  };
+
   const output = {
     documents: {
-      files: stats.rows.map(r => ({
-        type: r.fileType,
-        ...(r.fileName ? { name: r.fileName } : {}),
-        ...(r.filePath ? { path: r.filePath } : {}),
-        count: r.files,
-        words: r.words || 0,
-        pages: r.pages || 0,
-        paragraphs: r.paragraphs || 0,
-        sheets: r.sheets || 0,
-        rows: r.rows || 0,
-        cells: r.cells || 0,
-        slides: r.slides || 0,
-        size: r.size,
-      })),
-      totals: {
-        files: stats.totals.files,
-        words: stats.totals.words,
-        pages: stats.totals.pages,
-        paragraphs: stats.totals.paragraphs,
-        sheets: stats.totals.sheets,
-        rows: stats.totals.rows,
-        cells: stats.totals.cells,
-        slides: stats.totals.slides,
-        size: stats.totals.size,
-      },
+      files: stats.rows.map(mapRow),
+      totals: mapTotals(stats.totals),
     },
   };
 

package/src/output/tabular.js

@@ -6,25 +6,30 @@ export function formatDocumentTable(stats, options = {}) {
   const { ci = false } = options;
   const c = ci ? noColor : colorize;
 
-  const headers = buildHeaders(stats.columns, stats.mode === 'by-file', c);
+  const isByFile = stats.mode === 'by-file';
+  const headers = buildHeaders(stats.columns, isByFile, c);
+  const colAligns = buildColAligns(stats.columns, isByFile);
   const table = new Table({
     head: headers.map(h => h.label),
-    chars: ci ? asciiChars() : unicodeChars(),
+    chars: tableChars(ci),
     style: { head: [], border: [] },
+    colAligns,
   });
 
   for (const row of stats.rows) {
-    table.push(buildRow(row, stats.columns, stats.mode === 'by-file', c));
+    table.push(buildRow(row, stats.columns, isByFile, c));
   }
 
-  // Totals row
-  const isByFile = stats.mode === 'by-file';
   table.push(buildRow(stats.totals, stats.columns, isByFile, c, true));
 
+  const tableStr = addSeparators(table.toString(), ci ? '-' : '─');
+
+  const tableWidth = stripAnsi(tableStr.split('\n')[0]).length;
+
   const lines = [];
   lines.push('');
-  lines.push(c.header(`── Documents ${'─'.repeat(56)}`));
-  lines.push(table.toString());
+  lines.push(c.header(sectionHeader('Documents', tableWidth, ci)));
+  lines.push(tableStr);
 
   // Footnotes
   const hasEstimatedPages = stats.rows.some(r =>
@@ -52,7 +57,7 @@ export function formatSccTable(sccData, options = {}) {
       c.headerCell('Comments'),
       c.headerCell('Code'),
     ],
-    chars: ci ? asciiChars() : unicodeChars(),
+    chars: tableChars(ci),
     style: { head: [], border: [] },
     colAligns: ['left', 'right', 'right', 'right', 'right', 'right'],
   });
@@ -66,8 +71,8 @@ export function formatSccTable(sccData, options = {}) {
           c.type(file.Filename || file.Location || ''),
           formatNumber(1),
           c.number(formatNumber(file.Lines)),
-          formatNumber(file.Blank),
-          formatNumber(file.Comment),
+          c.number(formatNumber(file.Blank)),
+          c.number(formatNumber(file.Comment)),
           c.number(formatNumber(file.Code)),
         ]);
       }
@@ -76,8 +81,8 @@ export function formatSccTable(sccData, options = {}) {
         c.type(lang.Name),
         formatNumber(lang.Count),
         c.number(formatNumber(lang.Lines)),
-        formatNumber(lang.Blank),
-        formatNumber(lang.Comment),
+        c.number(formatNumber(lang.Blank)),
+        c.number(formatNumber(lang.Comment)),
         c.number(formatNumber(lang.Code)),
       ]);
     }
@@ -97,30 +102,117 @@ export function formatSccTable(sccData, options = {}) {
     c.total(formatNumber(totalCode)),
   ]);
 
