@veda-hq/pariksha 0.3.1 → 0.3.2

package/README.md

@@ -4,8 +4,8 @@
 test-quality ratchets. Part of [Veda](https://github.com/veda-hq/veda).
 
 ```sh
-npx @veda-hq/pariksha@0.3.1 <check> [flags]
-npx @veda-hq/pariksha@0.3.1 --version
+npx @veda-hq/pariksha@0.3.2 <check> [flags]
+npx @veda-hq/pariksha@0.3.2 --version
 ```
 
 Every check exits 0 when the repository passes, 1 when it refuses something
@@ -13,6 +13,37 @@ Every check exits 0 when the repository passes, 1 when it refuses something
 error. `--root <dir>` (default: the current directory) names the repository.
 Node 24 or later. MIT.
 
+## `authority-citations`
+
+```sh
+pariksha authority-citations [--mode staged|tree] [--authority <a,b>]
+  [--issue-prefix <A,B>] [--adr-dir <dir>] [--root <dir>]
+```
+
+A coherent fabrication passes every internal check: an agent that deletes a
+public API and calls the deletion "an owner decision" is consistent with
+itself. So a line that invokes an authority (`owner decision`,
+`founder decided`, `product rule`, `approved by` / `decided by` /
+`authorized by` / `mandated by` / `per` an office, a `--authority` name or an
+`@handle`) must cite, within three lines, something only that authority could
+have produced:
+
+- resolved: a commit id naming a commit here, or `ADR-NNNN` /
+  `<adr-dir>/NNNN` naming an existing `NNNN-*.md` other than the claiming file
+  (default `docs/adr`);
+- shape-checked: an issue id with a `--issue-prefix` (`ABC-123`), a GitHub
+  pull request or issue URL, or `PR #123`.
+
+`ALLOW-AUTHORITY-PHRASE: <reason>` in the window marks words used without
+asserting authority; the reason is required. TypeScript, JavaScript, SQL,
+Prisma, shell and Markdown files are read, outside `node_modules`, `dist`,
+`build`, `coverage`, `generated`, `.tmp` and `.local`.
+
+`staged` (the default, for a pre-commit or pre-merge-commit hook) judges only
+the lines the commit adds; on a merge, only lines new against every parent,
+so text a merged branch already carried is not judged again. `tree` judges
+every tracked file. When git cannot read the change it exits 2.
+
 ## `boundary`
 
 ```sh

package/dist/authority-citations.js

@@ -0,0 +1,192 @@
+// The authority-citations check: a line that invokes an authority ("owner
+// decision", "approved by the founder", "per the CTO") must cite something only
+// that authority could have produced, outside the file making the claim.
+//
+// A claim asserted inside the file it justifies cannot be checked from inside
+// that file: an agent that deletes a public API and calls it "an owner
+// decision" passes every internal-consistency gate, because a coherent
+// fabrication is consistent. So the check asks for an anchor within three lines
+// of the claim:
+//
+//   resolved here:      an ADR number whose file exists (not the claiming file),
+//                       a commit id that names a commit in this repository
+//   shape-checked only: an issue id with a configured prefix (ABC-123), a
+//                       GitHub pull request or issue URL, "PR #123"
+//
+// `ALLOW-AUTHORITY-PHRASE: <reason>` in the same window marks words that are
+// used without asserting authority; the reason is required.
+//
+// staged mode judges only lines the commit adds; on a merge, only lines new
+// against every parent, so text a merged branch already carried is not judged
+// again. tree mode judges every tracked file.
+import { existsSync, readdirSync, readFileSync, statSync } from 'node:fs';
+import { join, posix } from 'node:path';
+import { must, PLAIN_DIFF } from './git.js';
+export const DEFAULTS = { authorities: [], issuePrefixes: [], adrDir: 'docs/adr' };
+const escape = (s) => s.replace(/[.*+?^${}()|[\]\\]/g, '\\$&');
+/**
+ * An authority is a person or an office, never a subsystem: requiring one after
+ * "approved by" and "per" keeps "decided by the diff status" out.
