@veda-hq/pariksha 0.1.0 → 0.3.1

package/README.md

@@ -3,24 +3,84 @@
 परीक्षा, examination. Repository checks: doc drift, rule enforcement,
 test-quality ratchets. Part of [Veda](https://github.com/veda-hq/veda).
 
-## v0.1: `pariksha boundary`
+```sh
+npx @veda-hq/pariksha@0.3.1 <check> [flags]
+npx @veda-hq/pariksha@0.3.1 --version
+```
 
-Refuses any file git tracks, by its path or its text, that names a word on
-the repository's deny list.
+Every check exits 0 when the repository passes, 1 when it refuses something
+(each finding on stderr, with how to fix it), and 2 on a usage or input
+error. `--root <dir>` (default: the current directory) names the repository.
+Node 24 or later. MIT.
+
+## `boundary`
 
 ```sh
-npx @veda-hq/pariksha@0.1.0 boundary [--root <dir>] [--deny <file>]
-npx @veda-hq/pariksha@0.1.0 hash <word>
-npx @veda-hq/pariksha@0.1.0 --version
+pariksha boundary [--root <dir>] [--deny <file>]
+pariksha hash <word>
 ```
 
+Refuses any file git tracks, by its path or its text, that names a word on
+the repository's deny list.
+
 - The deny list (default `.veda/deny.sha256`, relative to the root) holds one
   SHA-256 hash of a lowercase word per line; blank lines and `#` comments are
   ignored. `pariksha hash <word>` prints the line for a word.
 - Words are runs of ASCII letters and digits, compared case-insensitively:
   `foo-bar`, `foo_bar` and `@Foo/bar` all contain the word `foo`.
 - Binary files (any NUL byte) are skipped. Untracked files are not read.
-- Exit codes: 0 clean, 1 a denied word was found (each is listed with its file
-  and line; line 0 is the file's path), 2 a usage or deny-list error.
+  Line 0 in a finding is the file's path.
 
-Node 24 or later. MIT.
+## `doc-budgets`
+
+```sh
+pariksha doc-budgets --table <file> [--section <name>] [--root <dir>]
+```
+
+Keeps the documents agents read on every turn inside a byte budget. The
+budgets are one Markdown table, under `## Budgets` (or `--section`) in the
+`--table` file:
+
+```md
+## Budgets
+
+| Doc         | Budget |
+| ----------- | -----: |
+| `CLAUDE.md` | 9,000  |
+```
+
+Refuses a file over its budget, a budgeted file that does not exist, and a
+row that is not `` | `path` | bytes | ``, since nothing would enforce it.
+The table file is read on every check too, so it must budget itself: a row
+for its own path (relative to `--root`) is required.
+
+## `export-deletions`
+
+```sh
+pariksha export-deletions [--base <ref>] [--root <dir>]
+```
+
+An agent that removes a public function can remove its callers and their
+tests too: everything typechecks and passes, so only a statement of intent
+tells a correct removal from a coherent mistake. This check compares
+`<base>...HEAD` and refuses an exported declaration (`export const`,
+`function`, `class`, `interface`, `type`, `enum`) that is gone from every
+TypeScript and JavaScript file at HEAD, unless a commit body in the range
+declares it:
+
+```text
+Removes-Export: <symbol> — <why it is safe to remove>
+Removes-File: <path> — <why the file is gone>
+```
+
+`Removes-File` covers every export of a file that no longer exists at HEAD.
+A symbol still used anywhere (a move, a rename with its callers, a re-export)
+is never reported; a mention in a comment does not count as a use. Bare
+`export { a, b }` lists and files under `node_modules`, `dist`, `build`,
+`coverage` and `generated` are not read. Without `--base`, the base is the
+first of `origin/main`, `origin/develop`, `origin/master` and `main` that
+exists. It reads the whole repository from any directory inside it, and
+renames, colour, external diff tools and textconv in a user's git config
+do not change what it reads. With no base, or when git cannot read the
+range (no merge base, a shallow clone), it exits 2: nothing was checked,
+so it is not a pass.