+  const tableStr = addSeparators(table.toString(), ci ? '-' : '─');
+  const tableWidth = stripAnsi(tableStr.split('\n')[0]).length;
+
   const lines = [];
   lines.push('');
-  lines.push(c.header(`── Code (via scc) ${'─'.repeat(51)}`));
-  lines.push(table.toString());
+  lines.push(c.header(sectionHeader('Code (via scc)', tableWidth, ci)));
+  lines.push(tableStr);
 
   return lines.join('\n');
 }
 
+export function formatSummaryLine(stats, sccData, elapsed, options = {}) {
+  const { ci = false } = options;
+  const c = ci ? noColor : colorize;
+
+  const parts = [];
+  if (stats && stats.totals.files > 0) {
+    let docPart = `${stats.totals.files} document${stats.totals.files !== 1 ? 's' : ''}`;
+    const details = [];
+    if (stats.totals.words > 0) details.push(`${formatNumber(stats.totals.words)} word${stats.totals.words !== 1 ? 's' : ''}`);
+    if (stats.totals.pages > 0) details.push(`${formatNumber(stats.totals.pages)} page${stats.totals.pages !== 1 ? 's' : ''}`);
+    if (details.length > 0) docPart += ` (${details.join(', ')})`;
+    parts.push(docPart);
+  }
+  if (sccData && sccData.length > 0) {
+    const totalCode = sccData.reduce((sum, l) => sum + (l.Code || 0), 0);
+    parts.push(`${formatNumber(totalCode)} lines of code`);
+  }
+
+  if (parts.length === 0) return '';
+
+  const time = elapsed >= 1000
+    ? `${(elapsed / 1000).toFixed(1)}s`
+    : `${elapsed}ms`;
+
+  return '\n' + c.dim(`Scanned ${parts.join(', ')} in ${time}`) + '\n';
+}
+
+/**
+ * Post-process table string to insert separator lines after the header row
+ * and before the totals row (last data row).
+ *
+ * Table layout from cli-table3 (with empty mid chars):
+ *   line 0: top border
+ *   line 1: header row
+ *   lines 2..N-2: data rows
+ *   line N-1: totals row
+ *   line N: bottom border
+ */
+function addSeparators(tableStr, char) {
+  const lines = tableStr.split('\n');
+  if (lines.length < 4) return tableStr;
+
+  // Use header row width — top border is narrower due to single-char top-mid vs 2-char middle
+  const width = stripAnsi(lines[1]).length;
+  const sep = char.repeat(width);
+
+  const result = [];
+  // Skip lines[0] (top border) — section header already serves as delimiter
+  result.push(lines[1]); // header row
+  result.push(sep);      // header separator
+
+  // Data rows (everything except first 2 and last 2)
+  for (let i = 2; i < lines.length - 2; i++) {
+    result.push(lines[i]);
+  }
+
+  result.push(sep);                    // totals separator
+  result.push(lines[lines.length - 2]); // totals row
+  // Skip bottom border — totals row is the natural end
+
+  return result.join('\n');
+}
+
+function stripAnsi(str) {
+  return str.replace(/\x1b\[[0-9;]*m/g, '');
+}
+
+function sectionHeader(title, width, ci = false) {
+  const dash = ci ? '-' : '─';
+  const prefix = `${dash}${dash} ${title} `;
+  const padLen = Math.max(0, width - prefix.length);
+  return prefix + dash.repeat(padLen);
+}
+
+function hasExtraColumns(columns) {
+  return columns.hasParagraphs || columns.hasSheets || columns.hasSlides ||
+         columns.hasRows || columns.hasCells;
+}
+
 function buildHeaders(columns, byFile, c) {
   const headers = [];
   headers.push({ key: 'format', label: c.headerCell(byFile ? 'File' : 'Format') });
   if (!byFile) headers.push({ key: 'files', label: c.headerCell('Files') });
   if (columns.hasWords) headers.push({ key: 'words', label: c.headerCell('Words') });
   if (columns.hasPages) headers.push({ key: 'pages', label: c.headerCell('Pages') });
-
-  // Extra column for type-specific metrics
-  const hasExtra = columns.hasParagraphs || columns.hasSheets || columns.hasSlides ||
-                   columns.hasRows || columns.hasCells;
-  if (hasExtra) headers.push({ key: 'extra', label: c.headerCell('Extra') });
-
+  if (hasExtraColumns(columns)) headers.push({ key: 'extra', label: c.headerCell('Details') });
   headers.push({ key: 'size', label: c.headerCell('Size') });
   return headers;
 }
 