+ */
+export const phrasePattern = (authorities) => {
+    const names = ['owner', 'founder', 'CTO', 'CEO', 'management', 'leadership', ...authorities.map(escape), '@[A-Za-z0-9._-]+'];
+    const who = `(?:the )?(?:${names.join('|')})`;
+    return new RegExp(`owner (?:decision|decided)|founder (?:decision|decided)|product rule|(?:approved|decided|authorized|mandated) by ${who}|per ${who}`, 'i');
+};
+const SOURCE_EXT = /\.(?:ts|tsx|js|jsx|mjs|cjs|mts|cts|sql|prisma|sh|md)$/;
+/** Vendored, generated and scratch trees carry no authored claims. */
+const SKIPPED_PATH = /(^|\/)(node_modules|dist|build|coverage|\.tmp|\.local|generated)\//;
+const WINDOW = 3;
+/** The lines within WINDOW of the 1-based line `center`, joined. */
+export const windowOf = (lines, center) => lines.slice(Math.max(0, center - 1 - WINDOW), center + WINDOW).join('\n');
+/** True when the window holds the pragma with a reason, or a citation that resolves. */
+export const hasCitation = (window, claimingFile, opts, git, adrFiles) => {
+    if (/ALLOW-AUTHORITY-PHRASE:[^\S\n]*\S/.test(window))
+        return true;
+    if (opts.issuePrefixes.length > 0 && new RegExp(`\\b(?:${opts.issuePrefixes.map(escape).join('|')})-[0-9]+\\b`).test(window))
+        return true;
+    if (/https:\/\/github\.com\/[A-Za-z0-9_.-]+\/[A-Za-z0-9_.-]+\/(?:pull|issues)\/[0-9]+/.test(window))
+        return true;
+    if (/\bPR #[0-9]+\b/.test(window))
+        return true;
+    for (const [, n] of window.matchAll(new RegExp(`(?:ADR-|${escape(opts.adrDir)}/)([0-9]{4})`, 'g'))) {
+        if (adrFiles.some((f) => f.startsWith(`${opts.adrDir}/${n}-`) && f.endsWith('.md') && f !== claimingFile))
+            return true;
+    }
+    for (const [sha] of window.matchAll(/\b[0-9a-f]{7,40}\b/g)) {
+        if (git.run(['cat-file', '-e', `${sha}^{commit}`]) !== undefined)
+            return true;
+    }
+    return false;
+};
+/** 1-based line numbers a `-U0` diff adds. */
+export const addedLines = (diff) => {
+    const out = new Set();
+    for (const line of diff.split('\n')) {
+        const m = /^@@ [^+]*\+([0-9]+)(?:,([0-9]+))? @@/.exec(line);
+        if (!m)
+            continue;
+        const start = Number(m[1]);
+        const count = m[2] === undefined ? 1 : Number(m[2]);
+        for (let i = 0; i < count; i++)
+            out.add(start + i);
+    }
+    return out;
+};
+/**
+ * The other parents of the merge being committed; none outside a merge.
+ * MERGE_HEAD exists once a merge stops (a conflict, --no-commit). A clean
+ * merge runs the pre-merge-commit hook before writing MERGE_HEAD, leaving only
+ * the GITHEAD_<sha> variables `git merge` exports: one counts only when git is
+ * merging (AUTO_MERGE is the index tree) and the index is exactly the clean
+ * merge of HEAD and that commit, so a stale or hand-set variable hides nothing.
+ * Anything else falls back to the HEAD diff, which judges more, never less.
+ */
+export const mergeParents = (git, env, readFile) => {
+    const parents = [];
+    const listed = readFile(must(git, ['rev-parse', '--path-format=absolute', '--git-path', 'MERGE_HEAD']).trim());
+    for (const candidate of (listed ?? '').split('\n').filter(Boolean)) {
+        const sha = git.run(['rev-parse', '-q', '--verify', `${candidate}^{commit}`])?.trim();
+        if (sha)
+            parents.push(sha);
+    }
+    // An index with unresolved conflicts has no tree, and nothing can be committed from it.
+    const indexTree = git.run(['write-tree'])?.trim();
+    if (!indexTree || git.run(['rev-parse', '-q', '--verify', 'AUTO_MERGE^{tree}'])?.trim() !== indexTree)
+        return parents;
+    for (const name of Object.keys(env)) {
+        const sha = /^GITHEAD_([0-9a-f]{40}|[0-9a-f]{64})$/.exec(name)?.[1];
+        if (sha === undefined || parents.includes(sha))
+            continue;
+        if (git.run(['merge-tree', '--write-tree', 'HEAD', sha])?.trim() === indexTree)
+            parents.push(sha);
+    }
+    return parents;
+};
+const nulList = (out) => out.split('\0').filter(Boolean);
+const literal = (file) => `:(literal)${file}`;
+/** The staged change: what the commit being made adds. */
+export const stagedSource = (git, env, readFile) => {
+    const parents = mergeParents(git, env, readFile);
+    const added = (file, against) => addedLines(must(git, ['diff', ...PLAIN_DIFF, '--cached', '-U0', ...against, '--', literal(file)]));
+    return {
+        // T: a symlink or submodule replaced by a file brings in its every line.
+        files: nulList(must(git, ['diff', ...PLAIN_DIFF, '--cached', '-z', '--name-only', '--diff-filter=ACMT'])),
+        // `:0:` names stage 0 explicitly, so a path such as `0:a.md` is read as itself.