package/dist/cli.js

@@ -1,13 +1,18 @@
 #!/usr/bin/env node
-// pariksha: repository checks. v0.1 has one, `boundary`.
+// pariksha: repository checks. One subcommand per check.
 import { execFileSync } from 'node:child_process';
-import { existsSync, readFileSync, realpathSync } from 'node:fs';
-import { join, resolve } from 'node:path';
+import { existsSync, readFileSync, realpathSync, statSync } from 'node:fs';
+import { join, relative, resolve } from 'node:path';
 import { fileURLToPath } from 'node:url';
 import { findDenied, hash, isText, parseDenyList } from './boundary.js';
+import { checkBudgets } from './doc-budgets.js';
+import { checkExportDeletions, formatReport } from './export-deletions.js';
+import { BASE_CANDIDATES, gitAtTop, resolveBase } from './git.js';
 export const DENY_FILE = '.veda/deny.sha256';
 const USAGE = [
     'usage: pariksha boundary [--root <dir>] [--deny <file>]',
+    '       pariksha doc-budgets --table <file> [--section <name>] [--root <dir>]',
+    '       pariksha export-deletions [--base <ref>] [--root <dir>]',
     '       pariksha hash <word>',
     '       pariksha --version',
 ].join('\n');
@@ -29,23 +34,19 @@ export const trackedFiles = (root) => {
     }
     return files;
 };
-const flags = (rest) => {
+/** `--name value` pairs, each name allowed once and from `allowed`; undefined on anything else. */
+export const flags = (rest, allowed) => {
     const out = new Map();
     for (let i = 0; i < rest.length; i += 2) {
         const name = rest[i];
         const value = rest[i + 1];
-        if ((name !== '--root' && name !== '--deny') || !value || out.has(name))
+        if (name === undefined || !allowed.includes(name) || !value || out.has(name))
             return undefined;
         out.set(name, value);
     }
     return out;
 };
-const boundary = (rest, io) => {
-    const f = flags(rest);
-    if (!f) {
-        io.err(USAGE);
-        return 2;
-    }
+const boundary = (f, io) => {
     const root = resolve(f.get('--root') ?? '.');
     const denyPath = resolve(root, f.get('--deny') ?? DENY_FILE);
     if (!existsSync(denyPath)) {
@@ -72,6 +73,66 @@ const boundary = (rest, io) => {
     io.out(`pariksha boundary: ${files.length} files, none names a denied word (${deny.size} on the list)`);
     return 0;
 };
+const fileSize = (path) => {
+    try {
+        const s = statSync(path);
+        return s.isFile() ? s.size : undefined;
+    }
+    catch {
+        return undefined;
+    }
+};
+const docBudgets = (f, io) => {
+    const table = f.get('--table');
+    if (table === undefined) {
+        io.err(USAGE);
+        return 2;
+    }
+    const root = resolve(f.get('--root') ?? '.');
+    const tablePath = resolve(root, table);
+    if (fileSize(tablePath) === undefined) {
+        io.err(`pariksha doc-budgets: no budget table at ${tablePath}`);
+        return 2;
+    }
+    const outcome = checkBudgets(readFileSync(tablePath, 'utf8'), f.get('--section') ?? 'Budgets', relative(root, tablePath), (p) => fileSize(resolve(root, p)));
+    outcome.out.forEach(io.out);
+    outcome.err.forEach(io.err);
+    return outcome.ok ? 0 : 1;
+};
+const exportDeletions = (f, io) => {
+    const dir = resolve(f.get('--root') ?? '.');
+    const git = gitAtTop(dir);
+    if (git === undefined) {
+        io.err(`pariksha export-deletions: ${dir} is not in a git repository`);
+        return 2;
+    }
+    const asked = f.get('--base');
+    const base = asked === undefined ? resolveBase(git) : resolveBase(git, [asked]);
+    if (base === undefined) {
+        // A shallow single-branch checkout lands here; passing it would pass unread work.
+        io.err(asked === undefined
+            ? `pariksha export-deletions: none of ${BASE_CANDIDATES.join(', ')} names a commit; fetch one or pass --base`
+            : `pariksha export-deletions: --base ${asked} names no commit`);
+        return 2;
+    }
+    let report;
+    try {
+        report = checkExportDeletions(git, base);
+    }
+    catch (e) {
+        io.err(`pariksha export-deletions: ${e.message}; nothing was checked, so this is not a pass`);
+        return 2;
+    }
+    const result = formatReport(report);
+    result.out.forEach(io.out);
+    result.err.forEach(io.err);
+    return result.ok ? 0 : 1;
+};
+const COMMANDS = {
+    boundary: { allowed: ['--root', '--deny'], run: boundary },
+    'doc-budgets': { allowed: ['--table', '--section', '--root'], run: docBudgets },
+    'export-deletions': { allowed: ['--base', '--root'], run: exportDeletions },
+};
 export const run = (args, io, version = ownVersion()) => {
     const [command, ...rest] = args;
     if (command === '--version' && rest.length === 0) {
@@ -82,10 +143,13 @@ export const run = (args, io, version = ownVersion()) => {
         io.out(hash(rest[0]));
         return 0;
     }
-    if (command === 'boundary')
-        return boundary(rest, io);
-    io.err(USAGE);
-    return 2;
+    const spec = command !== undefined && Object.hasOwn(COMMANDS, command) ? COMMANDS[command] : undefined;
+    const f = spec && flags(rest, spec.allowed);
+    if (!spec || !f) {
+        io.err(USAGE);
+        return 2;
+    }
+    return spec.run(f, io);
 };
 const isMain = () => {
     const entry = process.argv[1];