+function buildColAligns(columns, byFile) {
+  const aligns = ['left']; // Format/File
+  if (!byFile) aligns.push('right'); // Files
+  if (columns.hasWords) aligns.push('right');
+  if (columns.hasPages) aligns.push('right');
+  if (hasExtraColumns(columns)) aligns.push('right');
+  aligns.push('right'); // Size
+  return aligns;
+}
+
 function buildRow(row, columns, byFile, c, isTotal = false) {
   const fmt = isTotal ? c.total : (v) => v;
   const fmtType = isTotal ? c.total : c.type;
@@ -142,9 +234,7 @@ function buildRow(row, columns, byFile, c, isTotal = false) {
   if (columns.hasWords) cells.push(fmtNum(row.words ? formatNumber(row.words) : ''));
   if (columns.hasPages) cells.push(fmtNum(row.pages ? formatNumber(row.pages) : ''));
 
-  const hasExtra = columns.hasParagraphs || columns.hasSheets || columns.hasSlides ||
-                   columns.hasRows || columns.hasCells;
-  if (hasExtra) {
+  if (hasExtraColumns(columns)) {
     const parts = [];
     if (row.paragraphs) parts.push(`${formatNumber(row.paragraphs)} paras`);
     if (row.sheets) parts.push(`${formatNumber(row.sheets)} sheets`);
@@ -158,21 +248,13 @@ function buildRow(row, columns, byFile, c, isTotal = false) {
   return cells;
 }
 
-function unicodeChars() {
+function tableChars(ci) {
+  const ch = ci ? '-' : '─';
   return {
-    top: '─', 'top-mid': '─', 'top-left': '─', 'top-right': '─',
-    bottom: '─', 'bottom-mid': '─', 'bottom-left': '─', 'bottom-right': '─',
-    left: ' ', 'left-mid': '─', mid: '─', 'mid-mid': '─',
-    right: ' ', 'right-mid': '─', middle: '  ',
-  };
-}
-
-function asciiChars() {
-  return {
-    top: '-', 'top-mid': '-', 'top-left': '-', 'top-right': '-',
-    bottom: '-', 'bottom-mid': '-', 'bottom-left': '-', 'bottom-right': '-',
-    left: ' ', 'left-mid': '-', mid: '-', 'mid-mid': '-',
-    right: ' ', 'right-mid': '-', middle: '  ',
+    top: ch, 'top-mid': ch, 'top-left': ch, 'top-right': ch,
+    bottom: ch, 'bottom-mid': ch, 'bottom-left': ch, 'bottom-right': ch,
+    left: ' ', 'left-mid': '', mid: '', 'mid-mid': '',
+    right: ' ', 'right-mid': '', middle: '  ',
   };
 }
 
@@ -186,12 +268,5 @@ const colorize = {
   dim: (s) => chalk.dim(s),
 };
 
-const noColor = {
-  header: (s) => s,
-  headerCell: (s) => s,
-  type: (s) => s,
-  number: (s) => s,
-  total: (s) => s,
-  error: (s) => s,
-  dim: (s) => s,
-};
+const identity = (s) => s;
+const noColor = Object.fromEntries(Object.keys(colorize).map(k => [k, identity]));

package/src/parsers/docx.js

@@ -10,14 +10,6 @@ export async function parseDocx(filePath) {
 
   return {
     fileType: 'Word',
-    metrics: {
-      words,
-      pages,
-      paragraphs,
-      sheets: null,
-      rows: null,
-      cells: null,
-      slides: null,
-    },
+    metrics: { words, pages, paragraphs },
   };
 }

package/src/parsers/index.js

@@ -15,18 +15,22 @@ const PARSER_MAP = {
   odp: parseOdf,
 };
 