+        content: (file) => must(git, ['show', `:0:${file}`]),
+        judged: (file) => {
+            let lines = added(file, []);
+            for (const parent of parents) {
+                const vsParent = added(file, [parent]);
+                lines = new Set([...lines].filter((n) => vsParent.has(n)));
+            }
+            return lines;
+        },
+    };
+};
+/** Every tracked file, as it is in the working tree. */
+export const treeSource = (git, root, readFile) => ({
+    files: nulList(must(git, ['ls-files', '-z'])),
+    content: (file) => readFile(join(root, file)),
+    judged: () => undefined,
+});
+/** Every uncited claim the source holds. */
+export const findUncited = (source, opts, git, adrFiles) => {
+    const phrase = phrasePattern(opts.authorities);
+    const claims = [];
+    for (const file of source.files) {
+        if (!SOURCE_EXT.test(file) || SKIPPED_PATH.test(file))
+            continue;
+        const text = source.content(file);
+        if (text === undefined || !phrase.test(text))
+            continue;
+        const lines = text.split('\n');
+        const judged = source.judged(file);
+        lines.forEach((line, i) => {
+            const n = i + 1;
+            const m = phrase.exec(line);
+            if (!m || (judged !== undefined && !judged.has(n)))
+                return;
+            if (hasCitation(windowOf(lines, n), file, opts, git, adrFiles))
+                return;
+            claims.push({ file, line: n, phrase: m[0], text: line.slice(0, 120) });
+        });
+    }
+    return claims;
+};
+/**
+ * An ADR directory as the claiming files' paths spell it: `./docs//adr/`
+ * is `docs/adr`, so an ADR citing itself is still recognised as itself.
+ */
+export const adrDirOf = (dir) => posix.normalize(dir).replace(/\/+$/, '') || '.';
+/** Files (not directories) under the ADR directory, relative to the root. */
+export const listAdrs = (root, adrDir) => {
+    const dir = join(root, adrDir);
+    return existsSync(dir) ? readdirSync(dir).filter((f) => statSync(join(dir, f)).isFile()).map((f) => `${adrDir}/${f}`) : [];
+};
+/** A file's text, or undefined when it is not there (gone, or now a directory); any other failure throws. */
+export const readOrUndefined = (path) => {
+    try {
+        return readFileSync(path, 'utf8');
+    }
+    catch (e) {
+        if (['ENOENT', 'ENOTDIR', 'EISDIR'].includes(e.code ?? ''))
+            return undefined;
+        throw e;
+    }
+};
+export const formatClaims = (claims, opts) => {
+    if (claims.length === 0)
+        return { ok: true, out: ['pariksha authority-citations: every authority claim cites an anchor'], err: [] };
+    const err = [];
+    let last = '';
+    for (const c of claims) {
+        if (c.file !== last)
+            err.push(`pariksha authority-citations: uncited authority claim(s) in ${c.file}:`);
+        last = c.file;
+        err.push(`  ${c.line}: [${c.phrase}] ${c.text}`);
+    }
+    const files = new Set(claims.map((c) => c.file)).size;
+    err.push('', 'An authority claim must anchor in something only that authority can produce. Cite one of:', '  a commit id                       (owner decision, f1a0da2d)', `  an existing ADR                   ADR-0040, in ${opts.adrDir}/`, ...(opts.issuePrefixes.length > 0 ? [`  an issue id                       ${opts.issuePrefixes[0]}-447`] : []), '  a GitHub pull request or issue    PR #269, or its full URL', 'A comment or a document an agent could have written is not a citation. If no such', 'artifact exists, the decision has not been made. Not an authority claim? Add', '  ALLOW-AUTHORITY-PHRASE: <reason>', '', `${claims.length} claim(s) across ${files} file(s).`);
+    return { ok: false, out: [], err };
+};

package/dist/cli.js

@@ -4,13 +4,15 @@ import { execFileSync } from 'node:child_process';
 import { existsSync, readFileSync, realpathSync, statSync } from 'node:fs';
 import { join, relative, resolve } from 'node:path';
 import { fileURLToPath } from 'node:url';
+import { adrDirOf, DEFAULTS, findUncited, formatClaims, listAdrs, readOrUndefined, stagedSource, treeSource } from './authority-citations.js';
 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';
+import { BASE_CANDIDATES, gitAt, gitAtTop, resolveBase, topOf } from './git.js';
 export const DENY_FILE = '.veda/deny.sha256';
 const USAGE = [
-    'usage: pariksha boundary [--root <dir>] [--deny <file>]',
+    'usage: pariksha authority-citations [--mode staged|tree] [--authority <a,b>] [--issue-prefix <A,B>] [--adr-dir <dir>] [--root <dir>]',
+    '       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>',