package/dist/doc-budgets.js

@@ -0,0 +1,60 @@
+// The doc-budgets check: documents that agents read on every turn stay inside
+// a byte budget. The budgets live in one Markdown table, so the rule that sets
+// them is also the only list of them:
+//
+//   ## Budgets
+//
+//   | Doc         | Budget |
+//   | ----------- | -----: |
+//   | `CLAUDE.md` | 9,000  |
+/** The text of the `## <section>` section, up to the next `## ` heading; '' when absent. */
+export const section = (markdown, name) => {
+    // Line endings normalised and a leading newline added, so a CRLF file and a
+    // heading on the first line read like any other.
+    const text = `\n${markdown.replaceAll('\r\n', '\n')}`;
+    const start = text.indexOf(`\n## ${name}\n`);
+    if (start === -1)
+        return '';
+    const end = text.indexOf('\n## ', start + 1);
+    return text.slice(start, end === -1 ? undefined : end);
+};
+/** Table lines after the header row and its `| --- |` (or `|:--|`) separator. */
+export const dataRows = (text) => text
+    .split('\n')
+    .filter((line) => line.startsWith('|'))
+    .slice(1)
+    .filter((line) => !/^\|\s*:?-/.test(line));
+/** Rows of the form "| `path` | 1,200 |". */
+export const parseBudgets = (text) => [...text.matchAll(/^\|\s*`([^`]+)`\s*\|\s*([\d,]+)\s*\|$/gm)].map(([, path = '', bytes = '']) => ({
+    path,
+    bytes: Number(bytes.replaceAll(',', '')),
+}));
+/**
+ * Every budget row is well formed, and every file it names is within budget.
+ * `size` returns a file's byte length, or undefined when it does not exist.
+ */
+export const checkBudgets = (table, sectionName, tablePath, size) => {
+    const text = section(table, sectionName);
+    const budgets = parseBudgets(text);
+    const rows = dataRows(text);
+    const err = [];
+    if (rows.length === 0)
+        err.push(`pariksha doc-budgets: ${tablePath} has no table under "## ${sectionName}"`);
+    else if (budgets.length !== rows.length)
+        err.push(`pariksha doc-budgets: ${tablePath}: ${rows.length - budgets.length} row(s) under "## ${sectionName}" are not "| \`path\` | bytes |", so nothing enforces them`);
+    // The table is read on every check, so it is a hot document too; a table
+    // without its own row could grow without limit while every row it lists passes.
+    if (rows.length > 0 && !budgets.some((b) => b.path === tablePath))
+        err.push(`pariksha doc-budgets: ${tablePath} sets budgets but has no row for itself; add "| \`${tablePath}\` | <bytes> |"`);
+    const out = [];
+    for (const b of budgets) {
+        const bytes = size(b.path);
+        if (bytes === undefined)
+            err.push(`pariksha doc-budgets: ${b.path} has a budget but does not exist`);
+        else if (bytes > b.bytes)
+            err.push(`pariksha doc-budgets: ${b.path} is ${bytes} bytes, over its budget of ${b.bytes}; cut it`);
+        else
+            out.push(`pariksha doc-budgets: ${b.path} ${bytes} / ${b.bytes} bytes`);
+    }
+    return { ok: err.length === 0, out, err };
+};