+function failureResult(filePath, size, ext) {
+  return {
+    filePath,
+    size,
+    success: false,
+    fileType: EXTENSION_TO_TYPE[ext] || ext.toUpperCase(),
+    metrics: null,
+  };
+}
+
 export async function parseFile(filePath, size) {
   const ext = getExtension(filePath);
   const parser = PARSER_MAP[ext];
 
   if (!parser) {
-    return {
-      filePath,
-      size,
-      success: false,
-      fileType: EXTENSION_TO_TYPE[ext] || ext.toUpperCase(),
-      metrics: null,
-    };
+    return failureResult(filePath, size, ext);
   }
 
   try {
@@ -39,13 +43,7 @@ export async function parseFile(filePath, size) {
       metrics: result.metrics,
     };
   } catch {
-    return {
-      filePath,
-      size,
-      success: false,
-      fileType: EXTENSION_TO_TYPE[ext] || ext.toUpperCase(),
-      metrics: null,
-    };
+    return failureResult(filePath, size, ext);
   }
 }
 

package/src/parsers/odf.js

@@ -5,11 +5,12 @@ import { countWords, getExtension } from '../utils.js';
 
 export async function parseOdf(filePath) {
   const ext = getExtension(filePath);
-  const buffer = await readFile(filePath);
 
   if (ext === 'odt') return parseOdt(filePath);
-  if (ext === 'ods') return parseOds(filePath, buffer);
-  if (ext === 'odp') return parseOdp(filePath, buffer);
+
+  const buffer = await readFile(filePath);
+  if (ext === 'ods') return parseOds(buffer);
+  if (ext === 'odp') return parseOdp(buffer);
 
   throw new Error(`Unsupported ODF format: ${ext}`);
 }
@@ -22,19 +23,11 @@ async function parseOdt(filePath) {
 
   return {
     fileType: 'ODT',
-    metrics: {
-      words,
-      pages,
-      paragraphs,
-      sheets: null,
-      rows: null,
-      cells: null,
-      slides: null,
-    },
+    metrics: { words, pages, paragraphs },
   };
 }
 
-async function parseOds(filePath, buffer) {
+async function parseOds(buffer) {
   const zip = await JSZip.loadAsync(buffer);
   const contentXml = await zip.file('content.xml')?.async('text');
   if (!contentXml) throw new Error('No content.xml found in ODS');
@@ -42,44 +35,28 @@ async function parseOds(filePath, buffer) {
   const sheets = (contentXml.match(/<table:table /g) || []).length;
   const rows = (contentXml.match(/<table:table-row/g) || []).length;
 
-  // Use officeparser for cell text count
-  const text = await officeparser.parseOffice(filePath);
+  // Use officeparser with buffer to avoid re-reading from disk
+  const text = await officeparser.parseOffice(buffer);
   const cells = text.split(/\n/).filter(s => s.trim().length > 0).length;
 
   return {
     fileType: 'ODS',
-    metrics: {
-      words: null,
-      pages: null,
-      paragraphs: null,
-      sheets,
-      rows,
-      cells,
-      slides: null,
-    },
+    metrics: { sheets, rows, cells },
   };
 }
 
-async function parseOdp(filePath, buffer) {
+async function parseOdp(buffer) {
   const zip = await JSZip.loadAsync(buffer);
   const contentXml = await zip.file('content.xml')?.async('text');
   if (!contentXml) throw new Error('No content.xml found in ODP');
 
   const slides = (contentXml.match(/<draw:page /g) || []).length;
 
-  const text = await officeparser.parseOffice(filePath);
+  const text = await officeparser.parseOffice(buffer);
   const words = countWords(text);
 
   return {
     fileType: 'ODP',
-    metrics: {
-      words,
-      pages: null,
-      paragraphs: null,
-      sheets: null,
-      rows: null,
-      cells: null,
-      slides,
-    },
+    metrics: { words, slides },
   };
 }

package/src/parsers/pdf.js

@@ -25,6 +25,7 @@ function beginSuppression() {
 function endSuppression() {
   if (--suppressionDepth === 0) {
     console.log = originalLog;
+    capturedWarnings.length = 0;
   }
 }
 
@@ -43,14 +44,6 @@ export async function parsePdf(filePath) {
 
   return {
     fileType: 'PDF',
-    metrics: {
-      words,
-      pages: data.numpages,
-      paragraphs: null,
-      sheets: null,
-      rows: null,
-      cells: null,
-      slides: null,
-    },
+    metrics: { words, pages: data.numpages },
   };
 }

package/src/parsers/pptx.js

@@ -13,20 +13,12 @@ export async function parsePptx(filePath) {
   );
   const slides = slideFiles.length;
 