@@ -128,12 +130,46 @@ const exportDeletions = (f, io) => {
     result.err.forEach(io.err);
     return result.ok ? 0 : 1;
 };
+/** A comma-separated flag value as a list; empty entries dropped. */
+const list = (value) => (value ?? '').split(',').map((s) => s.trim()).filter(Boolean);
+const authorityCitations = (f, io, env) => {
+    const mode = f.get('--mode') ?? 'staged';
+    if (mode !== 'staged' && mode !== 'tree') {
+        io.err(USAGE);
+        return 2;
+    }
+    const dir = resolve(f.get('--root') ?? '.');
+    const root = topOf(dir);
+    if (root === undefined) {
+        io.err(`pariksha authority-citations: ${dir} is not in a git repository`);
+        return 2;
+    }
+    const git = gitAt(root);
+    const opts = {
+        authorities: list(f.get('--authority')),
+        issuePrefixes: list(f.get('--issue-prefix')),
+        adrDir: adrDirOf(f.get('--adr-dir') ?? DEFAULTS.adrDir),
+    };
+    let result;
+    try {
+        const source = mode === 'tree' ? treeSource(git, root, readOrUndefined) : stagedSource(git, env, readOrUndefined);
+        result = formatClaims(findUncited(source, opts, git, listAdrs(root, opts.adrDir)), opts);
+    }
+    catch (e) {
+        io.err(`pariksha authority-citations: ${e.message}; nothing was checked, so this is not a pass`);
+        return 2;
+    }
+    result.out.forEach(io.out);
+    result.err.forEach(io.err);
+    return result.ok ? 0 : 1;
+};
 const COMMANDS = {
+    'authority-citations': { allowed: ['--mode', '--authority', '--issue-prefix', '--adr-dir', '--root'], run: authorityCitations },
     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()) => {
+export const run = (args, io, version = ownVersion(), env = process.env) => {
     const [command, ...rest] = args;
     if (command === '--version' && rest.length === 0) {
         io.out(version);
@@ -149,7 +185,7 @@ export const run = (args, io, version = ownVersion()) => {
         io.err(USAGE);
         return 2;
     }
-    return spec.run(f, io);
+    return spec.run(f, io, env);
 };
 const isMain = () => {
     const entry = process.argv[1];

package/dist/export-deletions.js

@@ -10,13 +10,12 @@
 //   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';
+import { must, PLAIN_DIFF } 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.

package/dist/git.js

@@ -5,12 +5,17 @@ import { execFileSync } from 'node:child_process';
  * 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 PINNED = ['-c', 'core.quotePath=off', '-c', 'grep.column=false', '-c', 'color.ui=never', '-c', 'core.precomposeUnicode=false'];
+/** Variables that change how git reads a pathspec, so `:(literal)` would name no file. */
+const PATHSPEC_ENV = ['GIT_LITERAL_PATHSPECS', 'GIT_GLOB_PATHSPECS', 'GIT_NOGLOB_PATHSPECS', 'GIT_ICASE_PATHSPECS'];
+/** The environment git runs in: the caller's, less the pathspec switches. */
+export const gitEnv = (env) => Object.fromEntries(Object.entries(env).filter(([k]) => !PATHSPEC_ENV.includes(k)));
 export const gitAt = (root) => ({
     run: (args) => {
         try {
             return execFileSync('git', [...PINNED, ...args], {
                 cwd: root,
+                env: gitEnv(process.env),
                 encoding: 'utf8',
                 maxBuffer: 1 << 28,
                 stdio: ['ignore', 'pipe', 'ignore'],
@@ -28,9 +33,17 @@ export const gitAt = (root) => ({
  * 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;
+    const top = topOf(dir);
+    return top === undefined ? undefined : gitAt(top);
 };
+/** The top level of the repository holding `dir`, or undefined outside one. */
+export const topOf = (dir) => gitAt(dir).run(['rev-parse', '--show-toplevel'])?.trim() || undefined;
+/**
+ * Diff output a user's config cannot reshape: no colour, external tool,
+ * textconv or rename pairing, and lines even for a file git or its
+ * attributes class as binary, which would otherwise show no hunk at all.
+ */
+export const PLAIN_DIFF = ['--no-renames', '--no-color', '--no-ext-diff', '--no-textconv', '--text'];
 /** 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);

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@veda-hq/pariksha",
-  "version": "0.3.1",
-  "description": "Repository checks: doc drift, rule enforcement, test-quality ratchets. Checks: boundary, doc-budgets, export-deletions.",
+  "version": "0.3.2",
+  "description": "Repository checks: doc drift, rule enforcement, test-quality ratchets. Checks: authority-citations, boundary, doc-budgets, export-deletions.",
   "keywords": [
     "repository checks",
     "lint",