package/dist/export-deletions.js

@@ -0,0 +1,125 @@
+// The export-deletions check: a public export that disappears from the whole
+// tree on a branch needs a stated reason, a commit trailer naming it.
+//
+// An agent that removes a public function can also remove its callers and the
+// tests that used it: everything typechecks and passes, so nothing internal
+// tells a correct removal from a coherent mistake. Only a statement of intent
+// can, so the check asks for one, and stays quiet for anything that moved:
+// a symbol still named anywhere in the tree's source is not reported.
+//
+//   Removes-Export: <symbol> — <why>     covers one symbol
+//   Removes-File: <path> — <why>         covers every export of a file that
+//                                        no longer exists at HEAD
+import { must } from './git.js';
+export const SOURCE_GLOBS = ['*.ts', '*.tsx', '*.js', '*.jsx', '*.mjs', '*.cjs', '*.mts', '*.cts'];
+/** Build output and vendored code never count as a source change, or as a use. */
+const SKIPPED = ['node_modules', 'dist', 'build', 'coverage', 'generated'];
+const SKIPPED_DIR = new RegExp(`(^|/)(${SKIPPED.join('|')})/`);
+const SKIPPED_PATHSPECS = SKIPPED.map((d) => `:(exclude,glob)**/${d}/**`);
+const PLAIN_DIFF = ['--no-renames', '--no-color', '--no-ext-diff', '--no-textconv'];
+/**
+ * A removed named declaration on a `-` diff line. Bare re-export lists
+ * (`export { a, b }`) are left out: they shuffle in refactors and name nothing new.
+ */
+const EXPORT_DECL = /^-\s*export\s+(?:default\s+)?(?:declare\s+)?(?:async\s+)?(?:abstract\s+)?(?:const\s+enum|const|let|var|function|class|interface|type|enum|namespace)[\s*]+([A-Za-z_$][A-Za-z0-9_$]*)/;
+/**
+ * A grep hit (`HEAD:path:line:text`) whose text starts a comment (`//`, `*`,
+ * `/*`) is a mention, not a use. Unanchored, so a colon in a path still matches.
+ */
+const COMMENT_HIT = /:\d+:\s*(?:\/\/|\*|\/\*)/;
+const unique = (xs) => [...new Set(xs)].sort();
+/** Symbols named by `Removes-Export:` trailers: the first word, trailing punctuation dropped. */
+export const declaredExports = (messages) => unique(messages
+    .split('\n')
+    .map((line) => /^\s*removes-export:\s*(\S+)/i.exec(line)?.[1]?.replace(/[,;()]+$/, ''))
+    .filter((s) => s !== undefined && s !== ''));
+/**
+ * Paths named by `Removes-File:` trailers. The path runs up to the " — " or
+ * " - " that starts the reason, so a path with a space in it survives.
+ */
+export const declaredFiles = (messages) => unique(messages
+    .split('\n')
+    .map((line) => /^\s*removes-file:\s*(.*)$/i
+    .exec(line)?.[1]
+    ?.replace(/\s+(?:—|-)\s.*$/, '')
+    .trim()
+    .replace(/[,;()]+$/, ''))
+    .filter((s) => s !== undefined && s !== ''));
+/** The symbols a unified diff removes from export declarations. */
+export const removedExports = (diff) => diff
+    .split('\n')
+    .map((line) => EXPORT_DECL.exec(line)?.[1])
+    .filter((s) => s !== undefined);
+/** True when some `git grep -n <sym> HEAD` hit is code rather than a comment. */
+export const usedOutsideComments = (hits) => hits.split('\n').some((hit) => hit !== '' && !COMMENT_HIT.test(hit));
+/**
+ * Compares `base...HEAD`: every export removed and named nowhere in HEAD's
+ * source must be declared. A git failure throws (with no merge base, say, in a
+ * shallow clone): the check cannot pass without having read the branch.
+ */
+export const checkExportDeletions = (git, base) => {
+    const messages = must(git, ['log', '--format=%B', `${base}..HEAD`]);
+    const symbols = new Set(declaredExports(messages));
+    const files = new Set(declaredFiles(messages));
+    // Renames off, so a file moved and edited lists its old path, whose removed
+    // lines the per-file diff then shows; colour, external diff tools and
+    // textconv off, so a user's config cannot rewrite the lines read here.
+    // NUL-separated, so no name comes back quoted.
+    const changed = must(git, ['diff', ...PLAIN_DIFF, '-z', '--name-only', '--diff-filter=ACMRD', `${base}...HEAD`, '--', ...SOURCE_GLOBS])
+        .split('\0')
+        .filter((f) => f !== '' && !SKIPPED_DIR.test(f));
+    const violations = [];
+    const declared = [];
+    const coveredFiles = [];
+    const used = new Map();
+    for (const file of changed) {
+        // `:(literal)` so a name like `src/[id].ts` names only itself.
+        const spec = `:(literal)${file}`;
+        const removed = removedExports(must(git, ['diff', ...PLAIN_DIFF, '-U0', `${base}...HEAD`, '--', spec]));
+        if (removed.length === 0)
+            continue;
+        // A file trailer covers a file only once HEAD has nothing at its path.
+        if (files.has(file) && must(git, ['ls-tree', '--name-only', 'HEAD', '--', spec]).trim() === '') {
+            coveredFiles.push(file);
+            continue;
+        }
+        for (const symbol of removed) {
+            let stillUsed = used.get(symbol);
+            if (stillUsed === undefined) {
+                // git grep exits 1 when nothing matches, so undefined here is "no hit".
+                // Skipped trees are excluded here too: a stale committed build naming the symbol is no use.
+                stillUsed = usedOutsideComments(git.run(['grep', '--no-color', '-nwF', '-e', symbol, 'HEAD', '--', ...SOURCE_GLOBS, ...SKIPPED_PATHSPECS]) ?? '');
+                used.set(symbol, stillUsed);
+            }
+            if (stillUsed)
+                continue;
+            (symbols.has(symbol) ? declared : violations).push({ symbol, file });
+        }
+    }
+    return { base, violations, declared, declaredFiles: coveredFiles };
+};
+/** The report as output lines; a refusal tells the author how to declare a removal. */
+export const formatReport = (report) => {
+    const out = [
+        ...report.declaredFiles.map((f) => `pariksha export-deletions: ${f} deleted; a Removes-File trailer declares its exports`),
+        ...report.declared.map((d) => `pariksha export-deletions: ${d.symbol} removed from ${d.file}; a Removes-Export trailer declares it`),
+    ];
+    if (report.violations.length === 0) {
+        out.push(`pariksha export-deletions: no undeclared export removals since ${report.base}`);
+        return { ok: true, out, err: [] };
+    }
+    const err = [
+        `pariksha export-deletions: ${report.violations.length} export(s) removed from the whole tree since ${report.base} with no stated reason:`,
+        ...report.violations.map((v) => `  ${v.symbol}   (removed from ${v.file})`),
+        '',
+        'Each is gone from every source file, not moved or renamed. If the removal is intended,',
+        'say so in a commit body:',
+        '',
+        '  Removes-Export: <symbol> — <why it is safe to remove>',
+        '',
+        'A file deleted outright can be declared once, covering all its exports:',
+        '',
+        '  Removes-File: <path> — <why the file is gone>',
+    ];
+    return { ok: false, out, err };
+};