-  // Extract text via officeparser
-  const text = await officeparser.parseOffice(filePath);
+  // Extract text via officeparser (reuse buffer to avoid re-reading)
+  const text = await officeparser.parseOffice(buffer);
   const words = countWords(text);
 
   return {
     fileType: 'PowerPoint',
-    metrics: {
-      words,
-      pages: null,
-      paragraphs: null,
-      sheets: null,
-      rows: null,
-      cells: null,
-      slides,
-    },
+    metrics: { words, slides },
   };
 }

package/src/parsers/xlsx.js

@@ -1,32 +1,23 @@
-import ExcelJS from 'exceljs';
+import XLSX from 'xlsx';
 
 export async function parseXlsx(filePath) {
-  const workbook = new ExcelJS.Workbook();
-  await workbook.xlsx.readFile(filePath);
+  const workbook = XLSX.readFile(filePath);
 
-  const sheets = workbook.worksheets.length;
+  const sheets = workbook.SheetNames.length;
   let rows = 0;
   let cells = 0;
 
-  for (const worksheet of workbook.worksheets) {
-    rows += worksheet.actualRowCount || 0;
-    worksheet.eachRow((row) => {
-      row.eachCell(() => {
-        cells++;
-      });
-    });
+  for (const name of workbook.SheetNames) {
+    const sheet = workbook.Sheets[name];
+    const ref = sheet['!ref'];
+    if (!ref) continue;
+    const range = XLSX.utils.decode_range(ref);
+    rows += range.e.r - range.s.r + 1;
+    cells += (range.e.r - range.s.r + 1) * (range.e.c - range.s.c + 1);
   }
 
   return {
     fileType: 'Excel',
-    metrics: {
-      words: null,
-      pages: null,
-      paragraphs: null,
-      sheets,
-      rows,
-      cells,
-      slides: null,
-    },
+    metrics: { sheets, rows, cells },
   };
 }

package/src/scc.js

@@ -28,19 +28,18 @@ async function findScc() {
   }
 }
 
-let sccBinary = null;
-
 export async function checkScc() {
-  sccBinary = await findScc();
-  if (!sccBinary) {
+  const binary = await findScc();
+  if (!binary) {
     throw new Error(
       'scc is required but not found.\n' +
       'Run "npm install" to auto-download it, or install manually from https://github.com/boyter/scc'
     );
   }
+  return binary;
 }
 
-export async function runScc(directories, options = {}) {
+export async function runScc(sccBinary, directories, options = {}) {
   const {
     byFile = false,
     excludeDir = [],
@@ -49,7 +48,6 @@ export async function runScc(directories, options = {}) {
     noGitignore = false,
   } = options;
 
-  if (!sccBinary) sccBinary = await findScc();
   if (!sccBinary) return [];
 
   const args = ['--format', 'json'];

package/src/stats.js

@@ -1,5 +1,7 @@
 import path from 'node:path';
-import { EXTENSION_TO_TYPE } from './utils.js';
+import { METRIC_FIELDS, hasKey } from './utils.js';
+
+const SUM_FIELDS = ['files', ...METRIC_FIELDS, 'size'];
 
 export function aggregate(results, options = {}) {
   const { byFile = false, sort = 'files' } = options;
@@ -16,25 +18,9 @@ function aggregateByType(results, sort) {
   for (const r of results) {
     const key = r.success ? r.fileType : 'Unreadable';
     if (!groups[key]) {
-      groups[key] = {
-        fileType: key,
-        files: 0,
-        words: 0,
-        pages: 0,
-        paragraphs: 0,
-        sheets: 0,
-        rows: 0,
-        cells: 0,
-        slides: 0,
-        size: 0,
-        hasWords: false,
-        hasPages: false,
-        hasParagraphs: false,
-        hasSheets: false,
-        hasRows: false,
-        hasCells: false,
-        hasSlides: false,
-      };
+      const g = { fileType: key, files: 0, size: 0 };
+      for (const f of METRIC_FIELDS) { g[f] = 0; g[hasKey(f)] = false; }
+      groups[key] = g;
     }
     const g = groups[key];
     g.files++;
@@ -42,54 +28,39 @@ function aggregateByType(results, sort) {
 
     if (r.success && r.metrics) {
       const m = r.metrics;
-      if (m.words != null) { g.words += m.words; g.hasWords = true; }
-      if (m.pages != null) { g.pages += m.pages; g.hasPages = true; }
-      if (m.paragraphs != null) { g.paragraphs += m.paragraphs; g.hasParagraphs = true; }
-      if (m.sheets != null) { g.sheets += m.sheets; g.hasSheets = true; }
-      if (m.rows != null) { g.rows += m.rows; g.hasRows = true; }
-      if (m.cells != null) { g.cells += m.cells; g.hasCells = true; }
-      if (m.slides != null) { g.slides += m.slides; g.hasSlides = true; }
+      for (const f of METRIC_FIELDS) {
+        if (m[f] != null) { g[f] += m[f]; g[hasKey(f)] = true; }
+      }
     }
   }
 
-  const rows = Object.values(groups);
-  sortRows(rows, sort);
-
-  const totals = computeTotals(rows);
-  const columns = detectColumns(rows);
-
-  return { rows, totals, columns, mode: 'grouped' };
+  return finalize(Object.values(groups), sort, 'grouped');
 }
 
 function aggregateByFile(results, sort) {
-  const rows = results.map(r => ({
-    fileType: r.success ? r.fileType : 'Unreadable',
-    fileName: path.basename(r.filePath),
-    filePath: r.filePath,
-    files: 1,
-    words: r.metrics?.words || 0,
-    pages: r.metrics?.pages || 0,
-    paragraphs: r.metrics?.paragraphs || 0,
-    sheets: r.metrics?.sheets || 0,
-    rows: r.metrics?.rows || 0,
-    cells: r.metrics?.cells || 0,
-    slides: r.metrics?.slides || 0,
-    size: r.size || 0,
-    hasWords: r.metrics?.words != null,
-    hasPages: r.metrics?.pages != null,
-    hasParagraphs: r.metrics?.paragraphs != null,
-    hasSheets: r.metrics?.sheets != null,
-    hasRows: r.metrics?.rows != null,
-    hasCells: r.metrics?.cells != null,
-    hasSlides: r.metrics?.slides != null,
-  }));
+  const rows = results.map(r => {
+    const row = {
+      fileType: r.success ? r.fileType : 'Unreadable',
+      fileName: path.basename(r.filePath),
+      filePath: r.filePath,
+      files: 1,
+      size: r.size || 0,
+    };
+    for (const f of METRIC_FIELDS) {
+      row[f] = r.metrics?.[f] || 0;
+      row[hasKey(f)] = r.metrics?.[f] != null;
+    }
+    return row;
+  });
 
-  sortRows(rows, sort);
+  return finalize(rows, sort, 'by-file');
+}
 
+function finalize(rows, sort, mode) {
+  sortRows(rows, sort);
   const totals = computeTotals(rows);
   const columns = detectColumns(rows);
-
-  return { rows, totals, columns, mode: 'by-file' };
+  return { rows, totals, columns, mode };
 }
 
 function sortRows(rows, sort) {
@@ -104,40 +75,18 @@ function sortRows(rows, sort) {
 }
 
 function computeTotals(rows) {
-  const totals = {
-    fileType: 'Total',
-    files: 0,
-    words: 0,
-    pages: 0,
-    paragraphs: 0,
-    sheets: 0,
-    rows: 0,
-    cells: 0,
-    slides: 0,
-    size: 0,
-  };
+  const totals = { fileType: 'Total' };
+  for (const f of SUM_FIELDS) totals[f] = 0;
   for (const r of rows) {
-    totals.files += r.files;
-    totals.words += r.words;
-    totals.pages += r.pages;
-    totals.paragraphs += r.paragraphs;
-    totals.sheets += r.sheets;
-    totals.rows += r.rows;
-    totals.cells += r.cells;
-    totals.slides += r.slides;
-    totals.size += r.size;
+    for (const f of SUM_FIELDS) totals[f] += r[f];
   }
   return totals;
 }
 