package/dist/git.js

@@ -0,0 +1,43 @@
+// Git, as the checks read it: a function from arguments to stdout.
+import { execFileSync } from 'node:child_process';
+/**
+ * Settings that change what git prints, pinned so a user's config cannot:
+ * quoted non-ASCII paths would name no file, and a column field would hide a
+ * grep hit's text.
+ */
+export const PINNED = ['-c', 'core.quotePath=off', '-c', 'grep.column=false', '-c', 'color.ui=never'];
+export const gitAt = (root) => ({
+    run: (args) => {
+        try {
+            return execFileSync('git', [...PINNED, ...args], {
+                cwd: root,
+                encoding: 'utf8',
+                maxBuffer: 1 << 28,
+                stdio: ['ignore', 'pipe', 'ignore'],
+                timeout: 120_000,
+            });
+        }
+        catch {
+            return undefined;
+        }
+    },
+});
+/**
+ * Git at the top level of the repository holding `dir`, or undefined outside
+ * one. Paths git prints are relative to the top level, so every check runs
+ * there whichever directory it was started in.
+ */
+export const gitAtTop = (dir) => {
+    const top = gitAt(dir).run(['rev-parse', '--show-toplevel'])?.trim();
+    return top ? gitAt(top) : undefined;
+};
+/** A git call whose failure must stop the check rather than read as "nothing found". */
+export const must = (git, args) => {
+    const out = git.run(args);
+    if (out === undefined)
+        throw new Error(`git ${args.join(' ')} failed`);
+    return out;
+};
+export const BASE_CANDIDATES = ['origin/main', 'origin/develop', 'origin/master', 'main'];
+/** The first ref that names a commit, or undefined. */
+export const resolveBase = (git, candidates = BASE_CANDIDATES) => candidates.find((ref) => git.run(['rev-parse', '--verify', '--quiet', `${ref}^{commit}`]) !== undefined);

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@veda-hq/pariksha",
-  "version": "0.1.0",
-  "description": "Repository checks: doc drift, rule enforcement, test-quality ratchets. v0.1: the boundary check, which refuses any tracked file naming a denied word.",
+  "version": "0.3.1",
+  "description": "Repository checks: doc drift, rule enforcement, test-quality ratchets. Checks: boundary, doc-budgets, export-deletions.",
   "keywords": [
     "repository checks",
     "lint",