 function detectColumns(rows) {
-  return {
-    hasWords: rows.some(r => r.hasWords),
-    hasPages: rows.some(r => r.hasPages),
-    hasParagraphs: rows.some(r => r.hasParagraphs),
-    hasSheets: rows.some(r => r.hasSheets),
-    hasRows: rows.some(r => r.hasRows),
-    hasCells: rows.some(r => r.hasCells),
-    hasSlides: rows.some(r => r.hasSlides),
-  };
+  const columns = {};
+  for (const f of METRIC_FIELDS) {
+    columns[hasKey(f)] = rows.some(r => r[hasKey(f)]);
+  }
+  return columns;
 }

package/src/utils.js

@@ -22,8 +22,6 @@ export function getExtension(filePath) {
   return path.extname(filePath).toLowerCase().replace('.', '');
 }
 
-export const OFFICE_EXTENSIONS = ['docx', 'xlsx', 'pptx', 'pdf', 'odt', 'ods', 'odp'];
-
 export const EXTENSION_TO_TYPE = {
   docx: 'Word',
   pdf: 'PDF',
@@ -33,3 +31,11 @@ export const EXTENSION_TO_TYPE = {
   ods: 'ODS',
   odp: 'ODP',
 };
+
+export const OFFICE_EXTENSIONS = Object.keys(EXTENSION_TO_TYPE);
+
+export const METRIC_FIELDS = ['words', 'pages', 'paragraphs', 'sheets', 'rows', 'cells', 'slides'];
+
+export function hasKey(field) {
+  return `has${field[0].toUpperCase()}${field.slice(1)}`;
+}

package/src/walker.js

@@ -30,55 +30,40 @@ export async function findFiles(directories, options = {}) {
 
   const ignore = excludeDir.map(d => `**/${d}/**`);
 
-  const paths = await fg(pattern, {
-    cwd: undefined,
-    absolute: true,
-    ignore,
-    dot: false,
-    onlyFiles: true,
-    followSymbolicLinks: false,
-    ...(directories.length > 0 ? {} : { cwd: process.cwd() }),
-  });
-
-  // If directories specified, search each one
-  let allPaths = [];
-  if (directories.length > 0) {
-    for (const dir of directories) {
-      const found = await fg(pattern, {
-        cwd: dir,
-        absolute: true,
-        ignore,
-        dot: false,
-        onlyFiles: true,
-        followSymbolicLinks: false,
-      });
-      allPaths.push(...found);
-    }
-  } else {
-    allPaths = await fg(pattern, {
-      cwd: process.cwd(),
+  const dirs = directories.length > 0 ? directories : [process.cwd()];
+  const allPaths = [];
+  for (const dir of dirs) {
+    const found = await fg(pattern, {
+      cwd: dir,
       absolute: true,
       ignore,
       dot: false,
       onlyFiles: true,
       followSymbolicLinks: false,
     });
+    allPaths.push(...found);
   }
 
   const limitBytes = largeFileLimit * 1024 * 1024;
   const files = [];
   const skipped = [];
 
-  for (const p of allPaths) {
-    try {
-      const s = await stat(p);
-      if (s.size > limitBytes) {
-        skipped.push({ path: p, reason: `Exceeds ${largeFileLimit}MB limit`, size: s.size });
+  // Batch stat calls for better throughput on large directories
+  const BATCH_SIZE = 50;
+  for (let i = 0; i < allPaths.length; i += BATCH_SIZE) {
+    const batch = allPaths.slice(i, i + BATCH_SIZE);
+    const results = await Promise.allSettled(batch.map(p => stat(p)));
+    for (let j = 0; j < results.length; j++) {
+      const p = batch[j];
+      const r = results[j];
+      if (r.status === 'rejected') {
+        const err = r.reason;
+        skipped.push({ path: p, reason: err.code === 'EACCES' ? 'Permission denied' : err.message, size: 0 });
+      } else if (r.value.size > limitBytes) {
+        skipped.push({ path: p, reason: `Exceeds ${largeFileLimit}MB limit`, size: r.value.size });
       } else {
-        files.push({ path: p, size: s.size });
+        files.push({ path: p, size: r.value.size });
       }
-    } catch (err) {
-      skipped.push({ path: p, reason: err.code === 'EACCES' ? 'Permission denied' : err.message, size: 0 });
     }
   }